Hugging Face's logo

jinyuan222
/
visualprm400K-random8

TensorBoard
Safetensors
internvl_chat
custom_code
Model card Files
xet
 Metrics Community
jinyuan222 commited on
Commit
d8a473b
·
verified ·
1 Parent(s): f07f200

Add files using upload-large-folder tool

Browse files
Files changed (45) hide show
  1. added_tokens.json +12 -0
  2. all_results.json +9 -0
  3. checkpoint-50/added_tokens.json +12 -0
  4. checkpoint-50/config.json +206 -0
  5. checkpoint-50/generation_config.json +8 -0
  6. checkpoint-50/model-00001-of-00004.safetensors +3 -0
  7. checkpoint-50/model-00002-of-00004.safetensors +3 -0
  8. checkpoint-50/model-00003-of-00004.safetensors +3 -0
  9. checkpoint-50/model-00004-of-00004.safetensors +3 -0
  10. checkpoint-50/model.safetensors.index.json +580 -0
  11. checkpoint-50/special_tokens_map.json +54 -0
  12. checkpoint-50/tokenization_internlm2.py +235 -0
  13. checkpoint-50/tokenizer.model +3 -0
  14. checkpoint-50/tokenizer_config.json +189 -0
  15. checkpoint-50/trainer_state.json +383 -0
  16. checkpoint-50/training_args.bin +3 -0
  17. checkpoint-84/added_tokens.json +12 -0
  18. checkpoint-84/config.json +206 -0
  19. checkpoint-84/generation_config.json +8 -0
  20. checkpoint-84/model-00001-of-00004.safetensors +3 -0
  21. checkpoint-84/model-00002-of-00004.safetensors +3 -0
  22. checkpoint-84/model-00003-of-00004.safetensors +3 -0
  23. checkpoint-84/model-00004-of-00004.safetensors +3 -0
  24. checkpoint-84/model.safetensors.index.json +580 -0
  25. checkpoint-84/special_tokens_map.json +54 -0
  26. checkpoint-84/tokenization_internlm2.py +235 -0
  27. checkpoint-84/tokenizer.model +3 -0
  28. checkpoint-84/tokenizer_config.json +189 -0
  29. checkpoint-84/trainer_state.json +621 -0
  30. checkpoint-84/training_args.bin +3 -0
  31. config.json +206 -0
  32. generation_config.json +8 -0
  33. model-00001-of-00004.safetensors +3 -0
  34. model-00002-of-00004.safetensors +3 -0
  35. model-00003-of-00004.safetensors +3 -0
  36. model-00004-of-00004.safetensors +3 -0
  37. model.safetensors.index.json +580 -0
  38. runs/Apr06_03-40-24_brev-mnism5o8g/events.out.tfevents.1775446875.brev-mnism5o8g.2636796.0 +3 -0
  39. special_tokens_map.json +54 -0
  40. tokenization_internlm2.py +235 -0
  41. tokenizer.model +3 -0
  42. tokenizer_config.json +189 -0
  43. train_results.json +9 -0
  44. training_args.bin +3 -0
  45. training_log.txt +0 -0
added_tokens.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</box>": 92552,
3
+ "</img>": 92545,
4
+ "</quad>": 92548,
5
+ "</ref>": 92550,
6
+ "<IMG_CONTEXT>": 92546,
7
+ "<box>": 92551,
8
+ "<img>": 92544,
9
+ "<prm>": 92553,
10
+ "<quad>": 92547,
11
+ "<ref>": 92549
12
+ }
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9926144756277696,
3
+ "total_flos": 2.4692764709042835e+20,
4
+ "train_loss": 3.329987657921655,
5
+ "train_runtime": 7432.7063,
6
+ "train_samples": 43323,
7
+ "train_samples_per_second": 5.829,
8
+ "train_steps_per_second": 0.011
9
+ }
checkpoint-50/added_tokens.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</box>": 92552,
3
+ "</img>": 92545,
4
+ "</quad>": 92548,
5
+ "</ref>": 92550,
6
+ "<IMG_CONTEXT>": 92546,
7
+ "<box>": 92551,
8
+ "<img>": 92544,
9
+ "<prm>": 92553,
10
+ "<quad>": 92547,
11
+ "<ref>": 92549
12
+ }
checkpoint-50/config.json ADDED
@@ -0,0 +1,206 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": "e9e4c0dc1db56bfab10458671519b7fa3dd29463",
3
+ "_name_or_path": "OpenGVLab/InternVL2_5-8B",
4
+ "architectures": [
5
+ "InternVLChatModel"
6
+ ],
7
+ "auto_map": {
8
+ "AutoConfig": "OpenGVLab/InternVL2_5-8B--configuration_internvl_chat.InternVLChatConfig",
9
+ "AutoModel": "OpenGVLab/InternVL2_5-8B--modeling_internvl_chat.InternVLChatModel",
10
+ "AutoModelForCausalLM": "OpenGVLab/InternVL2_5-8B--modeling_internvl_chat.InternVLChatModel"
11
+ },
12
+ "downsample_ratio": 0.5,
13
+ "dynamic_image_size": true,
14
+ "force_image_size": 448,
15
+ "hidden_size": 4096,
16
+ "llm_config": {
17
+ "_attn_implementation_autoset": true,
18
+ "_name_or_path": "internlm/internlm2_5-7b-chat",
19
+ "add_cross_attention": false,
20
+ "architectures": [
21
+ "InternLM2ForCausalLM"
22
+ ],
23
+ "attn_implementation": "flash_attention_2",
24
+ "auto_map": {
25
+ "AutoConfig": "configuration_internlm2.InternLM2Config",
26
+ "AutoModel": "modeling_internlm2.InternLM2ForCausalLM",
27
+ "AutoModelForCausalLM": "modeling_internlm2.InternLM2ForCausalLM",
28
+ "AutoModelForSequenceClassification": "modeling_internlm2.InternLM2ForSequenceClassification"
29
+ },
30
+ "bad_words_ids": null,
31
+ "begin_suppress_tokens": null,
32
+ "bias": false,
33
+ "bos_token_id": 1,
34
+ "chunk_size_feed_forward": 0,
35
+ "cross_attention_hidden_size": null,
36
+ "decoder_start_token_id": null,
37
+ "diversity_penalty": 0.0,
38
+ "do_sample": false,
39
+ "early_stopping": false,
40
+ "encoder_no_repeat_ngram_size": 0,
41
+ "eos_token_id": 2,
42
+ "exponential_decay_length_penalty": null,
43
+ "finetuning_task": null,
44
+ "forced_bos_token_id": null,
45
+ "forced_eos_token_id": null,
46
+ "hidden_act": "silu",
47
+ "hidden_size": 4096,
48
+ "id2label": {
49
+ "0": "LABEL_0",
50
+ "1": "LABEL_1"
51
+ },
52
+ "initializer_range": 0.02,
53
+ "intermediate_size": 14336,
54
+ "is_decoder": false,
55
+ "is_encoder_decoder": false,
56
+ "label2id": {
57
+ "LABEL_0": 0,
58
+ "LABEL_1": 1
59
+ },
60
+ "length_penalty": 1.0,
61
+ "max_length": 20,
62
+ "max_position_embeddings": 32768,
63
+ "min_length": 0,
64
+ "model_type": "internlm2",
65
+ "no_repeat_ngram_size": 0,
66
+ "num_attention_heads": 32,
67
+ "num_beam_groups": 1,
68
+ "num_beams": 1,
69
+ "num_hidden_layers": 32,
70
+ "num_key_value_heads": 8,
71
+ "num_return_sequences": 1,
72
+ "output_attentions": false,
73
+ "output_hidden_states": false,
74
+ "output_scores": false,
75
+ "pad_token_id": 2,
76
+ "prefix": null,
77
+ "pretraining_tp": 1,
78
+ "problem_type": null,
79
+ "pruned_heads": {},
80
+ "remove_invalid_values": false,
81
+ "repetition_penalty": 1.0,
82
+ "return_dict": true,
83
+ "return_dict_in_generate": false,
84
+ "rms_norm_eps": 1e-05,
85
+ "rope_scaling": {
86
+ "factor": 2.0,
87
+ "type": "dynamic"
88
+ },
89
+ "rope_theta": 1000000,
90
+ "sep_token_id": null,
91
+ "suppress_tokens": null,
92
+ "task_specific_params": null,
93
+ "temperature": 1.0,
94
+ "tf_legacy_loss": false,
95
+ "tie_encoder_decoder": false,
96
+ "tie_word_embeddings": false,
97
+ "tokenizer_class": null,
98
+ "top_k": 50,
99
+ "top_p": 1.0,
100
+ "torch_dtype": "bfloat16",
101
+ "torchscript": false,
102
+ "transformers_version": "4.47.1",
103
+ "typical_p": 1.0,
104
+ "use_bfloat16": true,
105
+ "use_cache": false,
106
+ "vocab_size": 92554
107
+ },
108
+ "max_dynamic_patch": 6,
109
+ "min_dynamic_patch": 1,
110
+ "model_type": "internvl_chat",
111
+ "pad2square": false,
112
+ "ps_version": "v2",
113
+ "select_layer": -1,
114
+ "template": "internvl2_5",
115
+ "tie_word_embeddings": false,
116
+ "torch_dtype": "bfloat16",
117
+ "transformers_version": null,
118
+ "use_backbone_lora": 0,
119
+ "use_llm_lora": 0,
120
+ "use_thumbnail": true,
121
+ "vision_config": {
122
+ "_attn_implementation_autoset": true,
123
+ "_name_or_path": "",
124
+ "add_cross_attention": false,
125
+ "architectures": [
126
+ "InternVisionModel"
127
+ ],
128
+ "attention_dropout": 0.0,
129
+ "bad_words_ids": null,
130
+ "begin_suppress_tokens": null,
131
+ "bos_token_id": null,
132
+ "chunk_size_feed_forward": 0,
133
+ "cross_attention_hidden_size": null,
134
+ "decoder_start_token_id": null,
135
+ "diversity_penalty": 0.0,
136
+ "do_sample": false,
137
+ "drop_path_rate": 0.4,
138
+ "dropout": 0.0,
139
+ "early_stopping": false,
140
+ "encoder_no_repeat_ngram_size": 0,
141
+ "eos_token_id": null,
142
+ "exponential_decay_length_penalty": null,
143
+ "finetuning_task": null,
144
+ "forced_bos_token_id": null,
145
+ "forced_eos_token_id": null,
146
+ "hidden_act": "gelu",
147
+ "hidden_size": 1024,
148
+ "id2label": {
149
+ "0": "LABEL_0",
150
+ "1": "LABEL_1"
151
+ },
152
+ "image_size": 448,
153
+ "initializer_factor": 1.0,
154
+ "initializer_range": 0.02,
155
+ "intermediate_size": 4096,
156
+ "is_decoder": false,
157
+ "is_encoder_decoder": false,
158
+ "label2id": {
159
+ "LABEL_0": 0,
160
+ "LABEL_1": 1
161
+ },
162
+ "layer_norm_eps": 1e-06,
163
+ "length_penalty": 1.0,
164
+ "max_length": 20,
165
+ "min_length": 0,
166
+ "model_type": "intern_vit_6b",
167
+ "no_repeat_ngram_size": 0,
168
+ "norm_type": "layer_norm",
169
+ "num_attention_heads": 16,
170
+ "num_beam_groups": 1,
171
+ "num_beams": 1,
172
+ "num_channels": 3,
173
+ "num_hidden_layers": 24,
174
+ "num_return_sequences": 1,
175
+ "output_attentions": false,
176
+ "output_hidden_states": false,
177
+ "output_scores": false,
178
+ "pad_token_id": null,
179
+ "patch_size": 14,
180
+ "prefix": null,
181
+ "problem_type": null,
182
+ "pruned_heads": {},
183
+ "qk_normalization": false,
184
+ "qkv_bias": true,
185
+ "remove_invalid_values": false,
186
+ "repetition_penalty": 1.0,
187
+ "return_dict": true,
188
+ "return_dict_in_generate": false,
189
+ "sep_token_id": null,
190
+ "suppress_tokens": null,
191
+ "task_specific_params": null,
192
+ "temperature": 1.0,
193
+ "tf_legacy_loss": false,
194
+ "tie_encoder_decoder": false,
195
+ "tie_word_embeddings": true,
196
+ "tokenizer_class": null,
197
+ "top_k": 50,
198
+ "top_p": 1.0,
199
+ "torch_dtype": "bfloat16",
200
+ "torchscript": false,
201
+ "transformers_version": "4.47.1",
202
+ "typical_p": 1.0,
203
+ "use_bfloat16": true,
204
+ "use_flash_attn": true
205
+ }
206
+ }
checkpoint-50/generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": [
4
+ 92542,
5
+ 92543
6
+ ],
7
+ "transformers_version": "4.47.1"
8
+ }
checkpoint-50/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d05cafe69873313c96b8b8894c5dccb87a9219997cb871ac1b3c842ad1139d0
3
+ size 4939952528
checkpoint-50/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62938d79bd001df4127f0381c1586f521965addd08d65d397487b981b3f5c71e
3
+ size 4915914584
checkpoint-50/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cde6a52acef83cd2bb173d8c6cd4b61543927c3a699b8c31cc1e44b53650dca5
3
+ size 4915914592
checkpoint-50/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9837fd9a775f9cb10ef20e9425ac6d733d49b2d54cf950f834c088433fc6f73
3
+ size 1379035112
checkpoint-50/model.safetensors.index.json ADDED
@@ -0,0 +1,580 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16150747136
4
+ },
5
+ "weight_map": {
6
+ "language_model.model.layers.0.attention.wo.weight": "model-00001-of-00004.safetensors",
7
+ "language_model.model.layers.0.attention.wqkv.weight": "model-00001-of-00004.safetensors",
8
+ "language_model.model.layers.0.attention_norm.weight": "model-00001-of-00004.safetensors",
9
+ "language_model.model.layers.0.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
10
+ "language_model.model.layers.0.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
11
+ "language_model.model.layers.0.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
12
+ "language_model.model.layers.0.ffn_norm.weight": "model-00001-of-00004.safetensors",
13
+ "language_model.model.layers.1.attention.wo.weight": "model-00001-of-00004.safetensors",
14
+ "language_model.model.layers.1.attention.wqkv.weight": "model-00001-of-00004.safetensors",
15
+ "language_model.model.layers.1.attention_norm.weight": "model-00001-of-00004.safetensors",
16
+ "language_model.model.layers.1.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
17
+ "language_model.model.layers.1.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
18
+ "language_model.model.layers.1.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
19
+ "language_model.model.layers.1.ffn_norm.weight": "model-00001-of-00004.safetensors",
20
+ "language_model.model.layers.10.attention.wo.weight": "model-00002-of-00004.safetensors",
21
+ "language_model.model.layers.10.attention.wqkv.weight": "model-00002-of-00004.safetensors",
22
+ "language_model.model.layers.10.attention_norm.weight": "model-00002-of-00004.safetensors",
23
+ "language_model.model.layers.10.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
24
+ "language_model.model.layers.10.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
25
+ "language_model.model.layers.10.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
26
+ "language_model.model.layers.10.ffn_norm.weight": "model-00002-of-00004.safetensors",
27
+ "language_model.model.layers.11.attention.wo.weight": "model-00002-of-00004.safetensors",
28
+ "language_model.model.layers.11.attention.wqkv.weight": "model-00002-of-00004.safetensors",
29
+ "language_model.model.layers.11.attention_norm.weight": "model-00002-of-00004.safetensors",
30
+ "language_model.model.layers.11.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
31
+ "language_model.model.layers.11.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
32
+ "language_model.model.layers.11.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
33
+ "language_model.model.layers.11.ffn_norm.weight": "model-00002-of-00004.safetensors",
34
+ "language_model.model.layers.12.attention.wo.weight": "model-00002-of-00004.safetensors",
35
+ "language_model.model.layers.12.attention.wqkv.weight": "model-00002-of-00004.safetensors",
36
+ "language_model.model.layers.12.attention_norm.weight": "model-00002-of-00004.safetensors",
37
+ "language_model.model.layers.12.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
38
+ "language_model.model.layers.12.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
39
+ "language_model.model.layers.12.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
40
+ "language_model.model.layers.12.ffn_norm.weight": "model-00002-of-00004.safetensors",
41
+ "language_model.model.layers.13.attention.wo.weight": "model-00002-of-00004.safetensors",
42
+ "language_model.model.layers.13.attention.wqkv.weight": "model-00002-of-00004.safetensors",
43
+ "language_model.model.layers.13.attention_norm.weight": "model-00002-of-00004.safetensors",
44
+ "language_model.model.layers.13.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
45
+ "language_model.model.layers.13.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
46
+ "language_model.model.layers.13.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
47
+ "language_model.model.layers.13.ffn_norm.weight": "model-00002-of-00004.safetensors",
48
+ "language_model.model.layers.14.attention.wo.weight": "model-00002-of-00004.safetensors",
49
+ "language_model.model.layers.14.attention.wqkv.weight": "model-00002-of-00004.safetensors",
50
+ "language_model.model.layers.14.attention_norm.weight": "model-00002-of-00004.safetensors",
51
+ "language_model.model.layers.14.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
52
+ "language_model.model.layers.14.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
53
+ "language_model.model.layers.14.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
54
+ "language_model.model.layers.14.ffn_norm.weight": "model-00002-of-00004.safetensors",
55
+ "language_model.model.layers.15.attention.wo.weight": "model-00002-of-00004.safetensors",
56
+ "language_model.model.layers.15.attention.wqkv.weight": "model-00002-of-00004.safetensors",
57
+ "language_model.model.layers.15.attention_norm.weight": "model-00002-of-00004.safetensors",
58
+ "language_model.model.layers.15.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
59
+ "language_model.model.layers.15.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
60
+ "language_model.model.layers.15.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
61
+ "language_model.model.layers.15.ffn_norm.weight": "model-00002-of-00004.safetensors",
62
+ "language_model.model.layers.16.attention.wo.weight": "model-00002-of-00004.safetensors",
63
+ "language_model.model.layers.16.attention.wqkv.weight": "model-00002-of-00004.safetensors",
64
+ "language_model.model.layers.16.attention_norm.weight": "model-00002-of-00004.safetensors",
65
+ "language_model.model.layers.16.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
66
+ "language_model.model.layers.16.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
67
+ "language_model.model.layers.16.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
68
+ "language_model.model.layers.16.ffn_norm.weight": "model-00002-of-00004.safetensors",
69
+ "language_model.model.layers.17.attention.wo.weight": "model-00002-of-00004.safetensors",
70
+ "language_model.model.layers.17.attention.wqkv.weight": "model-00002-of-00004.safetensors",
71
+ "language_model.model.layers.17.attention_norm.weight": "model-00002-of-00004.safetensors",
72
+ "language_model.model.layers.17.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
73
+ "language_model.model.layers.17.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
74
+ "language_model.model.layers.17.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
75
+ "language_model.model.layers.17.ffn_norm.weight": "model-00002-of-00004.safetensors",
76
+ "language_model.model.layers.18.attention.wo.weight": "model-00002-of-00004.safetensors",
77
+ "language_model.model.layers.18.attention.wqkv.weight": "model-00002-of-00004.safetensors",
78
+ "language_model.model.layers.18.attention_norm.weight": "model-00002-of-00004.safetensors",
79
+ "language_model.model.layers.18.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
80
+ "language_model.model.layers.18.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
81
+ "language_model.model.layers.18.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
82
+ "language_model.model.layers.18.ffn_norm.weight": "model-00002-of-00004.safetensors",
83
+ "language_model.model.layers.19.attention.wo.weight": "model-00002-of-00004.safetensors",
84
+ "language_model.model.layers.19.attention.wqkv.weight": "model-00002-of-00004.safetensors",
85
+ "language_model.model.layers.19.attention_norm.weight": "model-00003-of-00004.safetensors",
86
+ "language_model.model.layers.19.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
87
+ "language_model.model.layers.19.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
88
+ "language_model.model.layers.19.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
89
+ "language_model.model.layers.19.ffn_norm.weight": "model-00003-of-00004.safetensors",
90
+ "language_model.model.layers.2.attention.wo.weight": "model-00001-of-00004.safetensors",
91
+ "language_model.model.layers.2.attention.wqkv.weight": "model-00001-of-00004.safetensors",
92
+ "language_model.model.layers.2.attention_norm.weight": "model-00001-of-00004.safetensors",
93
+ "language_model.model.layers.2.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
94
+ "language_model.model.layers.2.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
95
+ "language_model.model.layers.2.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
96
+ "language_model.model.layers.2.ffn_norm.weight": "model-00001-of-00004.safetensors",
97
+ "language_model.model.layers.20.attention.wo.weight": "model-00003-of-00004.safetensors",
98
+ "language_model.model.layers.20.attention.wqkv.weight": "model-00003-of-00004.safetensors",
99
+ "language_model.model.layers.20.attention_norm.weight": "model-00003-of-00004.safetensors",
100
+ "language_model.model.layers.20.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
101
+ "language_model.model.layers.20.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
102
+ "language_model.model.layers.20.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
103
+ "language_model.model.layers.20.ffn_norm.weight": "model-00003-of-00004.safetensors",
104
+ "language_model.model.layers.21.attention.wo.weight": "model-00003-of-00004.safetensors",
105
+ "language_model.model.layers.21.attention.wqkv.weight": "model-00003-of-00004.safetensors",
106
+ "language_model.model.layers.21.attention_norm.weight": "model-00003-of-00004.safetensors",
107
+ "language_model.model.layers.21.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
108
+ "language_model.model.layers.21.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
109
+ "language_model.model.layers.21.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
110
+ "language_model.model.layers.21.ffn_norm.weight": "model-00003-of-00004.safetensors",
111
+ "language_model.model.layers.22.attention.wo.weight": "model-00003-of-00004.safetensors",
112
+ "language_model.model.layers.22.attention.wqkv.weight": "model-00003-of-00004.safetensors",
113
+ "language_model.model.layers.22.attention_norm.weight": "model-00003-of-00004.safetensors",
114
+ "language_model.model.layers.22.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
115
+ "language_model.model.layers.22.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
116
+ "language_model.model.layers.22.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
117
+ "language_model.model.layers.22.ffn_norm.weight": "model-00003-of-00004.safetensors",
118
+ "language_model.model.layers.23.attention.wo.weight": "model-00003-of-00004.safetensors",
119
+ "language_model.model.layers.23.attention.wqkv.weight": "model-00003-of-00004.safetensors",
120
+ "language_model.model.layers.23.attention_norm.weight": "model-00003-of-00004.safetensors",
121
+ "language_model.model.layers.23.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
122
+ "language_model.model.layers.23.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
123
+ "language_model.model.layers.23.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
124
+ "language_model.model.layers.23.ffn_norm.weight": "model-00003-of-00004.safetensors",
125
+ "language_model.model.layers.24.attention.wo.weight": "model-00003-of-00004.safetensors",
126
+ "language_model.model.layers.24.attention.wqkv.weight": "model-00003-of-00004.safetensors",
127
+ "language_model.model.layers.24.attention_norm.weight": "model-00003-of-00004.safetensors",
128
+ "language_model.model.layers.24.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
129
+ "language_model.model.layers.24.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
130
+ "language_model.model.layers.24.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
131
+ "language_model.model.layers.24.ffn_norm.weight": "model-00003-of-00004.safetensors",
132
+ "language_model.model.layers.25.attention.wo.weight": "model-00003-of-00004.safetensors",
133
+ "language_model.model.layers.25.attention.wqkv.weight": "model-00003-of-00004.safetensors",
134
+ "language_model.model.layers.25.attention_norm.weight": "model-00003-of-00004.safetensors",
135
+ "language_model.model.layers.25.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
136
+ "language_model.model.layers.25.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
137
+ "language_model.model.layers.25.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
138
+ "language_model.model.layers.25.ffn_norm.weight": "model-00003-of-00004.safetensors",
139
+ "language_model.model.layers.26.attention.wo.weight": "model-00003-of-00004.safetensors",
140
+ "language_model.model.layers.26.attention.wqkv.weight": "model-00003-of-00004.safetensors",
141
+ "language_model.model.layers.26.attention_norm.weight": "model-00003-of-00004.safetensors",
142
+ "language_model.model.layers.26.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
143
+ "language_model.model.layers.26.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
144
+ "language_model.model.layers.26.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
145
+ "language_model.model.layers.26.ffn_norm.weight": "model-00003-of-00004.safetensors",
146
+ "language_model.model.layers.27.attention.wo.weight": "model-00003-of-00004.safetensors",
147
+ "language_model.model.layers.27.attention.wqkv.weight": "model-00003-of-00004.safetensors",
148
+ "language_model.model.layers.27.attention_norm.weight": "model-00003-of-00004.safetensors",
149
+ "language_model.model.layers.27.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
150
+ "language_model.model.layers.27.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
151
+ "language_model.model.layers.27.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
152
+ "language_model.model.layers.27.ffn_norm.weight": "model-00003-of-00004.safetensors",
153
+ "language_model.model.layers.28.attention.wo.weight": "model-00003-of-00004.safetensors",
154
+ "language_model.model.layers.28.attention.wqkv.weight": "model-00003-of-00004.safetensors",
155
+ "language_model.model.layers.28.attention_norm.weight": "model-00003-of-00004.safetensors",
156
+ "language_model.model.layers.28.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
157
+ "language_model.model.layers.28.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
158
+ "language_model.model.layers.28.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
159
+ "language_model.model.layers.28.ffn_norm.weight": "model-00003-of-00004.safetensors",
160
+ "language_model.model.layers.29.attention.wo.weight": "model-00003-of-00004.safetensors",
161
+ "language_model.model.layers.29.attention.wqkv.weight": "model-00003-of-00004.safetensors",
162
+ "language_model.model.layers.29.attention_norm.weight": "model-00003-of-00004.safetensors",
163
+ "language_model.model.layers.29.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
164
+ "language_model.model.layers.29.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
165
+ "language_model.model.layers.29.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
166
+ "language_model.model.layers.29.ffn_norm.weight": "model-00003-of-00004.safetensors",
167
+ "language_model.model.layers.3.attention.wo.weight": "model-00001-of-00004.safetensors",
168
+ "language_model.model.layers.3.attention.wqkv.weight": "model-00001-of-00004.safetensors",
169
+ "language_model.model.layers.3.attention_norm.weight": "model-00001-of-00004.safetensors",
170
+ "language_model.model.layers.3.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
171
+ "language_model.model.layers.3.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
172
+ "language_model.model.layers.3.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
173
+ "language_model.model.layers.3.ffn_norm.weight": "model-00001-of-00004.safetensors",
174
+ "language_model.model.layers.30.attention.wo.weight": "model-00003-of-00004.safetensors",
175
+ "language_model.model.layers.30.attention.wqkv.weight": "model-00003-of-00004.safetensors",
176
+ "language_model.model.layers.30.attention_norm.weight": "model-00004-of-00004.safetensors",
177
+ "language_model.model.layers.30.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
178
+ "language_model.model.layers.30.feed_forward.w2.weight": "model-00004-of-00004.safetensors",
179
+ "language_model.model.layers.30.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
180
+ "language_model.model.layers.30.ffn_norm.weight": "model-00004-of-00004.safetensors",
181
+ "language_model.model.layers.31.attention.wo.weight": "model-00004-of-00004.safetensors",
182
+ "language_model.model.layers.31.attention.wqkv.weight": "model-00004-of-00004.safetensors",
183
+ "language_model.model.layers.31.attention_norm.weight": "model-00004-of-00004.safetensors",
184
+ "language_model.model.layers.31.feed_forward.w1.weight": "model-00004-of-00004.safetensors",
185
+ "language_model.model.layers.31.feed_forward.w2.weight": "model-00004-of-00004.safetensors",
186
+ "language_model.model.layers.31.feed_forward.w3.weight": "model-00004-of-00004.safetensors",
187
+ "language_model.model.layers.31.ffn_norm.weight": "model-00004-of-00004.safetensors",
188
+ "language_model.model.layers.4.attention.wo.weight": "model-00001-of-00004.safetensors",
189
+ "language_model.model.layers.4.attention.wqkv.weight": "model-00001-of-00004.safetensors",
190
+ "language_model.model.layers.4.attention_norm.weight": "model-00001-of-00004.safetensors",
191
+ "language_model.model.layers.4.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
192
+ "language_model.model.layers.4.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
193
+ "language_model.model.layers.4.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
194
+ "language_model.model.layers.4.ffn_norm.weight": "model-00001-of-00004.safetensors",
195
+ "language_model.model.layers.5.attention.wo.weight": "model-00001-of-00004.safetensors",
196
+ "language_model.model.layers.5.attention.wqkv.weight": "model-00001-of-00004.safetensors",
197
+ "language_model.model.layers.5.attention_norm.weight": "model-00001-of-00004.safetensors",
198
+ "language_model.model.layers.5.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
199
+ "language_model.model.layers.5.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
200
+ "language_model.model.layers.5.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
201
+ "language_model.model.layers.5.ffn_norm.weight": "model-00001-of-00004.safetensors",
202
+ "language_model.model.layers.6.attention.wo.weight": "model-00001-of-00004.safetensors",
203
+ "language_model.model.layers.6.attention.wqkv.weight": "model-00001-of-00004.safetensors",
204
+ "language_model.model.layers.6.attention_norm.weight": "model-00001-of-00004.safetensors",
205
+ "language_model.model.layers.6.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
206
+ "language_model.model.layers.6.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
207
+ "language_model.model.layers.6.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
208
+ "language_model.model.layers.6.ffn_norm.weight": "model-00001-of-00004.safetensors",
209
+ "language_model.model.layers.7.attention.wo.weight": "model-00001-of-00004.safetensors",
210
+ "language_model.model.layers.7.attention.wqkv.weight": "model-00001-of-00004.safetensors",
211
+ "language_model.model.layers.7.attention_norm.weight": "model-00001-of-00004.safetensors",
212
+ "language_model.model.layers.7.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
213
+ "language_model.model.layers.7.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
214
+ "language_model.model.layers.7.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
215
+ "language_model.model.layers.7.ffn_norm.weight": "model-00001-of-00004.safetensors",
216
+ "language_model.model.layers.8.attention.wo.weight": "model-00001-of-00004.safetensors",
217
+ "language_model.model.layers.8.attention.wqkv.weight": "model-00001-of-00004.safetensors",
218
+ "language_model.model.layers.8.attention_norm.weight": "model-00002-of-00004.safetensors",
219
+ "language_model.model.layers.8.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
220
+ "language_model.model.layers.8.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
221
+ "language_model.model.layers.8.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
222
+ "language_model.model.layers.8.ffn_norm.weight": "model-00002-of-00004.safetensors",
223
+ "language_model.model.layers.9.attention.wo.weight": "model-00002-of-00004.safetensors",
224
+ "language_model.model.layers.9.attention.wqkv.weight": "model-00002-of-00004.safetensors",
225
+ "language_model.model.layers.9.attention_norm.weight": "model-00002-of-00004.safetensors",
226
+ "language_model.model.layers.9.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
227
+ "language_model.model.layers.9.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
228
+ "language_model.model.layers.9.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
229
+ "language_model.model.layers.9.ffn_norm.weight": "model-00002-of-00004.safetensors",
230
+ "language_model.model.norm.weight": "model-00004-of-00004.safetensors",
231
+ "language_model.model.tok_embeddings.weight": "model-00001-of-00004.safetensors",
232
+ "language_model.output.weight": "model-00004-of-00004.safetensors",
233
+ "mlp1.0.bias": "model-00004-of-00004.safetensors",
234
+ "mlp1.0.weight": "model-00004-of-00004.safetensors",
235
+ "mlp1.1.bias": "model-00004-of-00004.safetensors",
236
+ "mlp1.1.weight": "model-00004-of-00004.safetensors",
237
+ "mlp1.3.bias": "model-00004-of-00004.safetensors",
238
+ "mlp1.3.weight": "model-00004-of-00004.safetensors",
239
+ "vision_model.embeddings.class_embedding": "model-00001-of-00004.safetensors",
240
+ "vision_model.embeddings.patch_embedding.bias": "model-00001-of-00004.safetensors",
241
+ "vision_model.embeddings.patch_embedding.weight": "model-00001-of-00004.safetensors",
242
+ "vision_model.embeddings.position_embedding": "model-00001-of-00004.safetensors",
243
+ "vision_model.encoder.layers.0.attn.proj.bias": "model-00001-of-00004.safetensors",
244
+ "vision_model.encoder.layers.0.attn.proj.weight": "model-00001-of-00004.safetensors",
245
+ "vision_model.encoder.layers.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
246
+ "vision_model.encoder.layers.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
247
+ "vision_model.encoder.layers.0.ls1": "model-00001-of-00004.safetensors",
248
+ "vision_model.encoder.layers.0.ls2": "model-00001-of-00004.safetensors",
249
+ "vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00004.safetensors",
250
+ "vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
251
+ "vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00004.safetensors",
252
+ "vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
253
+ "vision_model.encoder.layers.0.norm1.bias": "model-00001-of-00004.safetensors",
254
+ "vision_model.encoder.layers.0.norm1.weight": "model-00001-of-00004.safetensors",
255
+ "vision_model.encoder.layers.0.norm2.bias": "model-00001-of-00004.safetensors",
256
+ "vision_model.encoder.layers.0.norm2.weight": "model-00001-of-00004.safetensors",
257
+ "vision_model.encoder.layers.1.attn.proj.bias": "model-00001-of-00004.safetensors",
258
+ "vision_model.encoder.layers.1.attn.proj.weight": "model-00001-of-00004.safetensors",
259
+ "vision_model.encoder.layers.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
260
+ "vision_model.encoder.layers.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
261
+ "vision_model.encoder.layers.1.ls1": "model-00001-of-00004.safetensors",
262
+ "vision_model.encoder.layers.1.ls2": "model-00001-of-00004.safetensors",
263
+ "vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00004.safetensors",
264
+ "vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
265
+ "vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00004.safetensors",
266
+ "vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
267
+ "vision_model.encoder.layers.1.norm1.bias": "model-00001-of-00004.safetensors",
268
+ "vision_model.encoder.layers.1.norm1.weight": "model-00001-of-00004.safetensors",
269
+ "vision_model.encoder.layers.1.norm2.bias": "model-00001-of-00004.safetensors",
270
+ "vision_model.encoder.layers.1.norm2.weight": "model-00001-of-00004.safetensors",
271
+ "vision_model.encoder.layers.10.attn.proj.bias": "model-00001-of-00004.safetensors",
272
+ "vision_model.encoder.layers.10.attn.proj.weight": "model-00001-of-00004.safetensors",
273
+ "vision_model.encoder.layers.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
274
+ "vision_model.encoder.layers.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
275
+ "vision_model.encoder.layers.10.ls1": "model-00001-of-00004.safetensors",
276
+ "vision_model.encoder.layers.10.ls2": "model-00001-of-00004.safetensors",
277
+ "vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00004.safetensors",
278
+ "vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00004.safetensors",
279
+ "vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00004.safetensors",
280
+ "vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00004.safetensors",
281
+ "vision_model.encoder.layers.10.norm1.bias": "model-00001-of-00004.safetensors",
282
+ "vision_model.encoder.layers.10.norm1.weight": "model-00001-of-00004.safetensors",
283
+ "vision_model.encoder.layers.10.norm2.bias": "model-00001-of-00004.safetensors",
284
+ "vision_model.encoder.layers.10.norm2.weight": "model-00001-of-00004.safetensors",
285
+ "vision_model.encoder.layers.11.attn.proj.bias": "model-00001-of-00004.safetensors",
286
+ "vision_model.encoder.layers.11.attn.proj.weight": "model-00001-of-00004.safetensors",
287
+ "vision_model.encoder.layers.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
288
+ "vision_model.encoder.layers.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
289
+ "vision_model.encoder.layers.11.ls1": "model-00001-of-00004.safetensors",
290
+ "vision_model.encoder.layers.11.ls2": "model-00001-of-00004.safetensors",
291
+ "vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00004.safetensors",
292
+ "vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00004.safetensors",
293
+ "vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00004.safetensors",
294
+ "vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00004.safetensors",
295
+ "vision_model.encoder.layers.11.norm1.bias": "model-00001-of-00004.safetensors",
296
+ "vision_model.encoder.layers.11.norm1.weight": "model-00001-of-00004.safetensors",
297
+ "vision_model.encoder.layers.11.norm2.bias": "model-00001-of-00004.safetensors",
298
+ "vision_model.encoder.layers.11.norm2.weight": "model-00001-of-00004.safetensors",
299
+ "vision_model.encoder.layers.12.attn.proj.bias": "model-00001-of-00004.safetensors",
300
+ "vision_model.encoder.layers.12.attn.proj.weight": "model-00001-of-00004.safetensors",
301
+ "vision_model.encoder.layers.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
302
+ "vision_model.encoder.layers.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
303
+ "vision_model.encoder.layers.12.ls1": "model-00001-of-00004.safetensors",
304
+ "vision_model.encoder.layers.12.ls2": "model-00001-of-00004.safetensors",
305
+ "vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00004.safetensors",
306
+ "vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00004.safetensors",
307
+ "vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00004.safetensors",
308
+ "vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00004.safetensors",
309
+ "vision_model.encoder.layers.12.norm1.bias": "model-00001-of-00004.safetensors",
310
+ "vision_model.encoder.layers.12.norm1.weight": "model-00001-of-00004.safetensors",
311
+ "vision_model.encoder.layers.12.norm2.bias": "model-00001-of-00004.safetensors",
312
+ "vision_model.encoder.layers.12.norm2.weight": "model-00001-of-00004.safetensors",
313
+ "vision_model.encoder.layers.13.attn.proj.bias": "model-00001-of-00004.safetensors",
314
+ "vision_model.encoder.layers.13.attn.proj.weight": "model-00001-of-00004.safetensors",
315
+ "vision_model.encoder.layers.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
316
+ "vision_model.encoder.layers.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
317
+ "vision_model.encoder.layers.13.ls1": "model-00001-of-00004.safetensors",
318
+ "vision_model.encoder.layers.13.ls2": "model-00001-of-00004.safetensors",
319
+ "vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00004.safetensors",
320
+ "vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00004.safetensors",
321
+ "vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00004.safetensors",
322
+ "vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00004.safetensors",
323
+ "vision_model.encoder.layers.13.norm1.bias": "model-00001-of-00004.safetensors",
324
+ "vision_model.encoder.layers.13.norm1.weight": "model-00001-of-00004.safetensors",
325
+ "vision_model.encoder.layers.13.norm2.bias": "model-00001-of-00004.safetensors",
326
+ "vision_model.encoder.layers.13.norm2.weight": "model-00001-of-00004.safetensors",
327
+ "vision_model.encoder.layers.14.attn.proj.bias": "model-00001-of-00004.safetensors",
328
+ "vision_model.encoder.layers.14.attn.proj.weight": "model-00001-of-00004.safetensors",
329
+ "vision_model.encoder.layers.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
330
+ "vision_model.encoder.layers.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
331
+ "vision_model.encoder.layers.14.ls1": "model-00001-of-00004.safetensors",
332
+ "vision_model.encoder.layers.14.ls2": "model-00001-of-00004.safetensors",
333
+ "vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00004.safetensors",
334
+ "vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00004.safetensors",
335
+ "vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00004.safetensors",
336
+ "vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00004.safetensors",
337
+ "vision_model.encoder.layers.14.norm1.bias": "model-00001-of-00004.safetensors",
338
+ "vision_model.encoder.layers.14.norm1.weight": "model-00001-of-00004.safetensors",
339
+ "vision_model.encoder.layers.14.norm2.bias": "model-00001-of-00004.safetensors",
340
+ "vision_model.encoder.layers.14.norm2.weight": "model-00001-of-00004.safetensors",
341
+ "vision_model.encoder.layers.15.attn.proj.bias": "model-00001-of-00004.safetensors",
342
+ "vision_model.encoder.layers.15.attn.proj.weight": "model-00001-of-00004.safetensors",
343
+ "vision_model.encoder.layers.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
344
+ "vision_model.encoder.layers.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
345
+ "vision_model.encoder.layers.15.ls1": "model-00001-of-00004.safetensors",
346
+ "vision_model.encoder.layers.15.ls2": "model-00001-of-00004.safetensors",
347
+ "vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00004.safetensors",
348
+ "vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00004.safetensors",
349
+ "vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00004.safetensors",
350
+ "vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00004.safetensors",
351
+ "vision_model.encoder.layers.15.norm1.bias": "model-00001-of-00004.safetensors",
352
+ "vision_model.encoder.layers.15.norm1.weight": "model-00001-of-00004.safetensors",
353
+ "vision_model.encoder.layers.15.norm2.bias": "model-00001-of-00004.safetensors",
354
+ "vision_model.encoder.layers.15.norm2.weight": "model-00001-of-00004.safetensors",
355
+ "vision_model.encoder.layers.16.attn.proj.bias": "model-00001-of-00004.safetensors",
356
+ "vision_model.encoder.layers.16.attn.proj.weight": "model-00001-of-00004.safetensors",
357
+ "vision_model.encoder.layers.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
358
+ "vision_model.encoder.layers.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
359
+ "vision_model.encoder.layers.16.ls1": "model-00001-of-00004.safetensors",
360
+ "vision_model.encoder.layers.16.ls2": "model-00001-of-00004.safetensors",
361
+ "vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00004.safetensors",
362
+ "vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00004.safetensors",
363
+ "vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00004.safetensors",
364
+ "vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00004.safetensors",
365
+ "vision_model.encoder.layers.16.norm1.bias": "model-00001-of-00004.safetensors",
366
+ "vision_model.encoder.layers.16.norm1.weight": "model-00001-of-00004.safetensors",
367
+ "vision_model.encoder.layers.16.norm2.bias": "model-00001-of-00004.safetensors",
368
+ "vision_model.encoder.layers.16.norm2.weight": "model-00001-of-00004.safetensors",
369
+ "vision_model.encoder.layers.17.attn.proj.bias": "model-00001-of-00004.safetensors",
370
+ "vision_model.encoder.layers.17.attn.proj.weight": "model-00001-of-00004.safetensors",
371
+ "vision_model.encoder.layers.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
372
+ "vision_model.encoder.layers.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
373
+ "vision_model.encoder.layers.17.ls1": "model-00001-of-00004.safetensors",
374
+ "vision_model.encoder.layers.17.ls2": "model-00001-of-00004.safetensors",
375
+ "vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00004.safetensors",
376
+ "vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00004.safetensors",
377
+ "vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00004.safetensors",
378
+ "vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00004.safetensors",
379
+ "vision_model.encoder.layers.17.norm1.bias": "model-00001-of-00004.safetensors",
380
+ "vision_model.encoder.layers.17.norm1.weight": "model-00001-of-00004.safetensors",
381
+ "vision_model.encoder.layers.17.norm2.bias": "model-00001-of-00004.safetensors",
382
+ "vision_model.encoder.layers.17.norm2.weight": "model-00001-of-00004.safetensors",
383
+ "vision_model.encoder.layers.18.attn.proj.bias": "model-00001-of-00004.safetensors",
384
+ "vision_model.encoder.layers.18.attn.proj.weight": "model-00001-of-00004.safetensors",
385
+ "vision_model.encoder.layers.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
386
+ "vision_model.encoder.layers.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
387
+ "vision_model.encoder.layers.18.ls1": "model-00001-of-00004.safetensors",
388
+ "vision_model.encoder.layers.18.ls2": "model-00001-of-00004.safetensors",
389
+ "vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00004.safetensors",
390
+ "vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00004.safetensors",
391
+ "vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00004.safetensors",
392
+ "vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00004.safetensors",
393
+ "vision_model.encoder.layers.18.norm1.bias": "model-00001-of-00004.safetensors",
394
+ "vision_model.encoder.layers.18.norm1.weight": "model-00001-of-00004.safetensors",
395
+ "vision_model.encoder.layers.18.norm2.bias": "model-00001-of-00004.safetensors",
396
+ "vision_model.encoder.layers.18.norm2.weight": "model-00001-of-00004.safetensors",
397
+ "vision_model.encoder.layers.19.attn.proj.bias": "model-00001-of-00004.safetensors",
398
+ "vision_model.encoder.layers.19.attn.proj.weight": "model-00001-of-00004.safetensors",
399
+ "vision_model.encoder.layers.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
400
+ "vision_model.encoder.layers.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
401
+ "vision_model.encoder.layers.19.ls1": "model-00001-of-00004.safetensors",
402
+ "vision_model.encoder.layers.19.ls2": "model-00001-of-00004.safetensors",
403
+ "vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00004.safetensors",
404
+ "vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00004.safetensors",
405
+ "vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00004.safetensors",
406
+ "vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00004.safetensors",
407
+ "vision_model.encoder.layers.19.norm1.bias": "model-00001-of-00004.safetensors",
408
+ "vision_model.encoder.layers.19.norm1.weight": "model-00001-of-00004.safetensors",
409
+ "vision_model.encoder.layers.19.norm2.bias": "model-00001-of-00004.safetensors",
410
+ "vision_model.encoder.layers.19.norm2.weight": "model-00001-of-00004.safetensors",
411
+ "vision_model.encoder.layers.2.attn.proj.bias": "model-00001-of-00004.safetensors",
412
+ "vision_model.encoder.layers.2.attn.proj.weight": "model-00001-of-00004.safetensors",
413
+ "vision_model.encoder.layers.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
414
+ "vision_model.encoder.layers.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
415
+ "vision_model.encoder.layers.2.ls1": "model-00001-of-00004.safetensors",
416
+ "vision_model.encoder.layers.2.ls2": "model-00001-of-00004.safetensors",
417
+ "vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00004.safetensors",
418
+ "vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
419
+ "vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00004.safetensors",
420
+ "vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
421
+ "vision_model.encoder.layers.2.norm1.bias": "model-00001-of-00004.safetensors",
422
+ "vision_model.encoder.layers.2.norm1.weight": "model-00001-of-00004.safetensors",
423
+ "vision_model.encoder.layers.2.norm2.bias": "model-00001-of-00004.safetensors",
424
+ "vision_model.encoder.layers.2.norm2.weight": "model-00001-of-00004.safetensors",
425
+ "vision_model.encoder.layers.20.attn.proj.bias": "model-00001-of-00004.safetensors",
426
+ "vision_model.encoder.layers.20.attn.proj.weight": "model-00001-of-00004.safetensors",
427
+ "vision_model.encoder.layers.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
428
+ "vision_model.encoder.layers.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
429
+ "vision_model.encoder.layers.20.ls1": "model-00001-of-00004.safetensors",
430
+ "vision_model.encoder.layers.20.ls2": "model-00001-of-00004.safetensors",
431
+ "vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00004.safetensors",
432
+ "vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00004.safetensors",
433
+ "vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00004.safetensors",
434
+ "vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00004.safetensors",
435
+ "vision_model.encoder.layers.20.norm1.bias": "model-00001-of-00004.safetensors",
436
+ "vision_model.encoder.layers.20.norm1.weight": "model-00001-of-00004.safetensors",
437
+ "vision_model.encoder.layers.20.norm2.bias": "model-00001-of-00004.safetensors",
438
+ "vision_model.encoder.layers.20.norm2.weight": "model-00001-of-00004.safetensors",
439
+ "vision_model.encoder.layers.21.attn.proj.bias": "model-00001-of-00004.safetensors",
440
+ "vision_model.encoder.layers.21.attn.proj.weight": "model-00001-of-00004.safetensors",
441
+ "vision_model.encoder.layers.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
442
+ "vision_model.encoder.layers.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
443
+ "vision_model.encoder.layers.21.ls1": "model-00001-of-00004.safetensors",
444
+ "vision_model.encoder.layers.21.ls2": "model-00001-of-00004.safetensors",
445
+ "vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00004.safetensors",
446
+ "vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00004.safetensors",
447
+ "vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00004.safetensors",
448
+ "vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00004.safetensors",
449
+ "vision_model.encoder.layers.21.norm1.bias": "model-00001-of-00004.safetensors",
450
+ "vision_model.encoder.layers.21.norm1.weight": "model-00001-of-00004.safetensors",
451
+ "vision_model.encoder.layers.21.norm2.bias": "model-00001-of-00004.safetensors",
452
+ "vision_model.encoder.layers.21.norm2.weight": "model-00001-of-00004.safetensors",
453
+ "vision_model.encoder.layers.22.attn.proj.bias": "model-00001-of-00004.safetensors",
454
+ "vision_model.encoder.layers.22.attn.proj.weight": "model-00001-of-00004.safetensors",
455
+ "vision_model.encoder.layers.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
456
+ "vision_model.encoder.layers.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
457
+ "vision_model.encoder.layers.22.ls1": "model-00001-of-00004.safetensors",
458
+ "vision_model.encoder.layers.22.ls2": "model-00001-of-00004.safetensors",
459
+ "vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00004.safetensors",
460
+ "vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00004.safetensors",
461
+ "vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00004.safetensors",
462
+ "vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00004.safetensors",
463
+ "vision_model.encoder.layers.22.norm1.bias": "model-00001-of-00004.safetensors",
464
+ "vision_model.encoder.layers.22.norm1.weight": "model-00001-of-00004.safetensors",
465
+ "vision_model.encoder.layers.22.norm2.bias": "model-00001-of-00004.safetensors",
466
+ "vision_model.encoder.layers.22.norm2.weight": "model-00001-of-00004.safetensors",
467
+ "vision_model.encoder.layers.23.attn.proj.bias": "model-00001-of-00004.safetensors",
468
+ "vision_model.encoder.layers.23.attn.proj.weight": "model-00001-of-00004.safetensors",
469
+ "vision_model.encoder.layers.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
470
+ "vision_model.encoder.layers.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
471
+ "vision_model.encoder.layers.23.ls1": "model-00001-of-00004.safetensors",
472
+ "vision_model.encoder.layers.23.ls2": "model-00001-of-00004.safetensors",
473
+ "vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00004.safetensors",
474
+ "vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00004.safetensors",
475
+ "vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00004.safetensors",
476
+ "vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00004.safetensors",
477
+ "vision_model.encoder.layers.23.norm1.bias": "model-00001-of-00004.safetensors",
478
+ "vision_model.encoder.layers.23.norm1.weight": "model-00001-of-00004.safetensors",
479
+ "vision_model.encoder.layers.23.norm2.bias": "model-00001-of-00004.safetensors",
480
+ "vision_model.encoder.layers.23.norm2.weight": "model-00001-of-00004.safetensors",
481
+ "vision_model.encoder.layers.3.attn.proj.bias": "model-00001-of-00004.safetensors",
482
+ "vision_model.encoder.layers.3.attn.proj.weight": "model-00001-of-00004.safetensors",
483
+ "vision_model.encoder.layers.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
484
+ "vision_model.encoder.layers.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
485
+ "vision_model.encoder.layers.3.ls1": "model-00001-of-00004.safetensors",
486
+ "vision_model.encoder.layers.3.ls2": "model-00001-of-00004.safetensors",
487
+ "vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00004.safetensors",
488
+ "vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
489
+ "vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00004.safetensors",
490
+ "vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
491
+ "vision_model.encoder.layers.3.norm1.bias": "model-00001-of-00004.safetensors",
492
+ "vision_model.encoder.layers.3.norm1.weight": "model-00001-of-00004.safetensors",
493
+ "vision_model.encoder.layers.3.norm2.bias": "model-00001-of-00004.safetensors",
494
+ "vision_model.encoder.layers.3.norm2.weight": "model-00001-of-00004.safetensors",
495
+ "vision_model.encoder.layers.4.attn.proj.bias": "model-00001-of-00004.safetensors",
496
+ "vision_model.encoder.layers.4.attn.proj.weight": "model-00001-of-00004.safetensors",
497
+ "vision_model.encoder.layers.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
498
+ "vision_model.encoder.layers.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
499
+ "vision_model.encoder.layers.4.ls1": "model-00001-of-00004.safetensors",
500
+ "vision_model.encoder.layers.4.ls2": "model-00001-of-00004.safetensors",
501
+ "vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00004.safetensors",
502
+ "vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
503
+ "vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00004.safetensors",
504
+ "vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
505
+ "vision_model.encoder.layers.4.norm1.bias": "model-00001-of-00004.safetensors",
506
+ "vision_model.encoder.layers.4.norm1.weight": "model-00001-of-00004.safetensors",
507
+ "vision_model.encoder.layers.4.norm2.bias": "model-00001-of-00004.safetensors",
508
+ "vision_model.encoder.layers.4.norm2.weight": "model-00001-of-00004.safetensors",
509
+ "vision_model.encoder.layers.5.attn.proj.bias": "model-00001-of-00004.safetensors",
510
+ "vision_model.encoder.layers.5.attn.proj.weight": "model-00001-of-00004.safetensors",
511
+ "vision_model.encoder.layers.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
512
+ "vision_model.encoder.layers.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
513
+ "vision_model.encoder.layers.5.ls1": "model-00001-of-00004.safetensors",
514
+ "vision_model.encoder.layers.5.ls2": "model-00001-of-00004.safetensors",
515
+ "vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00004.safetensors",
516
+ "vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
517
+ "vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00004.safetensors",
518
+ "vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
519
+ "vision_model.encoder.layers.5.norm1.bias": "model-00001-of-00004.safetensors",
520
+ "vision_model.encoder.layers.5.norm1.weight": "model-00001-of-00004.safetensors",
521
+ "vision_model.encoder.layers.5.norm2.bias": "model-00001-of-00004.safetensors",
522
+ "vision_model.encoder.layers.5.norm2.weight": "model-00001-of-00004.safetensors",
523
+ "vision_model.encoder.layers.6.attn.proj.bias": "model-00001-of-00004.safetensors",
524
+ "vision_model.encoder.layers.6.attn.proj.weight": "model-00001-of-00004.safetensors",
525
+ "vision_model.encoder.layers.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
526
+ "vision_model.encoder.layers.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
527
+ "vision_model.encoder.layers.6.ls1": "model-00001-of-00004.safetensors",
528
+ "vision_model.encoder.layers.6.ls2": "model-00001-of-00004.safetensors",
529
+ "vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00004.safetensors",
530
+ "vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
531
+ "vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00004.safetensors",
532
+ "vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
533
+ "vision_model.encoder.layers.6.norm1.bias": "model-00001-of-00004.safetensors",
534
+ "vision_model.encoder.layers.6.norm1.weight": "model-00001-of-00004.safetensors",
535
+ "vision_model.encoder.layers.6.norm2.bias": "model-00001-of-00004.safetensors",
536
+ "vision_model.encoder.layers.6.norm2.weight": "model-00001-of-00004.safetensors",
537
+ "vision_model.encoder.layers.7.attn.proj.bias": "model-00001-of-00004.safetensors",
538
+ "vision_model.encoder.layers.7.attn.proj.weight": "model-00001-of-00004.safetensors",
539
+ "vision_model.encoder.layers.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
540
+ "vision_model.encoder.layers.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
541
+ "vision_model.encoder.layers.7.ls1": "model-00001-of-00004.safetensors",
542
+ "vision_model.encoder.layers.7.ls2": "model-00001-of-00004.safetensors",
543
+ "vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00004.safetensors",
544
+ "vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
545
+ "vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00004.safetensors",
546
+ "vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
547
+ "vision_model.encoder.layers.7.norm1.bias": "model-00001-of-00004.safetensors",
548
+ "vision_model.encoder.layers.7.norm1.weight": "model-00001-of-00004.safetensors",
549
+ "vision_model.encoder.layers.7.norm2.bias": "model-00001-of-00004.safetensors",
550
+ "vision_model.encoder.layers.7.norm2.weight": "model-00001-of-00004.safetensors",
551
+ "vision_model.encoder.layers.8.attn.proj.bias": "model-00001-of-00004.safetensors",
552
+ "vision_model.encoder.layers.8.attn.proj.weight": "model-00001-of-00004.safetensors",
553
+ "vision_model.encoder.layers.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
554
+ "vision_model.encoder.layers.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
555
+ "vision_model.encoder.layers.8.ls1": "model-00001-of-00004.safetensors",
556
+ "vision_model.encoder.layers.8.ls2": "model-00001-of-00004.safetensors",
557
+ "vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00004.safetensors",
558
+ "vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
559
+ "vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00004.safetensors",
560
+ "vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
561
+ "vision_model.encoder.layers.8.norm1.bias": "model-00001-of-00004.safetensors",
562
+ "vision_model.encoder.layers.8.norm1.weight": "model-00001-of-00004.safetensors",
563
+ "vision_model.encoder.layers.8.norm2.bias": "model-00001-of-00004.safetensors",
564
+ "vision_model.encoder.layers.8.norm2.weight": "model-00001-of-00004.safetensors",
565
+ "vision_model.encoder.layers.9.attn.proj.bias": "model-00001-of-00004.safetensors",
566
+ "vision_model.encoder.layers.9.attn.proj.weight": "model-00001-of-00004.safetensors",
567
+ "vision_model.encoder.layers.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
568
+ "vision_model.encoder.layers.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
569
+ "vision_model.encoder.layers.9.ls1": "model-00001-of-00004.safetensors",
570
+ "vision_model.encoder.layers.9.ls2": "model-00001-of-00004.safetensors",
571
+ "vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00004.safetensors",
572
+ "vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
573
+ "vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00004.safetensors",
574
+ "vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
575
+ "vision_model.encoder.layers.9.norm1.bias": "model-00001-of-00004.safetensors",
576
+ "vision_model.encoder.layers.9.norm1.weight": "model-00001-of-00004.safetensors",
577
+ "vision_model.encoder.layers.9.norm2.bias": "model-00001-of-00004.safetensors",
578
+ "vision_model.encoder.layers.9.norm2.weight": "model-00001-of-00004.safetensors"
579
+ }
580
+ }
checkpoint-50/special_tokens_map.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|action_start|>",
6
+ "<|action_end|>",
7
+ "<|interpreter|>",
8
+ "<|plugin|>",
9
+ "<img>",
10
+ "</img>",
11
+ "<IMG_CONTEXT>",
12
+ "<quad>",
13
+ "</quad>",
14
+ "<ref>",
15
+ "</ref>",
16
+ "<box>",
17
+ "</box>",
18
+ {
19
+ "content": "<prm>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ }
25
+ ],
26
+ "bos_token": {
27
+ "content": "<s>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ },
33
+ "eos_token": {
34
+ "content": "</s>",
35
+ "lstrip": false,
36
+ "normalized": false,
37
+ "rstrip": false,
38
+ "single_word": false
39
+ },
40
+ "pad_token": {
41
+ "content": "</s>",
42
+ "lstrip": false,
43
+ "normalized": false,
44
+ "rstrip": false,
45
+ "single_word": false
46
+ },
47
+ "unk_token": {
48
+ "content": "<unk>",
49
+ "lstrip": false,
50
+ "normalized": false,
51
+ "rstrip": false,
52
+ "single_word": false
53
+ }
54
+ }
checkpoint-50/tokenization_internlm2.py ADDED
@@ -0,0 +1,235 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Copyright (c) The InternLM team and The HuggingFace Inc. team. All rights reserved.
2
+ #
3
+ # This code is based on transformers/src/transformers/models/llama/tokenization_llama.py
4
+ #
5
+ # Licensed under the Apache License, Version 2.0 (the "License");
6
+ # you may not use this file except in compliance with the License.
7
+ # You may obtain a copy of the License at
8
+ #
9
+ # http://www.apache.org/licenses/LICENSE-2.0
10
+ #
11
+ # Unless required by applicable law or agreed to in writing, software
12
+ # distributed under the License is distributed on an "AS IS" BASIS,
13
+ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14
+ # See the License for the specific language governing permissions and
15
+ # limitations under the License.
16
+
17
+ """Tokenization classes for InternLM."""
18
+ import os
19
+ from shutil import copyfile
20
+ from typing import Any, Dict, List, Optional, Tuple
21
+
22
+ import sentencepiece as spm
23
+ from transformers.tokenization_utils import PreTrainedTokenizer
24
+ from transformers.utils import logging
25
+
26
+ logger = logging.get_logger(__name__)
27
+
28
+ VOCAB_FILES_NAMES = {'vocab_file': './tokenizer.model'}
29
+
30
+ PRETRAINED_VOCAB_FILES_MAP = {}
31
+
32
+
33
+ # Modified from transformers.model.llama.tokenization_llama.LlamaTokenizer
34
+ class InternLM2Tokenizer(PreTrainedTokenizer):
35
+ """
36
+ Construct a InternLM2 tokenizer. Based on byte-level Byte-Pair-Encoding.
37
+
38
+ Args:
39
+ vocab_file (`str`):
40
+ Path to the vocabulary file.
41
+ """
42
+
43
+ vocab_files_names = VOCAB_FILES_NAMES
44
+ pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
45
+ model_input_names = ['input_ids', 'attention_mask']
46
+ _auto_class = 'AutoTokenizer'
47
+
48
+ def __init__(
49
+ self,
50
+ vocab_file,
51
+ unk_token='<unk>',
52
+ bos_token='<s>',
53
+ eos_token='</s>',
54
+ pad_token='</s>',
55
+ sp_model_kwargs: Optional[Dict[str, Any]] = None,
56
+ add_bos_token=True,
57
+ add_eos_token=False,
58
+ decode_with_prefix_space=False,
59
+ clean_up_tokenization_spaces=False,
60
+ **kwargs,
61
+ ):
62
+ self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs
63
+ self.vocab_file = vocab_file
64
+ self.add_bos_token = add_bos_token
65
+ self.add_eos_token = add_eos_token
66
+ self.decode_with_prefix_space = decode_with_prefix_space
67
+ self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
68
+ self.sp_model.Load(vocab_file)
69
+ self._no_prefix_space_tokens = None
70
+ super().__init__(
71
+ bos_token=bos_token,
72
+ eos_token=eos_token,
73
+ unk_token=unk_token,
74
+ pad_token=pad_token,
75
+ clean_up_tokenization_spaces=clean_up_tokenization_spaces,
76
+ **kwargs,
77
+ )
78
+
79
+ @property
80
+ def no_prefix_space_tokens(self):
81
+ if self._no_prefix_space_tokens is None:
82
+ vocab = self.convert_ids_to_tokens(list(range(self.vocab_size)))
83
+ self._no_prefix_space_tokens = {i for i, tok in enumerate(vocab) if not tok.startswith('▁')}
84
+ return self._no_prefix_space_tokens
85
+
86
+ @property
87
+ def vocab_size(self):
88
+ """Returns vocab size"""
89
+ return self.sp_model.get_piece_size()
90
+
91
+ @property
92
+ def bos_token_id(self) -> Optional[int]:
93
+ return self.sp_model.bos_id()
94
+
95
+ @property
96
+ def eos_token_id(self) -> Optional[int]:
97
+ return self.sp_model.eos_id()
98
+
99
+ def get_vocab(self):
100
+ """Returns vocab as a dict"""
101
+ vocab = {self.convert_ids_to_tokens(i): i for i in range(self.vocab_size)}
102
+ vocab.update(self.added_tokens_encoder)
103
+ return vocab
104
+
105
+ def _tokenize(self, text):
106
+ """Returns a tokenized string."""
107
+ return self.sp_model.encode(text, out_type=str)
108
+
109
+ def _convert_token_to_id(self, token):
110
+ """Converts a token (str) in an id using the vocab."""
111
+ return self.sp_model.piece_to_id(token)
112
+
113
+ def _convert_id_to_token(self, index):
114
+ """Converts an index (integer) in a token (str) using the vocab."""
115
+ token = self.sp_model.IdToPiece(index)
116
+ return token
117
+
118
+ def _maybe_add_prefix_space(self, tokens, decoded):
119
+ if tokens and tokens[0] not in self.no_prefix_space_tokens:
120
+ return ' ' + decoded
121
+ else:
122
+ return decoded
123
+
124
+ def convert_tokens_to_string(self, tokens):
125
+ """Converts a sequence of tokens (string) in a single string."""
126
+ current_sub_tokens = []
127
+ out_string = ''
128
+ prev_is_special = False
129
+ for token in tokens:
130
+ # make sure that special tokens are not decoded using sentencepiece model
131
+ if token in self.all_special_tokens:
132
+ if not prev_is_special:
133
+ out_string += ' '
134
+ out_string += self.sp_model.decode(current_sub_tokens) + token
135
+ prev_is_special = True
136
+ current_sub_tokens = []
137
+ else:
138
+ current_sub_tokens.append(token)
139
+ prev_is_special = False
140
+ out_string += self.sp_model.decode(current_sub_tokens)
141
+ out_string = self.clean_up_tokenization(out_string)
142
+ out_string = self._maybe_add_prefix_space(tokens=tokens, decoded=out_string)
143
+ return out_string[1:]
144
+
145
+ def save_vocabulary(self, save_directory, filename_prefix: Optional[str] = None) -> Tuple[str]:
146
+ """
147
+ Save the vocabulary and special tokens file to a directory.
148
+
149
+ Args:
150
+ save_directory (`str`):
151
+ The directory in which to save the vocabulary.
152
+
153
+ Returns:
154
+ `Tuple(str)`: Paths to the files saved.
155
+ """
156
+ if not os.path.isdir(save_directory):
157
+ logger.error(f'Vocabulary path ({save_directory}) should be a directory')
158
+ return
159
+ out_vocab_file = os.path.join(
160
+ save_directory, (filename_prefix + '-' if filename_prefix else '') + VOCAB_FILES_NAMES['vocab_file']
161
+ )
162
+
163
+ if os.path.abspath(self.vocab_file) != os.path.abspath(out_vocab_file) and os.path.isfile(self.vocab_file):
164
+ copyfile(self.vocab_file, out_vocab_file)
165
+ elif not os.path.isfile(self.vocab_file):
166
+ with open(out_vocab_file, 'wb') as fi:
167
+ content_spiece_model = self.sp_model.serialized_model_proto()
168
+ fi.write(content_spiece_model)
169
+
170
+ return (out_vocab_file,)
171
+
172
+ def build_inputs_with_special_tokens(self, token_ids_0, token_ids_1=None):
173
+ if self.add_bos_token:
174
+ bos_token_ids = [self.bos_token_id]
175
+ else:
176
+ bos_token_ids = []
177
+
178
+ output = bos_token_ids + token_ids_0
179
+
180
+ if token_ids_1 is not None:
181
+ output = output + token_ids_1
182
+
183
+ if self.add_eos_token:
184
+ output = output + [self.eos_token_id]
185
+
186
+ return output
187
+
188
+ def get_special_tokens_mask(
189
+ self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None, already_has_special_tokens: bool = False
190
+ ) -> List[int]:
191
+ """
192
+ Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding
193
+ special tokens using the tokenizer `prepare_for_model` method.
194
+
195
+ Args:
196
+ token_ids_0 (`List[int]`):
197
+ List of IDs.
198
+ token_ids_1 (`List[int]`, *optional*):
199
+ Optional second list of IDs for sequence pairs.
200
+ already_has_special_tokens (`bool`, *optional*, defaults to `False`):
201
+ Whether or not the token list is already formatted with special tokens for the model.
202
+
203
+ Returns:
204
+ `List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
205
+ """
206
+ if already_has_special_tokens:
207
+ return super().get_special_tokens_mask(
208
+ token_ids_0=token_ids_0, token_ids_1=token_ids_1, already_has_special_tokens=True
209
+ )
210
+
211
+ if token_ids_1 is None:
212
+ return [1] + ([0] * len(token_ids_0)) + [1]
213
+ return [1] + ([0] * len(token_ids_0)) + [1, 1] + ([0] * len(token_ids_1)) + [1]
214
+
215
+ def create_token_type_ids_from_sequences(
216
+ self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
217
+ ) -> List[int]:
218
+ """
219
+ Create a mask from the two sequences passed to be used in a sequence-pair classification task. T5 does not make
220
+ use of token type ids, therefore a list of zeros is returned.
221
+
222
+ Args:
223
+ token_ids_0 (`List[int]`):
224
+ List of IDs.
225
+ token_ids_1 (`List[int]`, *optional*):
226
+ Optional second list of IDs for sequence pairs.
227
+
228
+ Returns:
229
+ `List[int]`: List of zeros.
230
+ """
231
+ eos = [self.eos_token_id]
232
+
233
+ if token_ids_1 is None:
234
+ return len(token_ids_0 + eos) * [0]
235
+ return len(token_ids_0 + eos + token_ids_1 + eos) * [0]
checkpoint-50/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f868398fc4e05ee1e8aeba95ddf18ddcc45b8bce55d5093bead5bbf80429b48b
3
+ size 1477754
checkpoint-50/tokenizer_config.json ADDED
@@ -0,0 +1,189 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "92538": {
28
+ "content": "<|plugin|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "92539": {
36
+ "content": "<|interpreter|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "92540": {
44
+ "content": "<|action_end|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "92541": {
52
+ "content": "<|action_start|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "92542": {
60
+ "content": "<|im_end|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "92543": {
68
+ "content": "<|im_start|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "92544": {
76
+ "content": "<img>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "92545": {
84
+ "content": "</img>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "92546": {
92
+ "content": "<IMG_CONTEXT>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "92547": {
100
+ "content": "<quad>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "92548": {
108
+ "content": "</quad>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "92549": {
116
+ "content": "<ref>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "92550": {
124
+ "content": "</ref>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "92551": {
132
+ "content": "<box>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "92552": {
140
+ "content": "</box>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "92553": {
148
+ "content": "<prm>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ }
155
+ },
156
+ "additional_special_tokens": [
157
+ "<|im_start|>",
158
+ "<|im_end|>",
159
+ "<|action_start|>",
160
+ "<|action_end|>",
161
+ "<|interpreter|>",
162
+ "<|plugin|>",
163
+ "<img>",
164
+ "</img>",
165
+ "<IMG_CONTEXT>",
166
+ "<quad>",
167
+ "</quad>",
168
+ "<ref>",
169
+ "</ref>",
170
+ "<box>",
171
+ "</box>",
172
+ "<prm>"
173
+ ],
174
+ "auto_map": {
175
+ "AutoTokenizer": [
176
+ "tokenization_internlm2.InternLM2Tokenizer",
177
+ null
178
+ ]
179
+ },
180
+ "bos_token": "<s>",
181
+ "chat_template": "{{ bos_token }}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
182
+ "clean_up_tokenization_spaces": false,
183
+ "eos_token": "</s>",
184
+ "extra_special_tokens": {},
185
+ "model_max_length": 8192,
186
+ "pad_token": "</s>",
187
+ "tokenizer_class": "InternLM2Tokenizer",
188
+ "unk_token": "<unk>"
189
+ }
checkpoint-50/trainer_state.json ADDED
@@ -0,0 +1,383 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.5908419497784343,
5
+ "eval_steps": 500,
6
+ "global_step": 50,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.011816838995568686,
13
+ "grad_norm": 141.58821940810319,
14
+ "learning_rate": 2.0000000000000003e-06,
15
+ "loss": 24.7396,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.023633677991137372,
20
+ "grad_norm": 143.0826093691902,
21
+ "learning_rate": 4.000000000000001e-06,
22
+ "loss": 24.9928,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.03545051698670606,
27
+ "grad_norm": 106.05432186386774,
28
+ "learning_rate": 6e-06,
29
+ "loss": 18.2222,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.047267355982274745,
34
+ "grad_norm": 19.635338999926788,
35
+ "learning_rate": 8.000000000000001e-06,
36
+ "loss": 7.9201,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.059084194977843424,
41
+ "grad_norm": 13.95265170436528,
42
+ "learning_rate": 1e-05,
43
+ "loss": 7.5088,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.07090103397341212,
48
+ "grad_norm": 10.13890459339853,
49
+ "learning_rate": 9.99604698613651e-06,
50
+ "loss": 7.5049,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.0827178729689808,
55
+ "grad_norm": 5.161331048523965,
56
+ "learning_rate": 9.98419419507348e-06,
57
+ "loss": 3.6598,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.09453471196454949,
62
+ "grad_norm": 139.7527677361183,
63
+ "learning_rate": 9.964460368509868e-06,
64
+ "loss": 21.683,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.10635155096011817,
69
+ "grad_norm": 17.32001191129204,
70
+ "learning_rate": 9.936876709681668e-06,
71
+ "loss": 6.269,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.11816838995568685,
76
+ "grad_norm": 3.6667439464627005,
77
+ "learning_rate": 9.901486834023182e-06,
78
+ "loss": 3.9577,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.12998522895125553,
83
+ "grad_norm": 4.3142551112177125,
84
+ "learning_rate": 9.85834670020205e-06,
85
+ "loss": 4.2225,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.14180206794682423,
90
+ "grad_norm": 2.554707938100202,
91
+ "learning_rate": 9.807524521637103e-06,
92
+ "loss": 3.8235,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.1536189069423929,
97
+ "grad_norm": 3.902409900663783,
98
+ "learning_rate": 9.749100658638914e-06,
99
+ "loss": 3.488,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.1654357459379616,
104
+ "grad_norm": 1.9177071201200944,
105
+ "learning_rate": 9.68316749134364e-06,
106
+ "loss": 3.6343,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.17725258493353027,
111
+ "grad_norm": 2.343695570919709,
112
+ "learning_rate": 9.609829273641034e-06,
113
+ "loss": 2.4759,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.18906942392909898,
118
+ "grad_norm": 2.670990461737092,
119
+ "learning_rate": 9.529201968327618e-06,
120
+ "loss": 2.8148,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.20088626292466766,
125
+ "grad_norm": 4.035538523683045,
126
+ "learning_rate": 9.44141306374566e-06,
127
+ "loss": 3.5358,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.21270310192023634,
132
+ "grad_norm": 1.9700378149332556,
133
+ "learning_rate": 9.346601372197914e-06,
134
+ "loss": 2.4168,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.22451994091580502,
139
+ "grad_norm": 1.5664890777552727,
140
+ "learning_rate": 9.244916810456822e-06,
141
+ "loss": 2.8056,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.2363367799113737,
146
+ "grad_norm": 2.4581786199164166,
147
+ "learning_rate": 9.136520162715288e-06,
148
+ "loss": 2.7812,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.2481536189069424,
153
+ "grad_norm": 1.1245546722153261,
154
+ "learning_rate": 9.021582826353825e-06,
155
+ "loss": 2.1436,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.25997045790251105,
160
+ "grad_norm": 1.7893027067897964,
161
+ "learning_rate": 8.900286540926062e-06,
162
+ "loss": 2.2205,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.2717872968980798,
167
+ "grad_norm": 3.9769501645462864,
168
+ "learning_rate": 8.772823100791152e-06,
169
+ "loss": 2.9946,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.28360413589364847,
174
+ "grad_norm": 3.7789691171773834,
175
+ "learning_rate": 8.639394051847472e-06,
176
+ "loss": 2.3066,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.29542097488921715,
181
+ "grad_norm": 5.6315683255278675,
182
+ "learning_rate": 8.500210372847128e-06,
183
+ "loss": 2.5008,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.3072378138847858,
188
+ "grad_norm": 1.8586124427568678,
189
+ "learning_rate": 8.355492141795185e-06,
190
+ "loss": 2.5177,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.3190546528803545,
195
+ "grad_norm": 1.7546209315437058,
196
+ "learning_rate": 8.2054681879611e-06,
197
+ "loss": 1.831,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.3308714918759232,
202
+ "grad_norm": 1.720970962604252,
203
+ "learning_rate": 8.050375730052622e-06,
204
+ "loss": 1.7447,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.34268833087149186,
209
+ "grad_norm": 1.464450414082788,
210
+ "learning_rate": 7.890460001124242e-06,
211
+ "loss": 2.2377,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.35450516986706054,
216
+ "grad_norm": 3.8274378731294636,
217
+ "learning_rate": 7.725973860813338e-06,
218
+ "loss": 2.3531,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.3663220088626292,
223
+ "grad_norm": 2.201173488939731,
224
+ "learning_rate": 7.5571773955171124e-06,
225
+ "loss": 2.1743,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.37813884785819796,
230
+ "grad_norm": 1.8071635950710907,
231
+ "learning_rate": 7.3843375071425315e-06,
232
+ "loss": 2.1838,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.38995568685376664,
237
+ "grad_norm": 1.7885207161263894,
238
+ "learning_rate": 7.2077274910795605e-06,
239
+ "loss": 1.7424,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.4017725258493353,
244
+ "grad_norm": 1.1269226512915496,
245
+ "learning_rate": 7.02762660406497e-06,
246
+ "loss": 1.7356,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.413589364844904,
251
+ "grad_norm": 1.075428967398824,
252
+ "learning_rate": 6.844319622620039e-06,
253
+ "loss": 1.8519,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.4254062038404727,
258
+ "grad_norm": 1.8285203027282286,
259
+ "learning_rate": 6.65809639276034e-06,
260
+ "loss": 1.9009,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.43722304283604135,
265
+ "grad_norm": 1.221068738720484,
266
+ "learning_rate": 6.469251371689606e-06,
267
+ "loss": 1.8889,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.44903988183161003,
272
+ "grad_norm": 1.60803342403716,
273
+ "learning_rate": 6.278083162202374e-06,
274
+ "loss": 2.0017,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.4608567208271787,
279
+ "grad_norm": 1.9615040257279748,
280
+ "learning_rate": 6.084894040531591e-06,
281
+ "loss": 2.0796,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.4726735598227474,
286
+ "grad_norm": 1.2009289522437243,
287
+ "learning_rate": 5.8899894783877536e-06,
288
+ "loss": 1.8679,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.4844903988183161,
293
+ "grad_norm": 1.6689113415110217,
294
+ "learning_rate": 5.693677659945343e-06,
295
+ "loss": 2.3915,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.4963072378138848,
300
+ "grad_norm": 2.252147221246225,
301
+ "learning_rate": 5.496268994540309e-06,
302
+ "loss": 2.3211,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.5081240768094535,
307
+ "grad_norm": 1.2607762998685017,
308
+ "learning_rate": 5.2980756258491e-06,
309
+ "loss": 1.9496,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.5199409158050221,
314
+ "grad_norm": 1.508309898485357,
315
+ "learning_rate": 5.099410938325351e-06,
316
+ "loss": 1.5493,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.5317577548005908,
321
+ "grad_norm": 1.8042049460482938,
322
+ "learning_rate": 4.900589061674649e-06,
323
+ "loss": 2.2117,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.5435745937961596,
328
+ "grad_norm": 2.255421993651045,
329
+ "learning_rate": 4.701924374150901e-06,
330
+ "loss": 1.846,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.5553914327917282,
335
+ "grad_norm": 1.6799486878239873,
336
+ "learning_rate": 4.5037310054596936e-06,
337
+ "loss": 1.8405,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.5672082717872969,
342
+ "grad_norm": 1.0181344550017597,
343
+ "learning_rate": 4.30632234005466e-06,
344
+ "loss": 1.6842,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.5790251107828656,
349
+ "grad_norm": 0.9377690889079295,
350
+ "learning_rate": 4.11001052161225e-06,
351
+ "loss": 1.3471,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.5908419497784343,
356
+ "grad_norm": 1.0604544664904838,
357
+ "learning_rate": 3.91510595946841e-06,
358
+ "loss": 1.4419,
359
+ "step": 50
360
+ }
361
+ ],
362
+ "logging_steps": 1.0,
363
+ "max_steps": 84,
364
+ "num_input_tokens_seen": 0,
365
+ "num_train_epochs": 1,
366
+ "save_steps": 50,
367
+ "stateful_callbacks": {
368
+ "TrainerControl": {
369
+ "args": {
370
+ "should_epoch_stop": false,
371
+ "should_evaluate": false,
372
+ "should_log": false,
373
+ "should_save": true,
374
+ "should_training_stop": false
375
+ },
376
+ "attributes": {}
377
+ }
378
+ },
379
+ "total_flos": 1.4649837787979291e+20,
380
+ "train_batch_size": 2,
381
+ "trial_name": null,
382
+ "trial_params": null
383
+ }
checkpoint-50/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b51f13a383cffb413ff7951e403fc4324c59ea047b57ad6b157ee6196c8552d3
3
+ size 7544
checkpoint-84/added_tokens.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</box>": 92552,
3
+ "</img>": 92545,
4
+ "</quad>": 92548,
5
+ "</ref>": 92550,
6
+ "<IMG_CONTEXT>": 92546,
7
+ "<box>": 92551,
8
+ "<img>": 92544,
9
+ "<prm>": 92553,
10
+ "<quad>": 92547,
11
+ "<ref>": 92549
12
+ }
checkpoint-84/config.json ADDED
@@ -0,0 +1,206 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": "e9e4c0dc1db56bfab10458671519b7fa3dd29463",
3
+ "_name_or_path": "OpenGVLab/InternVL2_5-8B",
4
+ "architectures": [
5
+ "InternVLChatModel"
6
+ ],
7
+ "auto_map": {
8
+ "AutoConfig": "OpenGVLab/InternVL2_5-8B--configuration_internvl_chat.InternVLChatConfig",
9
+ "AutoModel": "OpenGVLab/InternVL2_5-8B--modeling_internvl_chat.InternVLChatModel",
10
+ "AutoModelForCausalLM": "OpenGVLab/InternVL2_5-8B--modeling_internvl_chat.InternVLChatModel"
11
+ },
12
+ "downsample_ratio": 0.5,
13
+ "dynamic_image_size": true,
14
+ "force_image_size": 448,
15
+ "hidden_size": 4096,
16
+ "llm_config": {
17
+ "_attn_implementation_autoset": true,
18
+ "_name_or_path": "internlm/internlm2_5-7b-chat",
19
+ "add_cross_attention": false,
20
+ "architectures": [
21
+ "InternLM2ForCausalLM"
22
+ ],
23
+ "attn_implementation": "flash_attention_2",
24
+ "auto_map": {
25
+ "AutoConfig": "configuration_internlm2.InternLM2Config",
26
+ "AutoModel": "modeling_internlm2.InternLM2ForCausalLM",
27
+ "AutoModelForCausalLM": "modeling_internlm2.InternLM2ForCausalLM",
28
+ "AutoModelForSequenceClassification": "modeling_internlm2.InternLM2ForSequenceClassification"
29
+ },
30
+ "bad_words_ids": null,
31
+ "begin_suppress_tokens": null,
32
+ "bias": false,
33
+ "bos_token_id": 1,
34
+ "chunk_size_feed_forward": 0,
35
+ "cross_attention_hidden_size": null,
36
+ "decoder_start_token_id": null,
37
+ "diversity_penalty": 0.0,
38
+ "do_sample": false,
39
+ "early_stopping": false,
40
+ "encoder_no_repeat_ngram_size": 0,
41
+ "eos_token_id": 2,
42
+ "exponential_decay_length_penalty": null,
43
+ "finetuning_task": null,
44
+ "forced_bos_token_id": null,
45
+ "forced_eos_token_id": null,
46
+ "hidden_act": "silu",
47
+ "hidden_size": 4096,
48
+ "id2label": {
49
+ "0": "LABEL_0",
50
+ "1": "LABEL_1"
51
+ },
52
+ "initializer_range": 0.02,
53
+ "intermediate_size": 14336,
54
+ "is_decoder": false,
55
+ "is_encoder_decoder": false,
56
+ "label2id": {
57
+ "LABEL_0": 0,
58
+ "LABEL_1": 1
59
+ },
60
+ "length_penalty": 1.0,
61
+ "max_length": 20,
62
+ "max_position_embeddings": 32768,
63
+ "min_length": 0,
64
+ "model_type": "internlm2",
65
+ "no_repeat_ngram_size": 0,
66
+ "num_attention_heads": 32,
67
+ "num_beam_groups": 1,
68
+ "num_beams": 1,
69
+ "num_hidden_layers": 32,
70
+ "num_key_value_heads": 8,
71
+ "num_return_sequences": 1,
72
+ "output_attentions": false,
73
+ "output_hidden_states": false,
74
+ "output_scores": false,
75
+ "pad_token_id": 2,
76
+ "prefix": null,
77
+ "pretraining_tp": 1,
78
+ "problem_type": null,
79
+ "pruned_heads": {},
80
+ "remove_invalid_values": false,
81
+ "repetition_penalty": 1.0,
82
+ "return_dict": true,
83
+ "return_dict_in_generate": false,
84
+ "rms_norm_eps": 1e-05,
85
+ "rope_scaling": {
86
+ "factor": 2.0,
87
+ "type": "dynamic"
88
+ },
89
+ "rope_theta": 1000000,
90
+ "sep_token_id": null,
91
+ "suppress_tokens": null,
92
+ "task_specific_params": null,
93
+ "temperature": 1.0,
94
+ "tf_legacy_loss": false,
95
+ "tie_encoder_decoder": false,
96
+ "tie_word_embeddings": false,
97
+ "tokenizer_class": null,
98
+ "top_k": 50,
99
+ "top_p": 1.0,
100
+ "torch_dtype": "bfloat16",
101
+ "torchscript": false,
102
+ "transformers_version": "4.47.1",
103
+ "typical_p": 1.0,
104
+ "use_bfloat16": true,
105
+ "use_cache": false,
106
+ "vocab_size": 92554
107
+ },
108
+ "max_dynamic_patch": 6,
109
+ "min_dynamic_patch": 1,
110
+ "model_type": "internvl_chat",
111
+ "pad2square": false,
112
+ "ps_version": "v2",
113
+ "select_layer": -1,
114
+ "template": "internvl2_5",
115
+ "tie_word_embeddings": false,
116
+ "torch_dtype": "bfloat16",
117
+ "transformers_version": null,
118
+ "use_backbone_lora": 0,
119
+ "use_llm_lora": 0,
120
+ "use_thumbnail": true,
121
+ "vision_config": {
122
+ "_attn_implementation_autoset": true,
123
+ "_name_or_path": "",
124
+ "add_cross_attention": false,
125
+ "architectures": [
126
+ "InternVisionModel"
127
+ ],
128
+ "attention_dropout": 0.0,
129
+ "bad_words_ids": null,
130
+ "begin_suppress_tokens": null,
131
+ "bos_token_id": null,
132
+ "chunk_size_feed_forward": 0,
133
+ "cross_attention_hidden_size": null,
134
+ "decoder_start_token_id": null,
135
+ "diversity_penalty": 0.0,
136
+ "do_sample": false,
137
+ "drop_path_rate": 0.4,
138
+ "dropout": 0.0,
139
+ "early_stopping": false,
140
+ "encoder_no_repeat_ngram_size": 0,
141
+ "eos_token_id": null,
142
+ "exponential_decay_length_penalty": null,
143
+ "finetuning_task": null,
144
+ "forced_bos_token_id": null,
145
+ "forced_eos_token_id": null,
146
+ "hidden_act": "gelu",
147
+ "hidden_size": 1024,
148
+ "id2label": {
149
+ "0": "LABEL_0",
150
+ "1": "LABEL_1"
151
+ },
152
+ "image_size": 448,
153
+ "initializer_factor": 1.0,
154
+ "initializer_range": 0.02,
155
+ "intermediate_size": 4096,
156
+ "is_decoder": false,
157
+ "is_encoder_decoder": false,
158
+ "label2id": {
159
+ "LABEL_0": 0,
160
+ "LABEL_1": 1
161
+ },
162
+ "layer_norm_eps": 1e-06,
163
+ "length_penalty": 1.0,
164
+ "max_length": 20,
165
+ "min_length": 0,
166
+ "model_type": "intern_vit_6b",
167
+ "no_repeat_ngram_size": 0,
168
+ "norm_type": "layer_norm",
169
+ "num_attention_heads": 16,
170
+ "num_beam_groups": 1,
171
+ "num_beams": 1,
172
+ "num_channels": 3,
173
+ "num_hidden_layers": 24,
174
+ "num_return_sequences": 1,
175
+ "output_attentions": false,
176
+ "output_hidden_states": false,
177
+ "output_scores": false,
178
+ "pad_token_id": null,
179
+ "patch_size": 14,
180
+ "prefix": null,
181
+ "problem_type": null,
182
+ "pruned_heads": {},
183
+ "qk_normalization": false,
184
+ "qkv_bias": true,
185
+ "remove_invalid_values": false,
186
+ "repetition_penalty": 1.0,
187
+ "return_dict": true,
188
+ "return_dict_in_generate": false,
189
+ "sep_token_id": null,
190
+ "suppress_tokens": null,
191
+ "task_specific_params": null,
192
+ "temperature": 1.0,
193
+ "tf_legacy_loss": false,
194
+ "tie_encoder_decoder": false,
195
+ "tie_word_embeddings": true,
196
+ "tokenizer_class": null,
197
+ "top_k": 50,
198
+ "top_p": 1.0,
199
+ "torch_dtype": "bfloat16",
200
+ "torchscript": false,
201
+ "transformers_version": "4.47.1",
202
+ "typical_p": 1.0,
203
+ "use_bfloat16": true,
204
+ "use_flash_attn": true
205
+ }
206
+ }
checkpoint-84/generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": [
4
+ 92542,
5
+ 92543
6
+ ],
7
+ "transformers_version": "4.47.1"
8
+ }
checkpoint-84/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db3bc73eb670edd68fe669ce49f64bcde138c275540ed1fea8325f960c3a59cc
3
+ size 4939952528
checkpoint-84/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cb9a4fe1267e05aec0b770e2689fd1ce1270c69aa85def316177df6cc2b5bc6
3
+ size 4915914584
checkpoint-84/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d503967663140a73ac225e5c5c75290122f671972a60335c9d1b7cb4644e2b17
3
+ size 4915914592
checkpoint-84/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08ed2e31ef564ba8a5cebdd0456206d9951dadb62c1d1ad7e376dbcabd5b7de2
3
+ size 1379035112
checkpoint-84/model.safetensors.index.json ADDED
@@ -0,0 +1,580 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16150747136
4
+ },
5
+ "weight_map": {
6
+ "language_model.model.layers.0.attention.wo.weight": "model-00001-of-00004.safetensors",
7
+ "language_model.model.layers.0.attention.wqkv.weight": "model-00001-of-00004.safetensors",
8
+ "language_model.model.layers.0.attention_norm.weight": "model-00001-of-00004.safetensors",
9
+ "language_model.model.layers.0.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
10
+ "language_model.model.layers.0.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
11
+ "language_model.model.layers.0.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
12
+ "language_model.model.layers.0.ffn_norm.weight": "model-00001-of-00004.safetensors",
13
+ "language_model.model.layers.1.attention.wo.weight": "model-00001-of-00004.safetensors",
14
+ "language_model.model.layers.1.attention.wqkv.weight": "model-00001-of-00004.safetensors",
15
+ "language_model.model.layers.1.attention_norm.weight": "model-00001-of-00004.safetensors",
16
+ "language_model.model.layers.1.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
17
+ "language_model.model.layers.1.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
18
+ "language_model.model.layers.1.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
19
+ "language_model.model.layers.1.ffn_norm.weight": "model-00001-of-00004.safetensors",
20
+ "language_model.model.layers.10.attention.wo.weight": "model-00002-of-00004.safetensors",
21
+ "language_model.model.layers.10.attention.wqkv.weight": "model-00002-of-00004.safetensors",
22
+ "language_model.model.layers.10.attention_norm.weight": "model-00002-of-00004.safetensors",
23
+ "language_model.model.layers.10.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
24
+ "language_model.model.layers.10.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
25
+ "language_model.model.layers.10.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
26
+ "language_model.model.layers.10.ffn_norm.weight": "model-00002-of-00004.safetensors",
27
+ "language_model.model.layers.11.attention.wo.weight": "model-00002-of-00004.safetensors",
28
+ "language_model.model.layers.11.attention.wqkv.weight": "model-00002-of-00004.safetensors",
29
+ "language_model.model.layers.11.attention_norm.weight": "model-00002-of-00004.safetensors",
30
+ "language_model.model.layers.11.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
31
+ "language_model.model.layers.11.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
32
+ "language_model.model.layers.11.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
33
+ "language_model.model.layers.11.ffn_norm.weight": "model-00002-of-00004.safetensors",
34
+ "language_model.model.layers.12.attention.wo.weight": "model-00002-of-00004.safetensors",
35
+ "language_model.model.layers.12.attention.wqkv.weight": "model-00002-of-00004.safetensors",
36
+ "language_model.model.layers.12.attention_norm.weight": "model-00002-of-00004.safetensors",
37
+ "language_model.model.layers.12.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
38
+ "language_model.model.layers.12.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
39
+ "language_model.model.layers.12.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
40
+ "language_model.model.layers.12.ffn_norm.weight": "model-00002-of-00004.safetensors",
41
+ "language_model.model.layers.13.attention.wo.weight": "model-00002-of-00004.safetensors",
42
+ "language_model.model.layers.13.attention.wqkv.weight": "model-00002-of-00004.safetensors",
43
+ "language_model.model.layers.13.attention_norm.weight": "model-00002-of-00004.safetensors",
44
+ "language_model.model.layers.13.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
45
+ "language_model.model.layers.13.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
46
+ "language_model.model.layers.13.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
47
+ "language_model.model.layers.13.ffn_norm.weight": "model-00002-of-00004.safetensors",
48
+ "language_model.model.layers.14.attention.wo.weight": "model-00002-of-00004.safetensors",
49
+ "language_model.model.layers.14.attention.wqkv.weight": "model-00002-of-00004.safetensors",
50
+ "language_model.model.layers.14.attention_norm.weight": "model-00002-of-00004.safetensors",
51
+ "language_model.model.layers.14.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
52
+ "language_model.model.layers.14.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
53
+ "language_model.model.layers.14.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
54
+ "language_model.model.layers.14.ffn_norm.weight": "model-00002-of-00004.safetensors",
55
+ "language_model.model.layers.15.attention.wo.weight": "model-00002-of-00004.safetensors",
56
+ "language_model.model.layers.15.attention.wqkv.weight": "model-00002-of-00004.safetensors",
57
+ "language_model.model.layers.15.attention_norm.weight": "model-00002-of-00004.safetensors",
58
+ "language_model.model.layers.15.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
59
+ "language_model.model.layers.15.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
60
+ "language_model.model.layers.15.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
61
+ "language_model.model.layers.15.ffn_norm.weight": "model-00002-of-00004.safetensors",
62
+ "language_model.model.layers.16.attention.wo.weight": "model-00002-of-00004.safetensors",
63
+ "language_model.model.layers.16.attention.wqkv.weight": "model-00002-of-00004.safetensors",
64
+ "language_model.model.layers.16.attention_norm.weight": "model-00002-of-00004.safetensors",
65
+ "language_model.model.layers.16.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
66
+ "language_model.model.layers.16.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
67
+ "language_model.model.layers.16.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
68
+ "language_model.model.layers.16.ffn_norm.weight": "model-00002-of-00004.safetensors",
69
+ "language_model.model.layers.17.attention.wo.weight": "model-00002-of-00004.safetensors",
70
+ "language_model.model.layers.17.attention.wqkv.weight": "model-00002-of-00004.safetensors",
71
+ "language_model.model.layers.17.attention_norm.weight": "model-00002-of-00004.safetensors",
72
+ "language_model.model.layers.17.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
73
+ "language_model.model.layers.17.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
74
+ "language_model.model.layers.17.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
75
+ "language_model.model.layers.17.ffn_norm.weight": "model-00002-of-00004.safetensors",
76
+ "language_model.model.layers.18.attention.wo.weight": "model-00002-of-00004.safetensors",
77
+ "language_model.model.layers.18.attention.wqkv.weight": "model-00002-of-00004.safetensors",
78
+ "language_model.model.layers.18.attention_norm.weight": "model-00002-of-00004.safetensors",
79
+ "language_model.model.layers.18.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
80
+ "language_model.model.layers.18.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
81
+ "language_model.model.layers.18.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
82
+ "language_model.model.layers.18.ffn_norm.weight": "model-00002-of-00004.safetensors",
83
+ "language_model.model.layers.19.attention.wo.weight": "model-00002-of-00004.safetensors",
84
+ "language_model.model.layers.19.attention.wqkv.weight": "model-00002-of-00004.safetensors",
85
+ "language_model.model.layers.19.attention_norm.weight": "model-00003-of-00004.safetensors",
86
+ "language_model.model.layers.19.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
87
+ "language_model.model.layers.19.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
88
+ "language_model.model.layers.19.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
89
+ "language_model.model.layers.19.ffn_norm.weight": "model-00003-of-00004.safetensors",
90
+ "language_model.model.layers.2.attention.wo.weight": "model-00001-of-00004.safetensors",
91
+ "language_model.model.layers.2.attention.wqkv.weight": "model-00001-of-00004.safetensors",
92
+ "language_model.model.layers.2.attention_norm.weight": "model-00001-of-00004.safetensors",
93
+ "language_model.model.layers.2.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
94
+ "language_model.model.layers.2.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
95
+ "language_model.model.layers.2.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
96
+ "language_model.model.layers.2.ffn_norm.weight": "model-00001-of-00004.safetensors",
97
+ "language_model.model.layers.20.attention.wo.weight": "model-00003-of-00004.safetensors",
98
+ "language_model.model.layers.20.attention.wqkv.weight": "model-00003-of-00004.safetensors",
99
+ "language_model.model.layers.20.attention_norm.weight": "model-00003-of-00004.safetensors",
100
+ "language_model.model.layers.20.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
101
+ "language_model.model.layers.20.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
102
+ "language_model.model.layers.20.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
103
+ "language_model.model.layers.20.ffn_norm.weight": "model-00003-of-00004.safetensors",
104
+ "language_model.model.layers.21.attention.wo.weight": "model-00003-of-00004.safetensors",
105
+ "language_model.model.layers.21.attention.wqkv.weight": "model-00003-of-00004.safetensors",
106
+ "language_model.model.layers.21.attention_norm.weight": "model-00003-of-00004.safetensors",
107
+ "language_model.model.layers.21.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
108
+ "language_model.model.layers.21.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
109
+ "language_model.model.layers.21.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
110
+ "language_model.model.layers.21.ffn_norm.weight": "model-00003-of-00004.safetensors",
111
+ "language_model.model.layers.22.attention.wo.weight": "model-00003-of-00004.safetensors",
112
+ "language_model.model.layers.22.attention.wqkv.weight": "model-00003-of-00004.safetensors",
113
+ "language_model.model.layers.22.attention_norm.weight": "model-00003-of-00004.safetensors",
114
+ "language_model.model.layers.22.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
115
+ "language_model.model.layers.22.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
116
+ "language_model.model.layers.22.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
117
+ "language_model.model.layers.22.ffn_norm.weight": "model-00003-of-00004.safetensors",
118
+ "language_model.model.layers.23.attention.wo.weight": "model-00003-of-00004.safetensors",
119
+ "language_model.model.layers.23.attention.wqkv.weight": "model-00003-of-00004.safetensors",
120
+ "language_model.model.layers.23.attention_norm.weight": "model-00003-of-00004.safetensors",
121
+ "language_model.model.layers.23.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
122
+ "language_model.model.layers.23.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
123
+ "language_model.model.layers.23.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
124
+ "language_model.model.layers.23.ffn_norm.weight": "model-00003-of-00004.safetensors",
125
+ "language_model.model.layers.24.attention.wo.weight": "model-00003-of-00004.safetensors",
126
+ "language_model.model.layers.24.attention.wqkv.weight": "model-00003-of-00004.safetensors",
127
+ "language_model.model.layers.24.attention_norm.weight": "model-00003-of-00004.safetensors",
128
+ "language_model.model.layers.24.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
129
+ "language_model.model.layers.24.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
130
+ "language_model.model.layers.24.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
131
+ "language_model.model.layers.24.ffn_norm.weight": "model-00003-of-00004.safetensors",
132
+ "language_model.model.layers.25.attention.wo.weight": "model-00003-of-00004.safetensors",
133
+ "language_model.model.layers.25.attention.wqkv.weight": "model-00003-of-00004.safetensors",
134
+ "language_model.model.layers.25.attention_norm.weight": "model-00003-of-00004.safetensors",
135
+ "language_model.model.layers.25.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
136
+ "language_model.model.layers.25.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
137
+ "language_model.model.layers.25.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
138
+ "language_model.model.layers.25.ffn_norm.weight": "model-00003-of-00004.safetensors",
139
+ "language_model.model.layers.26.attention.wo.weight": "model-00003-of-00004.safetensors",
140
+ "language_model.model.layers.26.attention.wqkv.weight": "model-00003-of-00004.safetensors",
141
+ "language_model.model.layers.26.attention_norm.weight": "model-00003-of-00004.safetensors",
142
+ "language_model.model.layers.26.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
143
+ "language_model.model.layers.26.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
144
+ "language_model.model.layers.26.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
145
+ "language_model.model.layers.26.ffn_norm.weight": "model-00003-of-00004.safetensors",
146
+ "language_model.model.layers.27.attention.wo.weight": "model-00003-of-00004.safetensors",
147
+ "language_model.model.layers.27.attention.wqkv.weight": "model-00003-of-00004.safetensors",
148
+ "language_model.model.layers.27.attention_norm.weight": "model-00003-of-00004.safetensors",
149
+ "language_model.model.layers.27.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
150
+ "language_model.model.layers.27.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
151
+ "language_model.model.layers.27.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
152
+ "language_model.model.layers.27.ffn_norm.weight": "model-00003-of-00004.safetensors",
153
+ "language_model.model.layers.28.attention.wo.weight": "model-00003-of-00004.safetensors",
154
+ "language_model.model.layers.28.attention.wqkv.weight": "model-00003-of-00004.safetensors",
155
+ "language_model.model.layers.28.attention_norm.weight": "model-00003-of-00004.safetensors",
156
+ "language_model.model.layers.28.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
157
+ "language_model.model.layers.28.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
158
+ "language_model.model.layers.28.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
159
+ "language_model.model.layers.28.ffn_norm.weight": "model-00003-of-00004.safetensors",
160
+ "language_model.model.layers.29.attention.wo.weight": "model-00003-of-00004.safetensors",
161
+ "language_model.model.layers.29.attention.wqkv.weight": "model-00003-of-00004.safetensors",
162
+ "language_model.model.layers.29.attention_norm.weight": "model-00003-of-00004.safetensors",
163
+ "language_model.model.layers.29.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
164
+ "language_model.model.layers.29.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
165
+ "language_model.model.layers.29.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
166
+ "language_model.model.layers.29.ffn_norm.weight": "model-00003-of-00004.safetensors",
167
+ "language_model.model.layers.3.attention.wo.weight": "model-00001-of-00004.safetensors",
168
+ "language_model.model.layers.3.attention.wqkv.weight": "model-00001-of-00004.safetensors",
169
+ "language_model.model.layers.3.attention_norm.weight": "model-00001-of-00004.safetensors",
170
+ "language_model.model.layers.3.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
171
+ "language_model.model.layers.3.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
172
+ "language_model.model.layers.3.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
173
+ "language_model.model.layers.3.ffn_norm.weight": "model-00001-of-00004.safetensors",
174
+ "language_model.model.layers.30.attention.wo.weight": "model-00003-of-00004.safetensors",
175
+ "language_model.model.layers.30.attention.wqkv.weight": "model-00003-of-00004.safetensors",
176
+ "language_model.model.layers.30.attention_norm.weight": "model-00004-of-00004.safetensors",
177
+ "language_model.model.layers.30.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
178
+ "language_model.model.layers.30.feed_forward.w2.weight": "model-00004-of-00004.safetensors",
179
+ "language_model.model.layers.30.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
180
+ "language_model.model.layers.30.ffn_norm.weight": "model-00004-of-00004.safetensors",
181
+ "language_model.model.layers.31.attention.wo.weight": "model-00004-of-00004.safetensors",
182
+ "language_model.model.layers.31.attention.wqkv.weight": "model-00004-of-00004.safetensors",
183
+ "language_model.model.layers.31.attention_norm.weight": "model-00004-of-00004.safetensors",
184
+ "language_model.model.layers.31.feed_forward.w1.weight": "model-00004-of-00004.safetensors",
185
+ "language_model.model.layers.31.feed_forward.w2.weight": "model-00004-of-00004.safetensors",
186
+ "language_model.model.layers.31.feed_forward.w3.weight": "model-00004-of-00004.safetensors",
187
+ "language_model.model.layers.31.ffn_norm.weight": "model-00004-of-00004.safetensors",
188
+ "language_model.model.layers.4.attention.wo.weight": "model-00001-of-00004.safetensors",
189
+ "language_model.model.layers.4.attention.wqkv.weight": "model-00001-of-00004.safetensors",
190
+ "language_model.model.layers.4.attention_norm.weight": "model-00001-of-00004.safetensors",
191
+ "language_model.model.layers.4.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
192
+ "language_model.model.layers.4.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
193
+ "language_model.model.layers.4.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
194
+ "language_model.model.layers.4.ffn_norm.weight": "model-00001-of-00004.safetensors",
195
+ "language_model.model.layers.5.attention.wo.weight": "model-00001-of-00004.safetensors",
196
+ "language_model.model.layers.5.attention.wqkv.weight": "model-00001-of-00004.safetensors",
197
+ "language_model.model.layers.5.attention_norm.weight": "model-00001-of-00004.safetensors",
198
+ "language_model.model.layers.5.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
199
+ "language_model.model.layers.5.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
200
+ "language_model.model.layers.5.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
201
+ "language_model.model.layers.5.ffn_norm.weight": "model-00001-of-00004.safetensors",
202
+ "language_model.model.layers.6.attention.wo.weight": "model-00001-of-00004.safetensors",
203
+ "language_model.model.layers.6.attention.wqkv.weight": "model-00001-of-00004.safetensors",
204
+ "language_model.model.layers.6.attention_norm.weight": "model-00001-of-00004.safetensors",
205
+ "language_model.model.layers.6.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
206
+ "language_model.model.layers.6.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
207
+ "language_model.model.layers.6.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
208
+ "language_model.model.layers.6.ffn_norm.weight": "model-00001-of-00004.safetensors",
209
+ "language_model.model.layers.7.attention.wo.weight": "model-00001-of-00004.safetensors",
210
+ "language_model.model.layers.7.attention.wqkv.weight": "model-00001-of-00004.safetensors",
211
+ "language_model.model.layers.7.attention_norm.weight": "model-00001-of-00004.safetensors",
212
+ "language_model.model.layers.7.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
213
+ "language_model.model.layers.7.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
214
+ "language_model.model.layers.7.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
215
+ "language_model.model.layers.7.ffn_norm.weight": "model-00001-of-00004.safetensors",
216
+ "language_model.model.layers.8.attention.wo.weight": "model-00001-of-00004.safetensors",
217
+ "language_model.model.layers.8.attention.wqkv.weight": "model-00001-of-00004.safetensors",
218
+ "language_model.model.layers.8.attention_norm.weight": "model-00002-of-00004.safetensors",
219
+ "language_model.model.layers.8.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
220
+ "language_model.model.layers.8.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
221
+ "language_model.model.layers.8.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
222
+ "language_model.model.layers.8.ffn_norm.weight": "model-00002-of-00004.safetensors",
223
+ "language_model.model.layers.9.attention.wo.weight": "model-00002-of-00004.safetensors",
224
+ "language_model.model.layers.9.attention.wqkv.weight": "model-00002-of-00004.safetensors",
225
+ "language_model.model.layers.9.attention_norm.weight": "model-00002-of-00004.safetensors",
226
+ "language_model.model.layers.9.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
227
+ "language_model.model.layers.9.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
228
+ "language_model.model.layers.9.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
229
+ "language_model.model.layers.9.ffn_norm.weight": "model-00002-of-00004.safetensors",
230
+ "language_model.model.norm.weight": "model-00004-of-00004.safetensors",
231
+ "language_model.model.tok_embeddings.weight": "model-00001-of-00004.safetensors",
232
+ "language_model.output.weight": "model-00004-of-00004.safetensors",
233
+ "mlp1.0.bias": "model-00004-of-00004.safetensors",
234
+ "mlp1.0.weight": "model-00004-of-00004.safetensors",
235
+ "mlp1.1.bias": "model-00004-of-00004.safetensors",
236
+ "mlp1.1.weight": "model-00004-of-00004.safetensors",
237
+ "mlp1.3.bias": "model-00004-of-00004.safetensors",
238
+ "mlp1.3.weight": "model-00004-of-00004.safetensors",
239
+ "vision_model.embeddings.class_embedding": "model-00001-of-00004.safetensors",
240
+ "vision_model.embeddings.patch_embedding.bias": "model-00001-of-00004.safetensors",
241
+ "vision_model.embeddings.patch_embedding.weight": "model-00001-of-00004.safetensors",
242
+ "vision_model.embeddings.position_embedding": "model-00001-of-00004.safetensors",
243
+ "vision_model.encoder.layers.0.attn.proj.bias": "model-00001-of-00004.safetensors",
244
+ "vision_model.encoder.layers.0.attn.proj.weight": "model-00001-of-00004.safetensors",
245
+ "vision_model.encoder.layers.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
246
+ "vision_model.encoder.layers.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
247
+ "vision_model.encoder.layers.0.ls1": "model-00001-of-00004.safetensors",
248
+ "vision_model.encoder.layers.0.ls2": "model-00001-of-00004.safetensors",
249
+ "vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00004.safetensors",
250
+ "vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
251
+ "vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00004.safetensors",
252
+ "vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
253
+ "vision_model.encoder.layers.0.norm1.bias": "model-00001-of-00004.safetensors",
254
+ "vision_model.encoder.layers.0.norm1.weight": "model-00001-of-00004.safetensors",
255
+ "vision_model.encoder.layers.0.norm2.bias": "model-00001-of-00004.safetensors",
256
+ "vision_model.encoder.layers.0.norm2.weight": "model-00001-of-00004.safetensors",
257
+ "vision_model.encoder.layers.1.attn.proj.bias": "model-00001-of-00004.safetensors",
258
+ "vision_model.encoder.layers.1.attn.proj.weight": "model-00001-of-00004.safetensors",
259
+ "vision_model.encoder.layers.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
260
+ "vision_model.encoder.layers.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
261
+ "vision_model.encoder.layers.1.ls1": "model-00001-of-00004.safetensors",
262
+ "vision_model.encoder.layers.1.ls2": "model-00001-of-00004.safetensors",
263
+ "vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00004.safetensors",
264
+ "vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
265
+ "vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00004.safetensors",
266
+ "vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
267
+ "vision_model.encoder.layers.1.norm1.bias": "model-00001-of-00004.safetensors",
268
+ "vision_model.encoder.layers.1.norm1.weight": "model-00001-of-00004.safetensors",
269
+ "vision_model.encoder.layers.1.norm2.bias": "model-00001-of-00004.safetensors",
270
+ "vision_model.encoder.layers.1.norm2.weight": "model-00001-of-00004.safetensors",
271
+ "vision_model.encoder.layers.10.attn.proj.bias": "model-00001-of-00004.safetensors",
272
+ "vision_model.encoder.layers.10.attn.proj.weight": "model-00001-of-00004.safetensors",
273
+ "vision_model.encoder.layers.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
274
+ "vision_model.encoder.layers.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
275
+ "vision_model.encoder.layers.10.ls1": "model-00001-of-00004.safetensors",
276
+ "vision_model.encoder.layers.10.ls2": "model-00001-of-00004.safetensors",
277
+ "vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00004.safetensors",
278
+ "vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00004.safetensors",
279
+ "vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00004.safetensors",
280
+ "vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00004.safetensors",
281
+ "vision_model.encoder.layers.10.norm1.bias": "model-00001-of-00004.safetensors",
282
+ "vision_model.encoder.layers.10.norm1.weight": "model-00001-of-00004.safetensors",
283
+ "vision_model.encoder.layers.10.norm2.bias": "model-00001-of-00004.safetensors",
284
+ "vision_model.encoder.layers.10.norm2.weight": "model-00001-of-00004.safetensors",
285
+ "vision_model.encoder.layers.11.attn.proj.bias": "model-00001-of-00004.safetensors",
286
+ "vision_model.encoder.layers.11.attn.proj.weight": "model-00001-of-00004.safetensors",
287
+ "vision_model.encoder.layers.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
288
+ "vision_model.encoder.layers.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
289
+ "vision_model.encoder.layers.11.ls1": "model-00001-of-00004.safetensors",
290
+ "vision_model.encoder.layers.11.ls2": "model-00001-of-00004.safetensors",
291
+ "vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00004.safetensors",
292
+ "vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00004.safetensors",
293
+ "vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00004.safetensors",
294
+ "vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00004.safetensors",
295
+ "vision_model.encoder.layers.11.norm1.bias": "model-00001-of-00004.safetensors",
296
+ "vision_model.encoder.layers.11.norm1.weight": "model-00001-of-00004.safetensors",
297
+ "vision_model.encoder.layers.11.norm2.bias": "model-00001-of-00004.safetensors",
298
+ "vision_model.encoder.layers.11.norm2.weight": "model-00001-of-00004.safetensors",
299
+ "vision_model.encoder.layers.12.attn.proj.bias": "model-00001-of-00004.safetensors",
300
+ "vision_model.encoder.layers.12.attn.proj.weight": "model-00001-of-00004.safetensors",
301
+ "vision_model.encoder.layers.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
302
+ "vision_model.encoder.layers.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
303
+ "vision_model.encoder.layers.12.ls1": "model-00001-of-00004.safetensors",
304
+ "vision_model.encoder.layers.12.ls2": "model-00001-of-00004.safetensors",
305
+ "vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00004.safetensors",
306
+ "vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00004.safetensors",
307
+ "vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00004.safetensors",
308
+ "vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00004.safetensors",
309
+ "vision_model.encoder.layers.12.norm1.bias": "model-00001-of-00004.safetensors",
310
+ "vision_model.encoder.layers.12.norm1.weight": "model-00001-of-00004.safetensors",
311
+ "vision_model.encoder.layers.12.norm2.bias": "model-00001-of-00004.safetensors",
312
+ "vision_model.encoder.layers.12.norm2.weight": "model-00001-of-00004.safetensors",
313
+ "vision_model.encoder.layers.13.attn.proj.bias": "model-00001-of-00004.safetensors",
314
+ "vision_model.encoder.layers.13.attn.proj.weight": "model-00001-of-00004.safetensors",
315
+ "vision_model.encoder.layers.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
316
+ "vision_model.encoder.layers.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
317
+ "vision_model.encoder.layers.13.ls1": "model-00001-of-00004.safetensors",
318
+ "vision_model.encoder.layers.13.ls2": "model-00001-of-00004.safetensors",
319
+ "vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00004.safetensors",
320
+ "vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00004.safetensors",
321
+ "vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00004.safetensors",
322
+ "vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00004.safetensors",
323
+ "vision_model.encoder.layers.13.norm1.bias": "model-00001-of-00004.safetensors",
324
+ "vision_model.encoder.layers.13.norm1.weight": "model-00001-of-00004.safetensors",
325
+ "vision_model.encoder.layers.13.norm2.bias": "model-00001-of-00004.safetensors",
326
+ "vision_model.encoder.layers.13.norm2.weight": "model-00001-of-00004.safetensors",
327
+ "vision_model.encoder.layers.14.attn.proj.bias": "model-00001-of-00004.safetensors",
328
+ "vision_model.encoder.layers.14.attn.proj.weight": "model-00001-of-00004.safetensors",
329
+ "vision_model.encoder.layers.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
330
+ "vision_model.encoder.layers.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
331
+ "vision_model.encoder.layers.14.ls1": "model-00001-of-00004.safetensors",
332
+ "vision_model.encoder.layers.14.ls2": "model-00001-of-00004.safetensors",
333
+ "vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00004.safetensors",
334
+ "vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00004.safetensors",
335
+ "vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00004.safetensors",
336
+ "vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00004.safetensors",
337
+ "vision_model.encoder.layers.14.norm1.bias": "model-00001-of-00004.safetensors",
338
+ "vision_model.encoder.layers.14.norm1.weight": "model-00001-of-00004.safetensors",
339
+ "vision_model.encoder.layers.14.norm2.bias": "model-00001-of-00004.safetensors",
340
+ "vision_model.encoder.layers.14.norm2.weight": "model-00001-of-00004.safetensors",
341
+ "vision_model.encoder.layers.15.attn.proj.bias": "model-00001-of-00004.safetensors",
342
+ "vision_model.encoder.layers.15.attn.proj.weight": "model-00001-of-00004.safetensors",
343
+ "vision_model.encoder.layers.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
344
+ "vision_model.encoder.layers.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
345
+ "vision_model.encoder.layers.15.ls1": "model-00001-of-00004.safetensors",
346
+ "vision_model.encoder.layers.15.ls2": "model-00001-of-00004.safetensors",
347
+ "vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00004.safetensors",
348
+ "vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00004.safetensors",
349
+ "vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00004.safetensors",
350
+ "vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00004.safetensors",
351
+ "vision_model.encoder.layers.15.norm1.bias": "model-00001-of-00004.safetensors",
352
+ "vision_model.encoder.layers.15.norm1.weight": "model-00001-of-00004.safetensors",
353
+ "vision_model.encoder.layers.15.norm2.bias": "model-00001-of-00004.safetensors",
354
+ "vision_model.encoder.layers.15.norm2.weight": "model-00001-of-00004.safetensors",
355
+ "vision_model.encoder.layers.16.attn.proj.bias": "model-00001-of-00004.safetensors",
356
+ "vision_model.encoder.layers.16.attn.proj.weight": "model-00001-of-00004.safetensors",
357
+ "vision_model.encoder.layers.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
358
+ "vision_model.encoder.layers.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
359
+ "vision_model.encoder.layers.16.ls1": "model-00001-of-00004.safetensors",
360
+ "vision_model.encoder.layers.16.ls2": "model-00001-of-00004.safetensors",
361
+ "vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00004.safetensors",
362
+ "vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00004.safetensors",
363
+ "vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00004.safetensors",
364
+ "vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00004.safetensors",
365
+ "vision_model.encoder.layers.16.norm1.bias": "model-00001-of-00004.safetensors",
366
+ "vision_model.encoder.layers.16.norm1.weight": "model-00001-of-00004.safetensors",
367
+ "vision_model.encoder.layers.16.norm2.bias": "model-00001-of-00004.safetensors",
368
+ "vision_model.encoder.layers.16.norm2.weight": "model-00001-of-00004.safetensors",
369
+ "vision_model.encoder.layers.17.attn.proj.bias": "model-00001-of-00004.safetensors",
370
+ "vision_model.encoder.layers.17.attn.proj.weight": "model-00001-of-00004.safetensors",
371
+ "vision_model.encoder.layers.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
372
+ "vision_model.encoder.layers.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
373
+ "vision_model.encoder.layers.17.ls1": "model-00001-of-00004.safetensors",
374
+ "vision_model.encoder.layers.17.ls2": "model-00001-of-00004.safetensors",
375
+ "vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00004.safetensors",
376
+ "vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00004.safetensors",
377
+ "vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00004.safetensors",
378
+ "vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00004.safetensors",
379
+ "vision_model.encoder.layers.17.norm1.bias": "model-00001-of-00004.safetensors",
380
+ "vision_model.encoder.layers.17.norm1.weight": "model-00001-of-00004.safetensors",
381
+ "vision_model.encoder.layers.17.norm2.bias": "model-00001-of-00004.safetensors",
382
+ "vision_model.encoder.layers.17.norm2.weight": "model-00001-of-00004.safetensors",
383
+ "vision_model.encoder.layers.18.attn.proj.bias": "model-00001-of-00004.safetensors",
384
+ "vision_model.encoder.layers.18.attn.proj.weight": "model-00001-of-00004.safetensors",
385
+ "vision_model.encoder.layers.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
386
+ "vision_model.encoder.layers.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
387
+ "vision_model.encoder.layers.18.ls1": "model-00001-of-00004.safetensors",
388
+ "vision_model.encoder.layers.18.ls2": "model-00001-of-00004.safetensors",
389
+ "vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00004.safetensors",
390
+ "vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00004.safetensors",
391
+ "vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00004.safetensors",
392
+ "vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00004.safetensors",
393
+ "vision_model.encoder.layers.18.norm1.bias": "model-00001-of-00004.safetensors",
394
+ "vision_model.encoder.layers.18.norm1.weight": "model-00001-of-00004.safetensors",
395
+ "vision_model.encoder.layers.18.norm2.bias": "model-00001-of-00004.safetensors",
396
+ "vision_model.encoder.layers.18.norm2.weight": "model-00001-of-00004.safetensors",
397
+ "vision_model.encoder.layers.19.attn.proj.bias": "model-00001-of-00004.safetensors",
398
+ "vision_model.encoder.layers.19.attn.proj.weight": "model-00001-of-00004.safetensors",
399
+ "vision_model.encoder.layers.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
400
+ "vision_model.encoder.layers.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
401
+ "vision_model.encoder.layers.19.ls1": "model-00001-of-00004.safetensors",
402
+ "vision_model.encoder.layers.19.ls2": "model-00001-of-00004.safetensors",
403
+ "vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00004.safetensors",
404
+ "vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00004.safetensors",
405
+ "vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00004.safetensors",
406
+ "vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00004.safetensors",
407
+ "vision_model.encoder.layers.19.norm1.bias": "model-00001-of-00004.safetensors",
408
+ "vision_model.encoder.layers.19.norm1.weight": "model-00001-of-00004.safetensors",
409
+ "vision_model.encoder.layers.19.norm2.bias": "model-00001-of-00004.safetensors",
410
+ "vision_model.encoder.layers.19.norm2.weight": "model-00001-of-00004.safetensors",
411
+ "vision_model.encoder.layers.2.attn.proj.bias": "model-00001-of-00004.safetensors",
412
+ "vision_model.encoder.layers.2.attn.proj.weight": "model-00001-of-00004.safetensors",
413
+ "vision_model.encoder.layers.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
414
+ "vision_model.encoder.layers.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
415
+ "vision_model.encoder.layers.2.ls1": "model-00001-of-00004.safetensors",
416
+ "vision_model.encoder.layers.2.ls2": "model-00001-of-00004.safetensors",
417
+ "vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00004.safetensors",
418
+ "vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
419
+ "vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00004.safetensors",
420
+ "vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
421
+ "vision_model.encoder.layers.2.norm1.bias": "model-00001-of-00004.safetensors",
422
+ "vision_model.encoder.layers.2.norm1.weight": "model-00001-of-00004.safetensors",
423
+ "vision_model.encoder.layers.2.norm2.bias": "model-00001-of-00004.safetensors",
424
+ "vision_model.encoder.layers.2.norm2.weight": "model-00001-of-00004.safetensors",
425
+ "vision_model.encoder.layers.20.attn.proj.bias": "model-00001-of-00004.safetensors",
426
+ "vision_model.encoder.layers.20.attn.proj.weight": "model-00001-of-00004.safetensors",
427
+ "vision_model.encoder.layers.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
428
+ "vision_model.encoder.layers.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
429
+ "vision_model.encoder.layers.20.ls1": "model-00001-of-00004.safetensors",
430
+ "vision_model.encoder.layers.20.ls2": "model-00001-of-00004.safetensors",
431
+ "vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00004.safetensors",
432
+ "vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00004.safetensors",
433
+ "vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00004.safetensors",
434
+ "vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00004.safetensors",
435
+ "vision_model.encoder.layers.20.norm1.bias": "model-00001-of-00004.safetensors",
436
+ "vision_model.encoder.layers.20.norm1.weight": "model-00001-of-00004.safetensors",
437
+ "vision_model.encoder.layers.20.norm2.bias": "model-00001-of-00004.safetensors",
438
+ "vision_model.encoder.layers.20.norm2.weight": "model-00001-of-00004.safetensors",
439
+ "vision_model.encoder.layers.21.attn.proj.bias": "model-00001-of-00004.safetensors",
440
+ "vision_model.encoder.layers.21.attn.proj.weight": "model-00001-of-00004.safetensors",
441
+ "vision_model.encoder.layers.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
442
+ "vision_model.encoder.layers.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
443
+ "vision_model.encoder.layers.21.ls1": "model-00001-of-00004.safetensors",
444
+ "vision_model.encoder.layers.21.ls2": "model-00001-of-00004.safetensors",
445
+ "vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00004.safetensors",
446
+ "vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00004.safetensors",
447
+ "vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00004.safetensors",
448
+ "vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00004.safetensors",
449
+ "vision_model.encoder.layers.21.norm1.bias": "model-00001-of-00004.safetensors",
450
+ "vision_model.encoder.layers.21.norm1.weight": "model-00001-of-00004.safetensors",
451
+ "vision_model.encoder.layers.21.norm2.bias": "model-00001-of-00004.safetensors",
452
+ "vision_model.encoder.layers.21.norm2.weight": "model-00001-of-00004.safetensors",
453
+ "vision_model.encoder.layers.22.attn.proj.bias": "model-00001-of-00004.safetensors",
454
+ "vision_model.encoder.layers.22.attn.proj.weight": "model-00001-of-00004.safetensors",
455
+ "vision_model.encoder.layers.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
456
+ "vision_model.encoder.layers.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
457
+ "vision_model.encoder.layers.22.ls1": "model-00001-of-00004.safetensors",
458
+ "vision_model.encoder.layers.22.ls2": "model-00001-of-00004.safetensors",
459
+ "vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00004.safetensors",
460
+ "vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00004.safetensors",
461
+ "vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00004.safetensors",
462
+ "vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00004.safetensors",
463
+ "vision_model.encoder.layers.22.norm1.bias": "model-00001-of-00004.safetensors",
464
+ "vision_model.encoder.layers.22.norm1.weight": "model-00001-of-00004.safetensors",
465
+ "vision_model.encoder.layers.22.norm2.bias": "model-00001-of-00004.safetensors",
466
+ "vision_model.encoder.layers.22.norm2.weight": "model-00001-of-00004.safetensors",
467
+ "vision_model.encoder.layers.23.attn.proj.bias": "model-00001-of-00004.safetensors",
468
+ "vision_model.encoder.layers.23.attn.proj.weight": "model-00001-of-00004.safetensors",
469
+ "vision_model.encoder.layers.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
470
+ "vision_model.encoder.layers.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
471
+ "vision_model.encoder.layers.23.ls1": "model-00001-of-00004.safetensors",
472
+ "vision_model.encoder.layers.23.ls2": "model-00001-of-00004.safetensors",
473
+ "vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00004.safetensors",
474
+ "vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00004.safetensors",
475
+ "vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00004.safetensors",
476
+ "vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00004.safetensors",
477
+ "vision_model.encoder.layers.23.norm1.bias": "model-00001-of-00004.safetensors",
478
+ "vision_model.encoder.layers.23.norm1.weight": "model-00001-of-00004.safetensors",
479
+ "vision_model.encoder.layers.23.norm2.bias": "model-00001-of-00004.safetensors",
480
+ "vision_model.encoder.layers.23.norm2.weight": "model-00001-of-00004.safetensors",
481
+ "vision_model.encoder.layers.3.attn.proj.bias": "model-00001-of-00004.safetensors",
482
+ "vision_model.encoder.layers.3.attn.proj.weight": "model-00001-of-00004.safetensors",
483
+ "vision_model.encoder.layers.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
484
+ "vision_model.encoder.layers.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
485
+ "vision_model.encoder.layers.3.ls1": "model-00001-of-00004.safetensors",
486
+ "vision_model.encoder.layers.3.ls2": "model-00001-of-00004.safetensors",
487
+ "vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00004.safetensors",
488
+ "vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
489
+ "vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00004.safetensors",
490
+ "vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
491
+ "vision_model.encoder.layers.3.norm1.bias": "model-00001-of-00004.safetensors",
492
+ "vision_model.encoder.layers.3.norm1.weight": "model-00001-of-00004.safetensors",
493
+ "vision_model.encoder.layers.3.norm2.bias": "model-00001-of-00004.safetensors",
494
+ "vision_model.encoder.layers.3.norm2.weight": "model-00001-of-00004.safetensors",
495
+ "vision_model.encoder.layers.4.attn.proj.bias": "model-00001-of-00004.safetensors",
496
+ "vision_model.encoder.layers.4.attn.proj.weight": "model-00001-of-00004.safetensors",
497
+ "vision_model.encoder.layers.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
498
+ "vision_model.encoder.layers.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
499
+ "vision_model.encoder.layers.4.ls1": "model-00001-of-00004.safetensors",
500
+ "vision_model.encoder.layers.4.ls2": "model-00001-of-00004.safetensors",
501
+ "vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00004.safetensors",
502
+ "vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
503
+ "vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00004.safetensors",
504
+ "vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
505
+ "vision_model.encoder.layers.4.norm1.bias": "model-00001-of-00004.safetensors",
506
+ "vision_model.encoder.layers.4.norm1.weight": "model-00001-of-00004.safetensors",
507
+ "vision_model.encoder.layers.4.norm2.bias": "model-00001-of-00004.safetensors",
508
+ "vision_model.encoder.layers.4.norm2.weight": "model-00001-of-00004.safetensors",
509
+ "vision_model.encoder.layers.5.attn.proj.bias": "model-00001-of-00004.safetensors",
510
+ "vision_model.encoder.layers.5.attn.proj.weight": "model-00001-of-00004.safetensors",
511
+ "vision_model.encoder.layers.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
512
+ "vision_model.encoder.layers.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
513
+ "vision_model.encoder.layers.5.ls1": "model-00001-of-00004.safetensors",
514
+ "vision_model.encoder.layers.5.ls2": "model-00001-of-00004.safetensors",
515
+ "vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00004.safetensors",
516
+ "vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
517
+ "vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00004.safetensors",
518
+ "vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
519
+ "vision_model.encoder.layers.5.norm1.bias": "model-00001-of-00004.safetensors",
520
+ "vision_model.encoder.layers.5.norm1.weight": "model-00001-of-00004.safetensors",
521
+ "vision_model.encoder.layers.5.norm2.bias": "model-00001-of-00004.safetensors",
522
+ "vision_model.encoder.layers.5.norm2.weight": "model-00001-of-00004.safetensors",
523
+ "vision_model.encoder.layers.6.attn.proj.bias": "model-00001-of-00004.safetensors",
524
+ "vision_model.encoder.layers.6.attn.proj.weight": "model-00001-of-00004.safetensors",
525
+ "vision_model.encoder.layers.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
526
+ "vision_model.encoder.layers.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
527
+ "vision_model.encoder.layers.6.ls1": "model-00001-of-00004.safetensors",
528
+ "vision_model.encoder.layers.6.ls2": "model-00001-of-00004.safetensors",
529
+ "vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00004.safetensors",
530
+ "vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
531
+ "vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00004.safetensors",
532
+ "vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
533
+ "vision_model.encoder.layers.6.norm1.bias": "model-00001-of-00004.safetensors",
534
+ "vision_model.encoder.layers.6.norm1.weight": "model-00001-of-00004.safetensors",
535
+ "vision_model.encoder.layers.6.norm2.bias": "model-00001-of-00004.safetensors",
536
+ "vision_model.encoder.layers.6.norm2.weight": "model-00001-of-00004.safetensors",
537
+ "vision_model.encoder.layers.7.attn.proj.bias": "model-00001-of-00004.safetensors",
538
+ "vision_model.encoder.layers.7.attn.proj.weight": "model-00001-of-00004.safetensors",
539
+ "vision_model.encoder.layers.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
540
+ "vision_model.encoder.layers.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
541
+ "vision_model.encoder.layers.7.ls1": "model-00001-of-00004.safetensors",
542
+ "vision_model.encoder.layers.7.ls2": "model-00001-of-00004.safetensors",
543
+ "vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00004.safetensors",
544
+ "vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
545
+ "vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00004.safetensors",
546
+ "vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
547
+ "vision_model.encoder.layers.7.norm1.bias": "model-00001-of-00004.safetensors",
548
+ "vision_model.encoder.layers.7.norm1.weight": "model-00001-of-00004.safetensors",
549
+ "vision_model.encoder.layers.7.norm2.bias": "model-00001-of-00004.safetensors",
550
+ "vision_model.encoder.layers.7.norm2.weight": "model-00001-of-00004.safetensors",
551
+ "vision_model.encoder.layers.8.attn.proj.bias": "model-00001-of-00004.safetensors",
552
+ "vision_model.encoder.layers.8.attn.proj.weight": "model-00001-of-00004.safetensors",
553
+ "vision_model.encoder.layers.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
554
+ "vision_model.encoder.layers.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
555
+ "vision_model.encoder.layers.8.ls1": "model-00001-of-00004.safetensors",
556
+ "vision_model.encoder.layers.8.ls2": "model-00001-of-00004.safetensors",
557
+ "vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00004.safetensors",
558
+ "vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
559
+ "vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00004.safetensors",
560
+ "vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
561
+ "vision_model.encoder.layers.8.norm1.bias": "model-00001-of-00004.safetensors",
562
+ "vision_model.encoder.layers.8.norm1.weight": "model-00001-of-00004.safetensors",
563
+ "vision_model.encoder.layers.8.norm2.bias": "model-00001-of-00004.safetensors",
564
+ "vision_model.encoder.layers.8.norm2.weight": "model-00001-of-00004.safetensors",
565
+ "vision_model.encoder.layers.9.attn.proj.bias": "model-00001-of-00004.safetensors",
566
+ "vision_model.encoder.layers.9.attn.proj.weight": "model-00001-of-00004.safetensors",
567
+ "vision_model.encoder.layers.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
568
+ "vision_model.encoder.layers.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
569
+ "vision_model.encoder.layers.9.ls1": "model-00001-of-00004.safetensors",
570
+ "vision_model.encoder.layers.9.ls2": "model-00001-of-00004.safetensors",
571
+ "vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00004.safetensors",
572
+ "vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
573
+ "vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00004.safetensors",
574
+ "vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
575
+ "vision_model.encoder.layers.9.norm1.bias": "model-00001-of-00004.safetensors",
576
+ "vision_model.encoder.layers.9.norm1.weight": "model-00001-of-00004.safetensors",
577
+ "vision_model.encoder.layers.9.norm2.bias": "model-00001-of-00004.safetensors",
578
+ "vision_model.encoder.layers.9.norm2.weight": "model-00001-of-00004.safetensors"
579
+ }
580
+ }
checkpoint-84/special_tokens_map.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|action_start|>",
6
+ "<|action_end|>",
7
+ "<|interpreter|>",
8
+ "<|plugin|>",
9
+ "<img>",
10
+ "</img>",
11
+ "<IMG_CONTEXT>",
12
+ "<quad>",
13
+ "</quad>",
14
+ "<ref>",
15
+ "</ref>",
16
+ "<box>",
17
+ "</box>",
18
+ {
19
+ "content": "<prm>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ }
25
+ ],
26
+ "bos_token": {
27
+ "content": "<s>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ },
33
+ "eos_token": {
34
+ "content": "</s>",
35
+ "lstrip": false,
36
+ "normalized": false,
37
+ "rstrip": false,
38
+ "single_word": false
39
+ },
40
+ "pad_token": {
41
+ "content": "</s>",
42
+ "lstrip": false,
43
+ "normalized": false,
44
+ "rstrip": false,
45
+ "single_word": false
46
+ },
47
+ "unk_token": {
48
+ "content": "<unk>",
49
+ "lstrip": false,
50
+ "normalized": false,
51
+ "rstrip": false,
52
+ "single_word": false
53
+ }
54
+ }
checkpoint-84/tokenization_internlm2.py ADDED
@@ -0,0 +1,235 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Copyright (c) The InternLM team and The HuggingFace Inc. team. All rights reserved.
2
+ #
3
+ # This code is based on transformers/src/transformers/models/llama/tokenization_llama.py
4
+ #
5
+ # Licensed under the Apache License, Version 2.0 (the "License");
6
+ # you may not use this file except in compliance with the License.
7
+ # You may obtain a copy of the License at
8
+ #
9
+ # http://www.apache.org/licenses/LICENSE-2.0
10
+ #
11
+ # Unless required by applicable law or agreed to in writing, software
12
+ # distributed under the License is distributed on an "AS IS" BASIS,
13
+ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14
+ # See the License for the specific language governing permissions and
15
+ # limitations under the License.
16
+
17
+ """Tokenization classes for InternLM."""
18
+ import os
19
+ from shutil import copyfile
20
+ from typing import Any, Dict, List, Optional, Tuple
21
+
22
+ import sentencepiece as spm
23
+ from transformers.tokenization_utils import PreTrainedTokenizer
24
+ from transformers.utils import logging
25
+
26
+ logger = logging.get_logger(__name__)
27
+
28
+ VOCAB_FILES_NAMES = {'vocab_file': './tokenizer.model'}
29
+
30
+ PRETRAINED_VOCAB_FILES_MAP = {}
31
+
32
+
33
+ # Modified from transformers.model.llama.tokenization_llama.LlamaTokenizer
34
+ class InternLM2Tokenizer(PreTrainedTokenizer):
35
+ """
36
+ Construct a InternLM2 tokenizer. Based on byte-level Byte-Pair-Encoding.
37
+
38
+ Args:
39
+ vocab_file (`str`):
40
+ Path to the vocabulary file.
41
+ """
42
+
43
+ vocab_files_names = VOCAB_FILES_NAMES
44
+ pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
45
+ model_input_names = ['input_ids', 'attention_mask']
46
+ _auto_class = 'AutoTokenizer'
47
+
48
+ def __init__(
49
+ self,
50
+ vocab_file,
51
+ unk_token='<unk>',
52
+ bos_token='<s>',
53
+ eos_token='</s>',
54
+ pad_token='</s>',
55
+ sp_model_kwargs: Optional[Dict[str, Any]] = None,
56
+ add_bos_token=True,
57
+ add_eos_token=False,
58
+ decode_with_prefix_space=False,
59
+ clean_up_tokenization_spaces=False,
60
+ **kwargs,
61
+ ):
62
+ self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs
63
+ self.vocab_file = vocab_file
64
+ self.add_bos_token = add_bos_token
65
+ self.add_eos_token = add_eos_token
66
+ self.decode_with_prefix_space = decode_with_prefix_space
67
+ self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
68
+ self.sp_model.Load(vocab_file)
69
+ self._no_prefix_space_tokens = None
70
+ super().__init__(
71
+ bos_token=bos_token,
72
+ eos_token=eos_token,
73
+ unk_token=unk_token,
74
+ pad_token=pad_token,
75
+ clean_up_tokenization_spaces=clean_up_tokenization_spaces,
76
+ **kwargs,
77
+ )
78
+
79
+ @property
80
+ def no_prefix_space_tokens(self):
81
+ if self._no_prefix_space_tokens is None:
82
+ vocab = self.convert_ids_to_tokens(list(range(self.vocab_size)))
83
+ self._no_prefix_space_tokens = {i for i, tok in enumerate(vocab) if not tok.startswith('▁')}
84
+ return self._no_prefix_space_tokens
85
+
86
+ @property
87
+ def vocab_size(self):
88
+ """Returns vocab size"""
89
+ return self.sp_model.get_piece_size()
90
+
91
+ @property
92
+ def bos_token_id(self) -> Optional[int]:
93
+ return self.sp_model.bos_id()
94
+
95
+ @property
96
+ def eos_token_id(self) -> Optional[int]:
97
+ return self.sp_model.eos_id()
98
+
99
+ def get_vocab(self):
100
+ """Returns vocab as a dict"""
101
+ vocab = {self.convert_ids_to_tokens(i): i for i in range(self.vocab_size)}
102
+ vocab.update(self.added_tokens_encoder)
103
+ return vocab
104
+
105
+ def _tokenize(self, text):
106
+ """Returns a tokenized string."""
107
+ return self.sp_model.encode(text, out_type=str)
108
+
109
+ def _convert_token_to_id(self, token):
110
+ """Converts a token (str) in an id using the vocab."""
111
+ return self.sp_model.piece_to_id(token)
112
+
113
+ def _convert_id_to_token(self, index):
114
+ """Converts an index (integer) in a token (str) using the vocab."""
115
+ token = self.sp_model.IdToPiece(index)
116
+ return token
117
+
118
+ def _maybe_add_prefix_space(self, tokens, decoded):
119
+ if tokens and tokens[0] not in self.no_prefix_space_tokens:
120
+ return ' ' + decoded
121
+ else:
122
+ return decoded
123
+
124
+ def convert_tokens_to_string(self, tokens):
125
+ """Converts a sequence of tokens (string) in a single string."""
126
+ current_sub_tokens = []
127
+ out_string = ''
128
+ prev_is_special = False
129
+ for token in tokens:
130
+ # make sure that special tokens are not decoded using sentencepiece model
131
+ if token in self.all_special_tokens:
132
+ if not prev_is_special:
133
+ out_string += ' '
134
+ out_string += self.sp_model.decode(current_sub_tokens) + token
135
+ prev_is_special = True
136
+ current_sub_tokens = []
137
+ else:
138
+ current_sub_tokens.append(token)
139
+ prev_is_special = False
140
+ out_string += self.sp_model.decode(current_sub_tokens)
141
+ out_string = self.clean_up_tokenization(out_string)
142
+ out_string = self._maybe_add_prefix_space(tokens=tokens, decoded=out_string)
143
+ return out_string[1:]
144
+
145
+ def save_vocabulary(self, save_directory, filename_prefix: Optional[str] = None) -> Tuple[str]:
146
+ """
147
+ Save the vocabulary and special tokens file to a directory.
148
+
149
+ Args:
150
+ save_directory (`str`):
151
+ The directory in which to save the vocabulary.
152
+
153
+ Returns:
154
+ `Tuple(str)`: Paths to the files saved.
155
+ """
156
+ if not os.path.isdir(save_directory):
157
+ logger.error(f'Vocabulary path ({save_directory}) should be a directory')
158
+ return
159
+ out_vocab_file = os.path.join(
160
+ save_directory, (filename_prefix + '-' if filename_prefix else '') + VOCAB_FILES_NAMES['vocab_file']
161
+ )
162
+
163
+ if os.path.abspath(self.vocab_file) != os.path.abspath(out_vocab_file) and os.path.isfile(self.vocab_file):
164
+ copyfile(self.vocab_file, out_vocab_file)
165
+ elif not os.path.isfile(self.vocab_file):
166
+ with open(out_vocab_file, 'wb') as fi:
167
+ content_spiece_model = self.sp_model.serialized_model_proto()
168
+ fi.write(content_spiece_model)
169
+
170
+ return (out_vocab_file,)
171
+
172
+ def build_inputs_with_special_tokens(self, token_ids_0, token_ids_1=None):
173
+ if self.add_bos_token:
174
+ bos_token_ids = [self.bos_token_id]
175
+ else:
176
+ bos_token_ids = []
177
+
178
+ output = bos_token_ids + token_ids_0
179
+
180
+ if token_ids_1 is not None:
181
+ output = output + token_ids_1
182
+
183
+ if self.add_eos_token:
184
+ output = output + [self.eos_token_id]
185
+
186
+ return output
187
+
188
+ def get_special_tokens_mask(
189
+ self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None, already_has_special_tokens: bool = False
190
+ ) -> List[int]:
191
+ """
192
+ Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding
193
+ special tokens using the tokenizer `prepare_for_model` method.
194
+
195
+ Args:
196
+ token_ids_0 (`List[int]`):
197
+ List of IDs.
198
+ token_ids_1 (`List[int]`, *optional*):
199
+ Optional second list of IDs for sequence pairs.
200
+ already_has_special_tokens (`bool`, *optional*, defaults to `False`):
201
+ Whether or not the token list is already formatted with special tokens for the model.
202
+
203
+ Returns:
204
+ `List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
205
+ """
206
+ if already_has_special_tokens:
207
+ return super().get_special_tokens_mask(
208
+ token_ids_0=token_ids_0, token_ids_1=token_ids_1, already_has_special_tokens=True
209
+ )
210
+
211
+ if token_ids_1 is None:
212
+ return [1] + ([0] * len(token_ids_0)) + [1]
213
+ return [1] + ([0] * len(token_ids_0)) + [1, 1] + ([0] * len(token_ids_1)) + [1]
214
+
215
+ def create_token_type_ids_from_sequences(
216
+ self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
217
+ ) -> List[int]:
218
+ """
219
+ Create a mask from the two sequences passed to be used in a sequence-pair classification task. T5 does not make
220
+ use of token type ids, therefore a list of zeros is returned.
221
+
222
+ Args:
223
+ token_ids_0 (`List[int]`):
224
+ List of IDs.
225
+ token_ids_1 (`List[int]`, *optional*):
226
+ Optional second list of IDs for sequence pairs.
227
+
228
+ Returns:
229
+ `List[int]`: List of zeros.
230
+ """
231
+ eos = [self.eos_token_id]
232
+
233
+ if token_ids_1 is None:
234
+ return len(token_ids_0 + eos) * [0]
235
+ return len(token_ids_0 + eos + token_ids_1 + eos) * [0]
checkpoint-84/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f868398fc4e05ee1e8aeba95ddf18ddcc45b8bce55d5093bead5bbf80429b48b
3
+ size 1477754
checkpoint-84/tokenizer_config.json ADDED
@@ -0,0 +1,189 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "92538": {
28
+ "content": "<|plugin|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "92539": {
36
+ "content": "<|interpreter|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "92540": {
44
+ "content": "<|action_end|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "92541": {
52
+ "content": "<|action_start|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "92542": {
60
+ "content": "<|im_end|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "92543": {
68
+ "content": "<|im_start|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "92544": {
76
+ "content": "<img>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "92545": {
84
+ "content": "</img>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "92546": {
92
+ "content": "<IMG_CONTEXT>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "92547": {
100
+ "content": "<quad>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "92548": {
108
+ "content": "</quad>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "92549": {
116
+ "content": "<ref>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "92550": {
124
+ "content": "</ref>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "92551": {
132
+ "content": "<box>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "92552": {
140
+ "content": "</box>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "92553": {
148
+ "content": "<prm>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ }
155
+ },
156
+ "additional_special_tokens": [
157
+ "<|im_start|>",
158
+ "<|im_end|>",
159
+ "<|action_start|>",
160
+ "<|action_end|>",
161
+ "<|interpreter|>",
162
+ "<|plugin|>",
163
+ "<img>",
164
+ "</img>",
165
+ "<IMG_CONTEXT>",
166
+ "<quad>",
167
+ "</quad>",
168
+ "<ref>",
169
+ "</ref>",
170
+ "<box>",
171
+ "</box>",
172
+ "<prm>"
173
+ ],
174
+ "auto_map": {
175
+ "AutoTokenizer": [
176
+ "tokenization_internlm2.InternLM2Tokenizer",
177
+ null
178
+ ]
179
+ },
180
+ "bos_token": "<s>",
181
+ "chat_template": "{{ bos_token }}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
182
+ "clean_up_tokenization_spaces": false,
183
+ "eos_token": "</s>",
184
+ "extra_special_tokens": {},
185
+ "model_max_length": 8192,
186
+ "pad_token": "</s>",
187
+ "tokenizer_class": "InternLM2Tokenizer",
188
+ "unk_token": "<unk>"
189
+ }
checkpoint-84/trainer_state.json ADDED
@@ -0,0 +1,621 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9926144756277696,
5
+ "eval_steps": 500,
6
+ "global_step": 84,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.011816838995568686,
13
+ "grad_norm": 141.58821940810319,
14
+ "learning_rate": 2.0000000000000003e-06,
15
+ "loss": 24.7396,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.023633677991137372,
20
+ "grad_norm": 143.0826093691902,
21
+ "learning_rate": 4.000000000000001e-06,
22
+ "loss": 24.9928,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.03545051698670606,
27
+ "grad_norm": 106.05432186386774,
28
+ "learning_rate": 6e-06,
29
+ "loss": 18.2222,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.047267355982274745,
34
+ "grad_norm": 19.635338999926788,
35
+ "learning_rate": 8.000000000000001e-06,
36
+ "loss": 7.9201,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.059084194977843424,
41
+ "grad_norm": 13.95265170436528,
42
+ "learning_rate": 1e-05,
43
+ "loss": 7.5088,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.07090103397341212,
48
+ "grad_norm": 10.13890459339853,
49
+ "learning_rate": 9.99604698613651e-06,
50
+ "loss": 7.5049,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.0827178729689808,
55
+ "grad_norm": 5.161331048523965,
56
+ "learning_rate": 9.98419419507348e-06,
57
+ "loss": 3.6598,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.09453471196454949,
62
+ "grad_norm": 139.7527677361183,
63
+ "learning_rate": 9.964460368509868e-06,
64
+ "loss": 21.683,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.10635155096011817,
69
+ "grad_norm": 17.32001191129204,
70
+ "learning_rate": 9.936876709681668e-06,
71
+ "loss": 6.269,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.11816838995568685,
76
+ "grad_norm": 3.6667439464627005,
77
+ "learning_rate": 9.901486834023182e-06,
78
+ "loss": 3.9577,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.12998522895125553,
83
+ "grad_norm": 4.3142551112177125,
84
+ "learning_rate": 9.85834670020205e-06,
85
+ "loss": 4.2225,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.14180206794682423,
90
+ "grad_norm": 2.554707938100202,
91
+ "learning_rate": 9.807524521637103e-06,
92
+ "loss": 3.8235,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.1536189069423929,
97
+ "grad_norm": 3.902409900663783,
98
+ "learning_rate": 9.749100658638914e-06,
99
+ "loss": 3.488,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.1654357459379616,
104
+ "grad_norm": 1.9177071201200944,
105
+ "learning_rate": 9.68316749134364e-06,
106
+ "loss": 3.6343,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.17725258493353027,
111
+ "grad_norm": 2.343695570919709,
112
+ "learning_rate": 9.609829273641034e-06,
113
+ "loss": 2.4759,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.18906942392909898,
118
+ "grad_norm": 2.670990461737092,
119
+ "learning_rate": 9.529201968327618e-06,
120
+ "loss": 2.8148,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.20088626292466766,
125
+ "grad_norm": 4.035538523683045,
126
+ "learning_rate": 9.44141306374566e-06,
127
+ "loss": 3.5358,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.21270310192023634,
132
+ "grad_norm": 1.9700378149332556,
133
+ "learning_rate": 9.346601372197914e-06,
134
+ "loss": 2.4168,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.22451994091580502,
139
+ "grad_norm": 1.5664890777552727,
140
+ "learning_rate": 9.244916810456822e-06,
141
+ "loss": 2.8056,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.2363367799113737,
146
+ "grad_norm": 2.4581786199164166,
147
+ "learning_rate": 9.136520162715288e-06,
148
+ "loss": 2.7812,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.2481536189069424,
153
+ "grad_norm": 1.1245546722153261,
154
+ "learning_rate": 9.021582826353825e-06,
155
+ "loss": 2.1436,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.25997045790251105,
160
+ "grad_norm": 1.7893027067897964,
161
+ "learning_rate": 8.900286540926062e-06,
162
+ "loss": 2.2205,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.2717872968980798,
167
+ "grad_norm": 3.9769501645462864,
168
+ "learning_rate": 8.772823100791152e-06,
169
+ "loss": 2.9946,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.28360413589364847,
174
+ "grad_norm": 3.7789691171773834,
175
+ "learning_rate": 8.639394051847472e-06,
176
+ "loss": 2.3066,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.29542097488921715,
181
+ "grad_norm": 5.6315683255278675,
182
+ "learning_rate": 8.500210372847128e-06,
183
+ "loss": 2.5008,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.3072378138847858,
188
+ "grad_norm": 1.8586124427568678,
189
+ "learning_rate": 8.355492141795185e-06,
190
+ "loss": 2.5177,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.3190546528803545,
195
+ "grad_norm": 1.7546209315437058,
196
+ "learning_rate": 8.2054681879611e-06,
197
+ "loss": 1.831,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.3308714918759232,
202
+ "grad_norm": 1.720970962604252,
203
+ "learning_rate": 8.050375730052622e-06,
204
+ "loss": 1.7447,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.34268833087149186,
209
+ "grad_norm": 1.464450414082788,
210
+ "learning_rate": 7.890460001124242e-06,
211
+ "loss": 2.2377,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.35450516986706054,
216
+ "grad_norm": 3.8274378731294636,
217
+ "learning_rate": 7.725973860813338e-06,
218
+ "loss": 2.3531,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.3663220088626292,
223
+ "grad_norm": 2.201173488939731,
224
+ "learning_rate": 7.5571773955171124e-06,
225
+ "loss": 2.1743,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.37813884785819796,
230
+ "grad_norm": 1.8071635950710907,
231
+ "learning_rate": 7.3843375071425315e-06,
232
+ "loss": 2.1838,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.38995568685376664,
237
+ "grad_norm": 1.7885207161263894,
238
+ "learning_rate": 7.2077274910795605e-06,
239
+ "loss": 1.7424,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.4017725258493353,
244
+ "grad_norm": 1.1269226512915496,
245
+ "learning_rate": 7.02762660406497e-06,
246
+ "loss": 1.7356,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.413589364844904,
251
+ "grad_norm": 1.075428967398824,
252
+ "learning_rate": 6.844319622620039e-06,
253
+ "loss": 1.8519,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.4254062038404727,
258
+ "grad_norm": 1.8285203027282286,
259
+ "learning_rate": 6.65809639276034e-06,
260
+ "loss": 1.9009,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.43722304283604135,
265
+ "grad_norm": 1.221068738720484,
266
+ "learning_rate": 6.469251371689606e-06,
267
+ "loss": 1.8889,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.44903988183161003,
272
+ "grad_norm": 1.60803342403716,
273
+ "learning_rate": 6.278083162202374e-06,
274
+ "loss": 2.0017,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.4608567208271787,
279
+ "grad_norm": 1.9615040257279748,
280
+ "learning_rate": 6.084894040531591e-06,
281
+ "loss": 2.0796,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.4726735598227474,
286
+ "grad_norm": 1.2009289522437243,
287
+ "learning_rate": 5.8899894783877536e-06,
288
+ "loss": 1.8679,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.4844903988183161,
293
+ "grad_norm": 1.6689113415110217,
294
+ "learning_rate": 5.693677659945343e-06,
295
+ "loss": 2.3915,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.4963072378138848,
300
+ "grad_norm": 2.252147221246225,
301
+ "learning_rate": 5.496268994540309e-06,
302
+ "loss": 2.3211,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.5081240768094535,
307
+ "grad_norm": 1.2607762998685017,
308
+ "learning_rate": 5.2980756258491e-06,
309
+ "loss": 1.9496,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.5199409158050221,
314
+ "grad_norm": 1.508309898485357,
315
+ "learning_rate": 5.099410938325351e-06,
316
+ "loss": 1.5493,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.5317577548005908,
321
+ "grad_norm": 1.8042049460482938,
322
+ "learning_rate": 4.900589061674649e-06,
323
+ "loss": 2.2117,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.5435745937961596,
328
+ "grad_norm": 2.255421993651045,
329
+ "learning_rate": 4.701924374150901e-06,
330
+ "loss": 1.846,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.5553914327917282,
335
+ "grad_norm": 1.6799486878239873,
336
+ "learning_rate": 4.5037310054596936e-06,
337
+ "loss": 1.8405,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.5672082717872969,
342
+ "grad_norm": 1.0181344550017597,
343
+ "learning_rate": 4.30632234005466e-06,
344
+ "loss": 1.6842,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.5790251107828656,
349
+ "grad_norm": 0.9377690889079295,
350
+ "learning_rate": 4.11001052161225e-06,
351
+ "loss": 1.3471,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.5908419497784343,
356
+ "grad_norm": 1.0604544664904838,
357
+ "learning_rate": 3.91510595946841e-06,
358
+ "loss": 1.4419,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.6026587887740029,
363
+ "grad_norm": 1.3183889991350504,
364
+ "learning_rate": 3.721916837797627e-06,
365
+ "loss": 1.1625,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.6144756277695717,
370
+ "grad_norm": 1.3309506270053526,
371
+ "learning_rate": 3.5307486283103966e-06,
372
+ "loss": 1.8204,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.6262924667651403,
377
+ "grad_norm": 1.3908020842677533,
378
+ "learning_rate": 3.3419036072396614e-06,
379
+ "loss": 2.0076,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.638109305760709,
384
+ "grad_norm": 1.8045527771613592,
385
+ "learning_rate": 3.1556803773799616e-06,
386
+ "loss": 1.9708,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.6499261447562777,
391
+ "grad_norm": 1.6155589691159733,
392
+ "learning_rate": 2.972373395935031e-06,
393
+ "loss": 2.3293,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.6617429837518464,
398
+ "grad_norm": 1.1333893122029324,
399
+ "learning_rate": 2.792272508920443e-06,
400
+ "loss": 1.4237,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.6735598227474151,
405
+ "grad_norm": 1.283105098512756,
406
+ "learning_rate": 2.615662492857471e-06,
407
+ "loss": 2.0387,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.6853766617429837,
412
+ "grad_norm": 1.2055699321798468,
413
+ "learning_rate": 2.4428226044828896e-06,
414
+ "loss": 2.1093,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.6971935007385525,
419
+ "grad_norm": 1.46291581605696,
420
+ "learning_rate": 2.2740261391866634e-06,
421
+ "loss": 2.0646,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.7090103397341211,
426
+ "grad_norm": 1.354252095411459,
427
+ "learning_rate": 2.1095399988757574e-06,
428
+ "loss": 2.0771,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.7208271787296898,
433
+ "grad_norm": 2.2359351678824346,
434
+ "learning_rate": 1.949624269947378e-06,
435
+ "loss": 1.5331,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.7326440177252584,
440
+ "grad_norm": 2.611963554561244,
441
+ "learning_rate": 1.794531812038901e-06,
442
+ "loss": 1.7467,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.7444608567208272,
447
+ "grad_norm": 2.004867953108283,
448
+ "learning_rate": 1.6445078582048158e-06,
449
+ "loss": 2.0128,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.7562776957163959,
454
+ "grad_norm": 1.1958237987023843,
455
+ "learning_rate": 1.499789627152874e-06,
456
+ "loss": 1.7522,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.7680945347119645,
461
+ "grad_norm": 1.3451993672754103,
462
+ "learning_rate": 1.3606059481525296e-06,
463
+ "loss": 2.1617,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.7799113737075333,
468
+ "grad_norm": 1.5021049478411668,
469
+ "learning_rate": 1.227176899208849e-06,
470
+ "loss": 1.5243,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.7917282127031019,
475
+ "grad_norm": 0.8944669191514794,
476
+ "learning_rate": 1.09971345907394e-06,
477
+ "loss": 1.2521,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.8035450516986706,
482
+ "grad_norm": 2.1538270859821806,
483
+ "learning_rate": 9.784171736461762e-07,
484
+ "loss": 1.7906,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.8153618906942393,
489
+ "grad_norm": 1.3437372655995639,
490
+ "learning_rate": 8.634798372847148e-07,
491
+ "loss": 1.4159,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.827178729689808,
496
+ "grad_norm": 2.591952439654916,
497
+ "learning_rate": 7.550831895431799e-07,
498
+ "loss": 2.2183,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.8389955686853766,
503
+ "grad_norm": 1.1280617832761364,
504
+ "learning_rate": 6.533986278020876e-07,
505
+ "loss": 1.5536,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.8508124076809453,
510
+ "grad_norm": 2.3847807482487284,
511
+ "learning_rate": 5.585869362543416e-07,
512
+ "loss": 1.9509,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.8626292466765141,
517
+ "grad_norm": 1.0033166957629358,
518
+ "learning_rate": 4.707980316723837e-07,
519
+ "loss": 1.5954,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.8744460856720827,
524
+ "grad_norm": 1.2000006716817688,
525
+ "learning_rate": 3.9017072635896716e-07,
526
+ "loss": 1.7373,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.8862629246676514,
531
+ "grad_norm": 1.9758624464832955,
532
+ "learning_rate": 3.168325086563612e-07,
533
+ "loss": 1.8503,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.8980797636632201,
538
+ "grad_norm": 1.496904248898433,
539
+ "learning_rate": 2.5089934136108665e-07,
540
+ "loss": 1.87,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.9098966026587888,
545
+ "grad_norm": 1.5024973288826626,
546
+ "learning_rate": 1.9247547836289792e-07,
547
+ "loss": 1.9597,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.9217134416543574,
552
+ "grad_norm": 1.127157992127101,
553
+ "learning_rate": 1.4165329979794972e-07,
554
+ "loss": 1.6419,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.9335302806499262,
559
+ "grad_norm": 1.060797857457364,
560
+ "learning_rate": 9.851316597681959e-08,
561
+ "loss": 1.1101,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.9453471196454948,
566
+ "grad_norm": 1.710935010210181,
567
+ "learning_rate": 6.31232903183332e-08,
568
+ "loss": 1.3758,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.9571639586410635,
573
+ "grad_norm": 1.2078229826303308,
574
+ "learning_rate": 3.553963149013295e-08,
575
+ "loss": 1.9823,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.9689807976366323,
580
+ "grad_norm": 1.149901610435076,
581
+ "learning_rate": 1.580580492652084e-08,
582
+ "loss": 1.7658,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.9807976366322009,
587
+ "grad_norm": 1.7045657504563692,
588
+ "learning_rate": 3.953013863490784e-09,
589
+ "loss": 1.8352,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.9926144756277696,
594
+ "grad_norm": 0.9173356348350563,
595
+ "learning_rate": 0.0,
596
+ "loss": 1.7623,
597
+ "step": 84
598
+ }
599
+ ],
600
+ "logging_steps": 1.0,
601
+ "max_steps": 84,
602
+ "num_input_tokens_seen": 0,
603
+ "num_train_epochs": 1,
604
+ "save_steps": 50,
605
+ "stateful_callbacks": {
606
+ "TrainerControl": {
607
+ "args": {
608
+ "should_epoch_stop": false,
609
+ "should_evaluate": false,
610
+ "should_log": false,
611
+ "should_save": true,
612
+ "should_training_stop": true
613
+ },
614
+ "attributes": {}
615
+ }
616
+ },
617
+ "total_flos": 2.4692764709042835e+20,
618
+ "train_batch_size": 2,
619
+ "trial_name": null,
620
+ "trial_params": null
621
+ }
checkpoint-84/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b51f13a383cffb413ff7951e403fc4324c59ea047b57ad6b157ee6196c8552d3
3
+ size 7544
config.json ADDED
@@ -0,0 +1,206 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": "e9e4c0dc1db56bfab10458671519b7fa3dd29463",
3
+ "_name_or_path": "OpenGVLab/InternVL2_5-8B",
4
+ "architectures": [
5
+ "InternVLChatModel"
6
+ ],
7
+ "auto_map": {
8
+ "AutoConfig": "OpenGVLab/InternVL2_5-8B--configuration_internvl_chat.InternVLChatConfig",
9
+ "AutoModel": "OpenGVLab/InternVL2_5-8B--modeling_internvl_chat.InternVLChatModel",
10
+ "AutoModelForCausalLM": "OpenGVLab/InternVL2_5-8B--modeling_internvl_chat.InternVLChatModel"
11
+ },
12
+ "downsample_ratio": 0.5,
13
+ "dynamic_image_size": true,
14
+ "force_image_size": 448,
15
+ "hidden_size": 4096,
16
+ "llm_config": {
17
+ "_attn_implementation_autoset": true,
18
+ "_name_or_path": "internlm/internlm2_5-7b-chat",
19
+ "add_cross_attention": false,
20
+ "architectures": [
21
+ "InternLM2ForCausalLM"
22
+ ],
23
+ "attn_implementation": "flash_attention_2",
24
+ "auto_map": {
25
+ "AutoConfig": "configuration_internlm2.InternLM2Config",
26
+ "AutoModel": "modeling_internlm2.InternLM2ForCausalLM",
27
+ "AutoModelForCausalLM": "modeling_internlm2.InternLM2ForCausalLM",
28
+ "AutoModelForSequenceClassification": "modeling_internlm2.InternLM2ForSequenceClassification"
29
+ },
30
+ "bad_words_ids": null,
31
+ "begin_suppress_tokens": null,
32
+ "bias": false,
33
+ "bos_token_id": 1,
34
+ "chunk_size_feed_forward": 0,
35
+ "cross_attention_hidden_size": null,
36
+ "decoder_start_token_id": null,
37
+ "diversity_penalty": 0.0,
38
+ "do_sample": false,
39
+ "early_stopping": false,
40
+ "encoder_no_repeat_ngram_size": 0,
41
+ "eos_token_id": 2,
42
+ "exponential_decay_length_penalty": null,
43
+ "finetuning_task": null,
44
+ "forced_bos_token_id": null,
45
+ "forced_eos_token_id": null,
46
+ "hidden_act": "silu",
47
+ "hidden_size": 4096,
48
+ "id2label": {
49
+ "0": "LABEL_0",
50
+ "1": "LABEL_1"
51
+ },
52
+ "initializer_range": 0.02,
53
+ "intermediate_size": 14336,
54
+ "is_decoder": false,
55
+ "is_encoder_decoder": false,
56
+ "label2id": {
57
+ "LABEL_0": 0,
58
+ "LABEL_1": 1
59
+ },
60
+ "length_penalty": 1.0,
61
+ "max_length": 20,
62
+ "max_position_embeddings": 32768,
63
+ "min_length": 0,
64
+ "model_type": "internlm2",
65
+ "no_repeat_ngram_size": 0,
66
+ "num_attention_heads": 32,
67
+ "num_beam_groups": 1,
68
+ "num_beams": 1,
69
+ "num_hidden_layers": 32,
70
+ "num_key_value_heads": 8,
71
+ "num_return_sequences": 1,
72
+ "output_attentions": false,
73
+ "output_hidden_states": false,
74
+ "output_scores": false,
75
+ "pad_token_id": 2,
76
+ "prefix": null,
77
+ "pretraining_tp": 1,
78
+ "problem_type": null,
79
+ "pruned_heads": {},
80
+ "remove_invalid_values": false,
81
+ "repetition_penalty": 1.0,
82
+ "return_dict": true,
83
+ "return_dict_in_generate": false,
84
+ "rms_norm_eps": 1e-05,
85
+ "rope_scaling": {
86
+ "factor": 2.0,
87
+ "type": "dynamic"
88
+ },
89
+ "rope_theta": 1000000,
90
+ "sep_token_id": null,
91
+ "suppress_tokens": null,
92
+ "task_specific_params": null,
93
+ "temperature": 1.0,
94
+ "tf_legacy_loss": false,
95
+ "tie_encoder_decoder": false,
96
+ "tie_word_embeddings": false,
97
+ "tokenizer_class": null,
98
+ "top_k": 50,
99
+ "top_p": 1.0,
100
+ "torch_dtype": "bfloat16",
101
+ "torchscript": false,
102
+ "transformers_version": "4.47.1",
103
+ "typical_p": 1.0,
104
+ "use_bfloat16": true,
105
+ "use_cache": false,
106
+ "vocab_size": 92554
107
+ },
108
+ "max_dynamic_patch": 6,
109
+ "min_dynamic_patch": 1,
110
+ "model_type": "internvl_chat",
111
+ "pad2square": false,
112
+ "ps_version": "v2",
113
+ "select_layer": -1,
114
+ "template": "internvl2_5",
115
+ "tie_word_embeddings": false,
116
+ "torch_dtype": "bfloat16",
117
+ "transformers_version": null,
118
+ "use_backbone_lora": 0,
119
+ "use_llm_lora": 0,
120
+ "use_thumbnail": true,
121
+ "vision_config": {
122
+ "_attn_implementation_autoset": true,
123
+ "_name_or_path": "",
124
+ "add_cross_attention": false,
125
+ "architectures": [
126
+ "InternVisionModel"
127
+ ],
128
+ "attention_dropout": 0.0,
129
+ "bad_words_ids": null,
130
+ "begin_suppress_tokens": null,
131
+ "bos_token_id": null,
132
+ "chunk_size_feed_forward": 0,
133
+ "cross_attention_hidden_size": null,
134
+ "decoder_start_token_id": null,
135
+ "diversity_penalty": 0.0,
136
+ "do_sample": false,
137
+ "drop_path_rate": 0.4,
138
+ "dropout": 0.0,
139
+ "early_stopping": false,
140
+ "encoder_no_repeat_ngram_size": 0,
141
+ "eos_token_id": null,
142
+ "exponential_decay_length_penalty": null,
143
+ "finetuning_task": null,
144
+ "forced_bos_token_id": null,
145
+ "forced_eos_token_id": null,
146
+ "hidden_act": "gelu",
147
+ "hidden_size": 1024,
148
+ "id2label": {
149
+ "0": "LABEL_0",
150
+ "1": "LABEL_1"
151
+ },
152
+ "image_size": 448,
153
+ "initializer_factor": 1.0,
154
+ "initializer_range": 0.02,
155
+ "intermediate_size": 4096,
156
+ "is_decoder": false,
157
+ "is_encoder_decoder": false,
158
+ "label2id": {
159
+ "LABEL_0": 0,
160
+ "LABEL_1": 1
161
+ },
162
+ "layer_norm_eps": 1e-06,
163
+ "length_penalty": 1.0,
164
+ "max_length": 20,
165
+ "min_length": 0,
166
+ "model_type": "intern_vit_6b",
167
+ "no_repeat_ngram_size": 0,
168
+ "norm_type": "layer_norm",
169
+ "num_attention_heads": 16,
170
+ "num_beam_groups": 1,
171
+ "num_beams": 1,
172
+ "num_channels": 3,
173
+ "num_hidden_layers": 24,
174
+ "num_return_sequences": 1,
175
+ "output_attentions": false,
176
+ "output_hidden_states": false,
177
+ "output_scores": false,
178
+ "pad_token_id": null,
179
+ "patch_size": 14,
180
+ "prefix": null,
181
+ "problem_type": null,
182
+ "pruned_heads": {},
183
+ "qk_normalization": false,
184
+ "qkv_bias": true,
185
+ "remove_invalid_values": false,
186
+ "repetition_penalty": 1.0,
187
+ "return_dict": true,
188
+ "return_dict_in_generate": false,
189
+ "sep_token_id": null,
190
+ "suppress_tokens": null,
191
+ "task_specific_params": null,
192
+ "temperature": 1.0,
193
+ "tf_legacy_loss": false,
194
+ "tie_encoder_decoder": false,
195
+ "tie_word_embeddings": true,
196
+ "tokenizer_class": null,
197
+ "top_k": 50,
198
+ "top_p": 1.0,
199
+ "torch_dtype": "bfloat16",
200
+ "torchscript": false,
201
+ "transformers_version": "4.47.1",
202
+ "typical_p": 1.0,
203
+ "use_bfloat16": true,
204
+ "use_flash_attn": true
205
+ }
206
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": [
4
+ 92542,
5
+ 92543
6
+ ],
7
+ "transformers_version": "4.47.1"
8
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db3bc73eb670edd68fe669ce49f64bcde138c275540ed1fea8325f960c3a59cc
3
+ size 4939952528
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cb9a4fe1267e05aec0b770e2689fd1ce1270c69aa85def316177df6cc2b5bc6
3
+ size 4915914584
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d503967663140a73ac225e5c5c75290122f671972a60335c9d1b7cb4644e2b17
3
+ size 4915914592
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08ed2e31ef564ba8a5cebdd0456206d9951dadb62c1d1ad7e376dbcabd5b7de2
3
+ size 1379035112
model.safetensors.index.json ADDED
@@ -0,0 +1,580 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16150747136
4
+ },
5
+ "weight_map": {
6
+ "language_model.model.layers.0.attention.wo.weight": "model-00001-of-00004.safetensors",
7
+ "language_model.model.layers.0.attention.wqkv.weight": "model-00001-of-00004.safetensors",
8
+ "language_model.model.layers.0.attention_norm.weight": "model-00001-of-00004.safetensors",
9
+ "language_model.model.layers.0.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
10
+ "language_model.model.layers.0.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
11
+ "language_model.model.layers.0.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
12
+ "language_model.model.layers.0.ffn_norm.weight": "model-00001-of-00004.safetensors",
13
+ "language_model.model.layers.1.attention.wo.weight": "model-00001-of-00004.safetensors",
14
+ "language_model.model.layers.1.attention.wqkv.weight": "model-00001-of-00004.safetensors",
15
+ "language_model.model.layers.1.attention_norm.weight": "model-00001-of-00004.safetensors",
16
+ "language_model.model.layers.1.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
17
+ "language_model.model.layers.1.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
18
+ "language_model.model.layers.1.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
19
+ "language_model.model.layers.1.ffn_norm.weight": "model-00001-of-00004.safetensors",
20
+ "language_model.model.layers.10.attention.wo.weight": "model-00002-of-00004.safetensors",
21
+ "language_model.model.layers.10.attention.wqkv.weight": "model-00002-of-00004.safetensors",
22
+ "language_model.model.layers.10.attention_norm.weight": "model-00002-of-00004.safetensors",
23
+ "language_model.model.layers.10.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
24
+ "language_model.model.layers.10.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
25
+ "language_model.model.layers.10.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
26
+ "language_model.model.layers.10.ffn_norm.weight": "model-00002-of-00004.safetensors",
27
+ "language_model.model.layers.11.attention.wo.weight": "model-00002-of-00004.safetensors",
28
+ "language_model.model.layers.11.attention.wqkv.weight": "model-00002-of-00004.safetensors",
29
+ "language_model.model.layers.11.attention_norm.weight": "model-00002-of-00004.safetensors",
30
+ "language_model.model.layers.11.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
31
+ "language_model.model.layers.11.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
32
+ "language_model.model.layers.11.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
33
+ "language_model.model.layers.11.ffn_norm.weight": "model-00002-of-00004.safetensors",
34
+ "language_model.model.layers.12.attention.wo.weight": "model-00002-of-00004.safetensors",
35
+ "language_model.model.layers.12.attention.wqkv.weight": "model-00002-of-00004.safetensors",
36
+ "language_model.model.layers.12.attention_norm.weight": "model-00002-of-00004.safetensors",
37
+ "language_model.model.layers.12.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
38
+ "language_model.model.layers.12.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
39
+ "language_model.model.layers.12.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
40
+ "language_model.model.layers.12.ffn_norm.weight": "model-00002-of-00004.safetensors",
41
+ "language_model.model.layers.13.attention.wo.weight": "model-00002-of-00004.safetensors",
42
+ "language_model.model.layers.13.attention.wqkv.weight": "model-00002-of-00004.safetensors",
43
+ "language_model.model.layers.13.attention_norm.weight": "model-00002-of-00004.safetensors",
44
+ "language_model.model.layers.13.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
45
+ "language_model.model.layers.13.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
46
+ "language_model.model.layers.13.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
47
+ "language_model.model.layers.13.ffn_norm.weight": "model-00002-of-00004.safetensors",
48
+ "language_model.model.layers.14.attention.wo.weight": "model-00002-of-00004.safetensors",
49
+ "language_model.model.layers.14.attention.wqkv.weight": "model-00002-of-00004.safetensors",
50
+ "language_model.model.layers.14.attention_norm.weight": "model-00002-of-00004.safetensors",
51
+ "language_model.model.layers.14.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
52
+ "language_model.model.layers.14.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
53
+ "language_model.model.layers.14.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
54
+ "language_model.model.layers.14.ffn_norm.weight": "model-00002-of-00004.safetensors",
55
+ "language_model.model.layers.15.attention.wo.weight": "model-00002-of-00004.safetensors",
56
+ "language_model.model.layers.15.attention.wqkv.weight": "model-00002-of-00004.safetensors",
57
+ "language_model.model.layers.15.attention_norm.weight": "model-00002-of-00004.safetensors",
58
+ "language_model.model.layers.15.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
59
+ "language_model.model.layers.15.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
60
+ "language_model.model.layers.15.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
61
+ "language_model.model.layers.15.ffn_norm.weight": "model-00002-of-00004.safetensors",
62
+ "language_model.model.layers.16.attention.wo.weight": "model-00002-of-00004.safetensors",
63
+ "language_model.model.layers.16.attention.wqkv.weight": "model-00002-of-00004.safetensors",
64
+ "language_model.model.layers.16.attention_norm.weight": "model-00002-of-00004.safetensors",
65
+ "language_model.model.layers.16.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
66
+ "language_model.model.layers.16.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
67
+ "language_model.model.layers.16.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
68
+ "language_model.model.layers.16.ffn_norm.weight": "model-00002-of-00004.safetensors",
69
+ "language_model.model.layers.17.attention.wo.weight": "model-00002-of-00004.safetensors",
70
+ "language_model.model.layers.17.attention.wqkv.weight": "model-00002-of-00004.safetensors",
71
+ "language_model.model.layers.17.attention_norm.weight": "model-00002-of-00004.safetensors",
72
+ "language_model.model.layers.17.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
73
+ "language_model.model.layers.17.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
74
+ "language_model.model.layers.17.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
75
+ "language_model.model.layers.17.ffn_norm.weight": "model-00002-of-00004.safetensors",
76
+ "language_model.model.layers.18.attention.wo.weight": "model-00002-of-00004.safetensors",
77
+ "language_model.model.layers.18.attention.wqkv.weight": "model-00002-of-00004.safetensors",
78
+ "language_model.model.layers.18.attention_norm.weight": "model-00002-of-00004.safetensors",
79
+ "language_model.model.layers.18.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
80
+ "language_model.model.layers.18.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
81
+ "language_model.model.layers.18.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
82
+ "language_model.model.layers.18.ffn_norm.weight": "model-00002-of-00004.safetensors",
83
+ "language_model.model.layers.19.attention.wo.weight": "model-00002-of-00004.safetensors",
84
+ "language_model.model.layers.19.attention.wqkv.weight": "model-00002-of-00004.safetensors",
85
+ "language_model.model.layers.19.attention_norm.weight": "model-00003-of-00004.safetensors",
86
+ "language_model.model.layers.19.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
87
+ "language_model.model.layers.19.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
88
+ "language_model.model.layers.19.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
89
+ "language_model.model.layers.19.ffn_norm.weight": "model-00003-of-00004.safetensors",
90
+ "language_model.model.layers.2.attention.wo.weight": "model-00001-of-00004.safetensors",
91
+ "language_model.model.layers.2.attention.wqkv.weight": "model-00001-of-00004.safetensors",
92
+ "language_model.model.layers.2.attention_norm.weight": "model-00001-of-00004.safetensors",
93
+ "language_model.model.layers.2.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
94
+ "language_model.model.layers.2.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
95
+ "language_model.model.layers.2.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
96
+ "language_model.model.layers.2.ffn_norm.weight": "model-00001-of-00004.safetensors",
97
+ "language_model.model.layers.20.attention.wo.weight": "model-00003-of-00004.safetensors",
98
+ "language_model.model.layers.20.attention.wqkv.weight": "model-00003-of-00004.safetensors",
99
+ "language_model.model.layers.20.attention_norm.weight": "model-00003-of-00004.safetensors",
100
+ "language_model.model.layers.20.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
101
+ "language_model.model.layers.20.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
102
+ "language_model.model.layers.20.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
103
+ "language_model.model.layers.20.ffn_norm.weight": "model-00003-of-00004.safetensors",
104
+ "language_model.model.layers.21.attention.wo.weight": "model-00003-of-00004.safetensors",
105
+ "language_model.model.layers.21.attention.wqkv.weight": "model-00003-of-00004.safetensors",
106
+ "language_model.model.layers.21.attention_norm.weight": "model-00003-of-00004.safetensors",
107
+ "language_model.model.layers.21.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
108
+ "language_model.model.layers.21.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
109
+ "language_model.model.layers.21.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
110
+ "language_model.model.layers.21.ffn_norm.weight": "model-00003-of-00004.safetensors",
111
+ "language_model.model.layers.22.attention.wo.weight": "model-00003-of-00004.safetensors",
112
+ "language_model.model.layers.22.attention.wqkv.weight": "model-00003-of-00004.safetensors",
113
+ "language_model.model.layers.22.attention_norm.weight": "model-00003-of-00004.safetensors",
114
+ "language_model.model.layers.22.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
115
+ "language_model.model.layers.22.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
116
+ "language_model.model.layers.22.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
117
+ "language_model.model.layers.22.ffn_norm.weight": "model-00003-of-00004.safetensors",
118
+ "language_model.model.layers.23.attention.wo.weight": "model-00003-of-00004.safetensors",
119
+ "language_model.model.layers.23.attention.wqkv.weight": "model-00003-of-00004.safetensors",
120
+ "language_model.model.layers.23.attention_norm.weight": "model-00003-of-00004.safetensors",
121
+ "language_model.model.layers.23.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
122
+ "language_model.model.layers.23.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
123
+ "language_model.model.layers.23.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
124
+ "language_model.model.layers.23.ffn_norm.weight": "model-00003-of-00004.safetensors",
125
+ "language_model.model.layers.24.attention.wo.weight": "model-00003-of-00004.safetensors",
126
+ "language_model.model.layers.24.attention.wqkv.weight": "model-00003-of-00004.safetensors",
127
+ "language_model.model.layers.24.attention_norm.weight": "model-00003-of-00004.safetensors",
128
+ "language_model.model.layers.24.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
129
+ "language_model.model.layers.24.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
130
+ "language_model.model.layers.24.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
131
+ "language_model.model.layers.24.ffn_norm.weight": "model-00003-of-00004.safetensors",
132
+ "language_model.model.layers.25.attention.wo.weight": "model-00003-of-00004.safetensors",
133
+ "language_model.model.layers.25.attention.wqkv.weight": "model-00003-of-00004.safetensors",
134
+ "language_model.model.layers.25.attention_norm.weight": "model-00003-of-00004.safetensors",
135
+ "language_model.model.layers.25.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
136
+ "language_model.model.layers.25.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
137
+ "language_model.model.layers.25.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
138
+ "language_model.model.layers.25.ffn_norm.weight": "model-00003-of-00004.safetensors",
139
+ "language_model.model.layers.26.attention.wo.weight": "model-00003-of-00004.safetensors",
140
+ "language_model.model.layers.26.attention.wqkv.weight": "model-00003-of-00004.safetensors",
141
+ "language_model.model.layers.26.attention_norm.weight": "model-00003-of-00004.safetensors",
142
+ "language_model.model.layers.26.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
143
+ "language_model.model.layers.26.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
144
+ "language_model.model.layers.26.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
145
+ "language_model.model.layers.26.ffn_norm.weight": "model-00003-of-00004.safetensors",
146
+ "language_model.model.layers.27.attention.wo.weight": "model-00003-of-00004.safetensors",
147
+ "language_model.model.layers.27.attention.wqkv.weight": "model-00003-of-00004.safetensors",
148
+ "language_model.model.layers.27.attention_norm.weight": "model-00003-of-00004.safetensors",
149
+ "language_model.model.layers.27.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
150
+ "language_model.model.layers.27.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
151
+ "language_model.model.layers.27.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
152
+ "language_model.model.layers.27.ffn_norm.weight": "model-00003-of-00004.safetensors",
153
+ "language_model.model.layers.28.attention.wo.weight": "model-00003-of-00004.safetensors",
154
+ "language_model.model.layers.28.attention.wqkv.weight": "model-00003-of-00004.safetensors",
155
+ "language_model.model.layers.28.attention_norm.weight": "model-00003-of-00004.safetensors",
156
+ "language_model.model.layers.28.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
157
+ "language_model.model.layers.28.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
158
+ "language_model.model.layers.28.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
159
+ "language_model.model.layers.28.ffn_norm.weight": "model-00003-of-00004.safetensors",
160
+ "language_model.model.layers.29.attention.wo.weight": "model-00003-of-00004.safetensors",
161
+ "language_model.model.layers.29.attention.wqkv.weight": "model-00003-of-00004.safetensors",
162
+ "language_model.model.layers.29.attention_norm.weight": "model-00003-of-00004.safetensors",
163
+ "language_model.model.layers.29.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
164
+ "language_model.model.layers.29.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
165
+ "language_model.model.layers.29.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
166
+ "language_model.model.layers.29.ffn_norm.weight": "model-00003-of-00004.safetensors",
167
+ "language_model.model.layers.3.attention.wo.weight": "model-00001-of-00004.safetensors",
168
+ "language_model.model.layers.3.attention.wqkv.weight": "model-00001-of-00004.safetensors",
169
+ "language_model.model.layers.3.attention_norm.weight": "model-00001-of-00004.safetensors",
170
+ "language_model.model.layers.3.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
171
+ "language_model.model.layers.3.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
172
+ "language_model.model.layers.3.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
173
+ "language_model.model.layers.3.ffn_norm.weight": "model-00001-of-00004.safetensors",
174
+ "language_model.model.layers.30.attention.wo.weight": "model-00003-of-00004.safetensors",
175
+ "language_model.model.layers.30.attention.wqkv.weight": "model-00003-of-00004.safetensors",
176
+ "language_model.model.layers.30.attention_norm.weight": "model-00004-of-00004.safetensors",
177
+ "language_model.model.layers.30.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
178
+ "language_model.model.layers.30.feed_forward.w2.weight": "model-00004-of-00004.safetensors",
179
+ "language_model.model.layers.30.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
180
+ "language_model.model.layers.30.ffn_norm.weight": "model-00004-of-00004.safetensors",
181
+ "language_model.model.layers.31.attention.wo.weight": "model-00004-of-00004.safetensors",
182
+ "language_model.model.layers.31.attention.wqkv.weight": "model-00004-of-00004.safetensors",
183
+ "language_model.model.layers.31.attention_norm.weight": "model-00004-of-00004.safetensors",
184
+ "language_model.model.layers.31.feed_forward.w1.weight": "model-00004-of-00004.safetensors",
185
+ "language_model.model.layers.31.feed_forward.w2.weight": "model-00004-of-00004.safetensors",
186
+ "language_model.model.layers.31.feed_forward.w3.weight": "model-00004-of-00004.safetensors",
187
+ "language_model.model.layers.31.ffn_norm.weight": "model-00004-of-00004.safetensors",
188
+ "language_model.model.layers.4.attention.wo.weight": "model-00001-of-00004.safetensors",
189
+ "language_model.model.layers.4.attention.wqkv.weight": "model-00001-of-00004.safetensors",
190
+ "language_model.model.layers.4.attention_norm.weight": "model-00001-of-00004.safetensors",
191
+ "language_model.model.layers.4.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
192
+ "language_model.model.layers.4.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
193
+ "language_model.model.layers.4.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
194
+ "language_model.model.layers.4.ffn_norm.weight": "model-00001-of-00004.safetensors",
195
+ "language_model.model.layers.5.attention.wo.weight": "model-00001-of-00004.safetensors",
196
+ "language_model.model.layers.5.attention.wqkv.weight": "model-00001-of-00004.safetensors",
197
+ "language_model.model.layers.5.attention_norm.weight": "model-00001-of-00004.safetensors",
198
+ "language_model.model.layers.5.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
199
+ "language_model.model.layers.5.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
200
+ "language_model.model.layers.5.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
201
+ "language_model.model.layers.5.ffn_norm.weight": "model-00001-of-00004.safetensors",
202
+ "language_model.model.layers.6.attention.wo.weight": "model-00001-of-00004.safetensors",
203
+ "language_model.model.layers.6.attention.wqkv.weight": "model-00001-of-00004.safetensors",
204
+ "language_model.model.layers.6.attention_norm.weight": "model-00001-of-00004.safetensors",
205
+ "language_model.model.layers.6.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
206
+ "language_model.model.layers.6.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
207
+ "language_model.model.layers.6.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
208
+ "language_model.model.layers.6.ffn_norm.weight": "model-00001-of-00004.safetensors",
209
+ "language_model.model.layers.7.attention.wo.weight": "model-00001-of-00004.safetensors",
210
+ "language_model.model.layers.7.attention.wqkv.weight": "model-00001-of-00004.safetensors",
211
+ "language_model.model.layers.7.attention_norm.weight": "model-00001-of-00004.safetensors",
212
+ "language_model.model.layers.7.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
213
+ "language_model.model.layers.7.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
214
+ "language_model.model.layers.7.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
215
+ "language_model.model.layers.7.ffn_norm.weight": "model-00001-of-00004.safetensors",
216
+ "language_model.model.layers.8.attention.wo.weight": "model-00001-of-00004.safetensors",
217
+ "language_model.model.layers.8.attention.wqkv.weight": "model-00001-of-00004.safetensors",
218
+ "language_model.model.layers.8.attention_norm.weight": "model-00002-of-00004.safetensors",
219
+ "language_model.model.layers.8.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
220
+ "language_model.model.layers.8.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
221
+ "language_model.model.layers.8.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
222
+ "language_model.model.layers.8.ffn_norm.weight": "model-00002-of-00004.safetensors",
223
+ "language_model.model.layers.9.attention.wo.weight": "model-00002-of-00004.safetensors",
224
+ "language_model.model.layers.9.attention.wqkv.weight": "model-00002-of-00004.safetensors",
225
+ "language_model.model.layers.9.attention_norm.weight": "model-00002-of-00004.safetensors",
226
+ "language_model.model.layers.9.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
227
+ "language_model.model.layers.9.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
228
+ "language_model.model.layers.9.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
229
+ "language_model.model.layers.9.ffn_norm.weight": "model-00002-of-00004.safetensors",
230
+ "language_model.model.norm.weight": "model-00004-of-00004.safetensors",
231
+ "language_model.model.tok_embeddings.weight": "model-00001-of-00004.safetensors",
232
+ "language_model.output.weight": "model-00004-of-00004.safetensors",
233
+ "mlp1.0.bias": "model-00004-of-00004.safetensors",
234
+ "mlp1.0.weight": "model-00004-of-00004.safetensors",
235
+ "mlp1.1.bias": "model-00004-of-00004.safetensors",
236
+ "mlp1.1.weight": "model-00004-of-00004.safetensors",
237
+ "mlp1.3.bias": "model-00004-of-00004.safetensors",
238
+ "mlp1.3.weight": "model-00004-of-00004.safetensors",
239
+ "vision_model.embeddings.class_embedding": "model-00001-of-00004.safetensors",
240
+ "vision_model.embeddings.patch_embedding.bias": "model-00001-of-00004.safetensors",
241
+ "vision_model.embeddings.patch_embedding.weight": "model-00001-of-00004.safetensors",
242
+ "vision_model.embeddings.position_embedding": "model-00001-of-00004.safetensors",
243
+ "vision_model.encoder.layers.0.attn.proj.bias": "model-00001-of-00004.safetensors",
244
+ "vision_model.encoder.layers.0.attn.proj.weight": "model-00001-of-00004.safetensors",
245
+ "vision_model.encoder.layers.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
246
+ "vision_model.encoder.layers.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
247
+ "vision_model.encoder.layers.0.ls1": "model-00001-of-00004.safetensors",
248
+ "vision_model.encoder.layers.0.ls2": "model-00001-of-00004.safetensors",
249
+ "vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00004.safetensors",
250
+ "vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
251
+ "vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00004.safetensors",
252
+ "vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
253
+ "vision_model.encoder.layers.0.norm1.bias": "model-00001-of-00004.safetensors",
254
+ "vision_model.encoder.layers.0.norm1.weight": "model-00001-of-00004.safetensors",
255
+ "vision_model.encoder.layers.0.norm2.bias": "model-00001-of-00004.safetensors",
256
+ "vision_model.encoder.layers.0.norm2.weight": "model-00001-of-00004.safetensors",
257
+ "vision_model.encoder.layers.1.attn.proj.bias": "model-00001-of-00004.safetensors",
258
+ "vision_model.encoder.layers.1.attn.proj.weight": "model-00001-of-00004.safetensors",
259
+ "vision_model.encoder.layers.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
260
+ "vision_model.encoder.layers.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
261
+ "vision_model.encoder.layers.1.ls1": "model-00001-of-00004.safetensors",
262
+ "vision_model.encoder.layers.1.ls2": "model-00001-of-00004.safetensors",
263
+ "vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00004.safetensors",
264
+ "vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
265
+ "vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00004.safetensors",
266
+ "vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
267
+ "vision_model.encoder.layers.1.norm1.bias": "model-00001-of-00004.safetensors",
268
+ "vision_model.encoder.layers.1.norm1.weight": "model-00001-of-00004.safetensors",
269
+ "vision_model.encoder.layers.1.norm2.bias": "model-00001-of-00004.safetensors",
270
+ "vision_model.encoder.layers.1.norm2.weight": "model-00001-of-00004.safetensors",
271
+ "vision_model.encoder.layers.10.attn.proj.bias": "model-00001-of-00004.safetensors",
272
+ "vision_model.encoder.layers.10.attn.proj.weight": "model-00001-of-00004.safetensors",
273
+ "vision_model.encoder.layers.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
274
+ "vision_model.encoder.layers.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
275
+ "vision_model.encoder.layers.10.ls1": "model-00001-of-00004.safetensors",
276
+ "vision_model.encoder.layers.10.ls2": "model-00001-of-00004.safetensors",
277
+ "vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00004.safetensors",
278
+ "vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00004.safetensors",
279
+ "vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00004.safetensors",
280
+ "vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00004.safetensors",
281
+ "vision_model.encoder.layers.10.norm1.bias": "model-00001-of-00004.safetensors",
282
+ "vision_model.encoder.layers.10.norm1.weight": "model-00001-of-00004.safetensors",
283
+ "vision_model.encoder.layers.10.norm2.bias": "model-00001-of-00004.safetensors",
284
+ "vision_model.encoder.layers.10.norm2.weight": "model-00001-of-00004.safetensors",
285
+ "vision_model.encoder.layers.11.attn.proj.bias": "model-00001-of-00004.safetensors",
286
+ "vision_model.encoder.layers.11.attn.proj.weight": "model-00001-of-00004.safetensors",
287
+ "vision_model.encoder.layers.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
288
+ "vision_model.encoder.layers.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
289
+ "vision_model.encoder.layers.11.ls1": "model-00001-of-00004.safetensors",
290
+ "vision_model.encoder.layers.11.ls2": "model-00001-of-00004.safetensors",
291
+ "vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00004.safetensors",
292
+ "vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00004.safetensors",
293
+ "vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00004.safetensors",
294
+ "vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00004.safetensors",
295
+ "vision_model.encoder.layers.11.norm1.bias": "model-00001-of-00004.safetensors",
296
+ "vision_model.encoder.layers.11.norm1.weight": "model-00001-of-00004.safetensors",
297
+ "vision_model.encoder.layers.11.norm2.bias": "model-00001-of-00004.safetensors",
298
+ "vision_model.encoder.layers.11.norm2.weight": "model-00001-of-00004.safetensors",
299
+ "vision_model.encoder.layers.12.attn.proj.bias": "model-00001-of-00004.safetensors",
300
+ "vision_model.encoder.layers.12.attn.proj.weight": "model-00001-of-00004.safetensors",
301
+ "vision_model.encoder.layers.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
302
+ "vision_model.encoder.layers.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
303
+ "vision_model.encoder.layers.12.ls1": "model-00001-of-00004.safetensors",
304
+ "vision_model.encoder.layers.12.ls2": "model-00001-of-00004.safetensors",
305
+ "vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00004.safetensors",
306
+ "vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00004.safetensors",
307
+ "vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00004.safetensors",
308
+ "vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00004.safetensors",
309
+ "vision_model.encoder.layers.12.norm1.bias": "model-00001-of-00004.safetensors",
310
+ "vision_model.encoder.layers.12.norm1.weight": "model-00001-of-00004.safetensors",
311
+ "vision_model.encoder.layers.12.norm2.bias": "model-00001-of-00004.safetensors",
312
+ "vision_model.encoder.layers.12.norm2.weight": "model-00001-of-00004.safetensors",
313
+ "vision_model.encoder.layers.13.attn.proj.bias": "model-00001-of-00004.safetensors",
314
+ "vision_model.encoder.layers.13.attn.proj.weight": "model-00001-of-00004.safetensors",
315
+ "vision_model.encoder.layers.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
316
+ "vision_model.encoder.layers.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
317
+ "vision_model.encoder.layers.13.ls1": "model-00001-of-00004.safetensors",
318
+ "vision_model.encoder.layers.13.ls2": "model-00001-of-00004.safetensors",
319
+ "vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00004.safetensors",
320
+ "vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00004.safetensors",
321
+ "vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00004.safetensors",
322
+ "vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00004.safetensors",
323
+ "vision_model.encoder.layers.13.norm1.bias": "model-00001-of-00004.safetensors",
324
+ "vision_model.encoder.layers.13.norm1.weight": "model-00001-of-00004.safetensors",
325
+ "vision_model.encoder.layers.13.norm2.bias": "model-00001-of-00004.safetensors",
326
+ "vision_model.encoder.layers.13.norm2.weight": "model-00001-of-00004.safetensors",
327
+ "vision_model.encoder.layers.14.attn.proj.bias": "model-00001-of-00004.safetensors",
328
+ "vision_model.encoder.layers.14.attn.proj.weight": "model-00001-of-00004.safetensors",
329
+ "vision_model.encoder.layers.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
330
+ "vision_model.encoder.layers.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
331
+ "vision_model.encoder.layers.14.ls1": "model-00001-of-00004.safetensors",
332
+ "vision_model.encoder.layers.14.ls2": "model-00001-of-00004.safetensors",
333
+ "vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00004.safetensors",
334
+ "vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00004.safetensors",
335
+ "vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00004.safetensors",
336
+ "vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00004.safetensors",
337
+ "vision_model.encoder.layers.14.norm1.bias": "model-00001-of-00004.safetensors",
338
+ "vision_model.encoder.layers.14.norm1.weight": "model-00001-of-00004.safetensors",
339
+ "vision_model.encoder.layers.14.norm2.bias": "model-00001-of-00004.safetensors",
340
+ "vision_model.encoder.layers.14.norm2.weight": "model-00001-of-00004.safetensors",
341
+ "vision_model.encoder.layers.15.attn.proj.bias": "model-00001-of-00004.safetensors",
342
+ "vision_model.encoder.layers.15.attn.proj.weight": "model-00001-of-00004.safetensors",
343
+ "vision_model.encoder.layers.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
344
+ "vision_model.encoder.layers.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
345
+ "vision_model.encoder.layers.15.ls1": "model-00001-of-00004.safetensors",
346
+ "vision_model.encoder.layers.15.ls2": "model-00001-of-00004.safetensors",
347
+ "vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00004.safetensors",
348
+ "vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00004.safetensors",
349
+ "vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00004.safetensors",
350
+ "vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00004.safetensors",
351
+ "vision_model.encoder.layers.15.norm1.bias": "model-00001-of-00004.safetensors",
352
+ "vision_model.encoder.layers.15.norm1.weight": "model-00001-of-00004.safetensors",
353
+ "vision_model.encoder.layers.15.norm2.bias": "model-00001-of-00004.safetensors",
354
+ "vision_model.encoder.layers.15.norm2.weight": "model-00001-of-00004.safetensors",
355
+ "vision_model.encoder.layers.16.attn.proj.bias": "model-00001-of-00004.safetensors",
356
+ "vision_model.encoder.layers.16.attn.proj.weight": "model-00001-of-00004.safetensors",
357
+ "vision_model.encoder.layers.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
358
+ "vision_model.encoder.layers.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
359
+ "vision_model.encoder.layers.16.ls1": "model-00001-of-00004.safetensors",
360
+ "vision_model.encoder.layers.16.ls2": "model-00001-of-00004.safetensors",
361
+ "vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00004.safetensors",
362
+ "vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00004.safetensors",
363
+ "vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00004.safetensors",
364
+ "vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00004.safetensors",
365
+ "vision_model.encoder.layers.16.norm1.bias": "model-00001-of-00004.safetensors",
366
+ "vision_model.encoder.layers.16.norm1.weight": "model-00001-of-00004.safetensors",
367
+ "vision_model.encoder.layers.16.norm2.bias": "model-00001-of-00004.safetensors",
368
+ "vision_model.encoder.layers.16.norm2.weight": "model-00001-of-00004.safetensors",
369
+ "vision_model.encoder.layers.17.attn.proj.bias": "model-00001-of-00004.safetensors",
370
+ "vision_model.encoder.layers.17.attn.proj.weight": "model-00001-of-00004.safetensors",
371
+ "vision_model.encoder.layers.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
372
+ "vision_model.encoder.layers.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
373
+ "vision_model.encoder.layers.17.ls1": "model-00001-of-00004.safetensors",
374
+ "vision_model.encoder.layers.17.ls2": "model-00001-of-00004.safetensors",
375
+ "vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00004.safetensors",
376
+ "vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00004.safetensors",
377
+ "vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00004.safetensors",
378
+ "vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00004.safetensors",
379
+ "vision_model.encoder.layers.17.norm1.bias": "model-00001-of-00004.safetensors",
380
+ "vision_model.encoder.layers.17.norm1.weight": "model-00001-of-00004.safetensors",
381
+ "vision_model.encoder.layers.17.norm2.bias": "model-00001-of-00004.safetensors",
382
+ "vision_model.encoder.layers.17.norm2.weight": "model-00001-of-00004.safetensors",
383
+ "vision_model.encoder.layers.18.attn.proj.bias": "model-00001-of-00004.safetensors",
384
+ "vision_model.encoder.layers.18.attn.proj.weight": "model-00001-of-00004.safetensors",
385
+ "vision_model.encoder.layers.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
386
+ "vision_model.encoder.layers.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
387
+ "vision_model.encoder.layers.18.ls1": "model-00001-of-00004.safetensors",
388
+ "vision_model.encoder.layers.18.ls2": "model-00001-of-00004.safetensors",
389
+ "vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00004.safetensors",
390
+ "vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00004.safetensors",
391
+ "vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00004.safetensors",
392
+ "vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00004.safetensors",
393
+ "vision_model.encoder.layers.18.norm1.bias": "model-00001-of-00004.safetensors",
394
+ "vision_model.encoder.layers.18.norm1.weight": "model-00001-of-00004.safetensors",
395
+ "vision_model.encoder.layers.18.norm2.bias": "model-00001-of-00004.safetensors",
396
+ "vision_model.encoder.layers.18.norm2.weight": "model-00001-of-00004.safetensors",
397
+ "vision_model.encoder.layers.19.attn.proj.bias": "model-00001-of-00004.safetensors",
398
+ "vision_model.encoder.layers.19.attn.proj.weight": "model-00001-of-00004.safetensors",
399
+ "vision_model.encoder.layers.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
400
+ "vision_model.encoder.layers.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
401
+ "vision_model.encoder.layers.19.ls1": "model-00001-of-00004.safetensors",
402
+ "vision_model.encoder.layers.19.ls2": "model-00001-of-00004.safetensors",
403
+ "vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00004.safetensors",
404
+ "vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00004.safetensors",
405
+ "vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00004.safetensors",
406
+ "vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00004.safetensors",
407
+ "vision_model.encoder.layers.19.norm1.bias": "model-00001-of-00004.safetensors",
408
+ "vision_model.encoder.layers.19.norm1.weight": "model-00001-of-00004.safetensors",
409
+ "vision_model.encoder.layers.19.norm2.bias": "model-00001-of-00004.safetensors",
410
+ "vision_model.encoder.layers.19.norm2.weight": "model-00001-of-00004.safetensors",
411
+ "vision_model.encoder.layers.2.attn.proj.bias": "model-00001-of-00004.safetensors",
412
+ "vision_model.encoder.layers.2.attn.proj.weight": "model-00001-of-00004.safetensors",
413
+ "vision_model.encoder.layers.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
414
+ "vision_model.encoder.layers.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
415
+ "vision_model.encoder.layers.2.ls1": "model-00001-of-00004.safetensors",
416
+ "vision_model.encoder.layers.2.ls2": "model-00001-of-00004.safetensors",
417
+ "vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00004.safetensors",
418
+ "vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
419
+ "vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00004.safetensors",
420
+ "vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
421
+ "vision_model.encoder.layers.2.norm1.bias": "model-00001-of-00004.safetensors",
422
+ "vision_model.encoder.layers.2.norm1.weight": "model-00001-of-00004.safetensors",
423
+ "vision_model.encoder.layers.2.norm2.bias": "model-00001-of-00004.safetensors",
424
+ "vision_model.encoder.layers.2.norm2.weight": "model-00001-of-00004.safetensors",
425
+ "vision_model.encoder.layers.20.attn.proj.bias": "model-00001-of-00004.safetensors",
426
+ "vision_model.encoder.layers.20.attn.proj.weight": "model-00001-of-00004.safetensors",
427
+ "vision_model.encoder.layers.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
428
+ "vision_model.encoder.layers.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
429
+ "vision_model.encoder.layers.20.ls1": "model-00001-of-00004.safetensors",
430
+ "vision_model.encoder.layers.20.ls2": "model-00001-of-00004.safetensors",
431
+ "vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00004.safetensors",
432
+ "vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00004.safetensors",
433
+ "vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00004.safetensors",
434
+ "vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00004.safetensors",
435
+ "vision_model.encoder.layers.20.norm1.bias": "model-00001-of-00004.safetensors",
436
+ "vision_model.encoder.layers.20.norm1.weight": "model-00001-of-00004.safetensors",
437
+ "vision_model.encoder.layers.20.norm2.bias": "model-00001-of-00004.safetensors",
438
+ "vision_model.encoder.layers.20.norm2.weight": "model-00001-of-00004.safetensors",
439
+ "vision_model.encoder.layers.21.attn.proj.bias": "model-00001-of-00004.safetensors",
440
+ "vision_model.encoder.layers.21.attn.proj.weight": "model-00001-of-00004.safetensors",
441
+ "vision_model.encoder.layers.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
442
+ "vision_model.encoder.layers.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
443
+ "vision_model.encoder.layers.21.ls1": "model-00001-of-00004.safetensors",
444
+ "vision_model.encoder.layers.21.ls2": "model-00001-of-00004.safetensors",
445
+ "vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00004.safetensors",
446
+ "vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00004.safetensors",
447
+ "vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00004.safetensors",
448
+ "vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00004.safetensors",
449
+ "vision_model.encoder.layers.21.norm1.bias": "model-00001-of-00004.safetensors",
450
+ "vision_model.encoder.layers.21.norm1.weight": "model-00001-of-00004.safetensors",
451
+ "vision_model.encoder.layers.21.norm2.bias": "model-00001-of-00004.safetensors",
452
+ "vision_model.encoder.layers.21.norm2.weight": "model-00001-of-00004.safetensors",
453
+ "vision_model.encoder.layers.22.attn.proj.bias": "model-00001-of-00004.safetensors",
454
+ "vision_model.encoder.layers.22.attn.proj.weight": "model-00001-of-00004.safetensors",
455
+ "vision_model.encoder.layers.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
456
+ "vision_model.encoder.layers.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
457
+ "vision_model.encoder.layers.22.ls1": "model-00001-of-00004.safetensors",
458
+ "vision_model.encoder.layers.22.ls2": "model-00001-of-00004.safetensors",
459
+ "vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00004.safetensors",
460
+ "vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00004.safetensors",
461
+ "vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00004.safetensors",
462
+ "vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00004.safetensors",
463
+ "vision_model.encoder.layers.22.norm1.bias": "model-00001-of-00004.safetensors",
464
+ "vision_model.encoder.layers.22.norm1.weight": "model-00001-of-00004.safetensors",
465
+ "vision_model.encoder.layers.22.norm2.bias": "model-00001-of-00004.safetensors",
466
+ "vision_model.encoder.layers.22.norm2.weight": "model-00001-of-00004.safetensors",
467
+ "vision_model.encoder.layers.23.attn.proj.bias": "model-00001-of-00004.safetensors",
468
+ "vision_model.encoder.layers.23.attn.proj.weight": "model-00001-of-00004.safetensors",
469
+ "vision_model.encoder.layers.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
470
+ "vision_model.encoder.layers.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
471
+ "vision_model.encoder.layers.23.ls1": "model-00001-of-00004.safetensors",
472
+ "vision_model.encoder.layers.23.ls2": "model-00001-of-00004.safetensors",
473
+ "vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00004.safetensors",
474
+ "vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00004.safetensors",
475
+ "vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00004.safetensors",
476
+ "vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00004.safetensors",
477
+ "vision_model.encoder.layers.23.norm1.bias": "model-00001-of-00004.safetensors",
478
+ "vision_model.encoder.layers.23.norm1.weight": "model-00001-of-00004.safetensors",
479
+ "vision_model.encoder.layers.23.norm2.bias": "model-00001-of-00004.safetensors",
480
+ "vision_model.encoder.layers.23.norm2.weight": "model-00001-of-00004.safetensors",
481
+ "vision_model.encoder.layers.3.attn.proj.bias": "model-00001-of-00004.safetensors",
482
+ "vision_model.encoder.layers.3.attn.proj.weight": "model-00001-of-00004.safetensors",
483
+ "vision_model.encoder.layers.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
484
+ "vision_model.encoder.layers.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
485
+ "vision_model.encoder.layers.3.ls1": "model-00001-of-00004.safetensors",
486
+ "vision_model.encoder.layers.3.ls2": "model-00001-of-00004.safetensors",
487
+ "vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00004.safetensors",
488
+ "vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
489
+ "vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00004.safetensors",
490
+ "vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
491
+ "vision_model.encoder.layers.3.norm1.bias": "model-00001-of-00004.safetensors",
492
+ "vision_model.encoder.layers.3.norm1.weight": "model-00001-of-00004.safetensors",
493
+ "vision_model.encoder.layers.3.norm2.bias": "model-00001-of-00004.safetensors",
494
+ "vision_model.encoder.layers.3.norm2.weight": "model-00001-of-00004.safetensors",
495
+ "vision_model.encoder.layers.4.attn.proj.bias": "model-00001-of-00004.safetensors",
496
+ "vision_model.encoder.layers.4.attn.proj.weight": "model-00001-of-00004.safetensors",
497
+ "vision_model.encoder.layers.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
498
+ "vision_model.encoder.layers.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
499
+ "vision_model.encoder.layers.4.ls1": "model-00001-of-00004.safetensors",
500
+ "vision_model.encoder.layers.4.ls2": "model-00001-of-00004.safetensors",
501
+ "vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00004.safetensors",
502
+ "vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
503
+ "vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00004.safetensors",
504
+ "vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
505
+ "vision_model.encoder.layers.4.norm1.bias": "model-00001-of-00004.safetensors",
506
+ "vision_model.encoder.layers.4.norm1.weight": "model-00001-of-00004.safetensors",
507
+ "vision_model.encoder.layers.4.norm2.bias": "model-00001-of-00004.safetensors",
508
+ "vision_model.encoder.layers.4.norm2.weight": "model-00001-of-00004.safetensors",
509
+ "vision_model.encoder.layers.5.attn.proj.bias": "model-00001-of-00004.safetensors",
510
+ "vision_model.encoder.layers.5.attn.proj.weight": "model-00001-of-00004.safetensors",
511
+ "vision_model.encoder.layers.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
512
+ "vision_model.encoder.layers.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
513
+ "vision_model.encoder.layers.5.ls1": "model-00001-of-00004.safetensors",
514
+ "vision_model.encoder.layers.5.ls2": "model-00001-of-00004.safetensors",
515
+ "vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00004.safetensors",
516
+ "vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
517
+ "vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00004.safetensors",
518
+ "vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
519
+ "vision_model.encoder.layers.5.norm1.bias": "model-00001-of-00004.safetensors",
520
+ "vision_model.encoder.layers.5.norm1.weight": "model-00001-of-00004.safetensors",
521
+ "vision_model.encoder.layers.5.norm2.bias": "model-00001-of-00004.safetensors",
522
+ "vision_model.encoder.layers.5.norm2.weight": "model-00001-of-00004.safetensors",
523
+ "vision_model.encoder.layers.6.attn.proj.bias": "model-00001-of-00004.safetensors",
524
+ "vision_model.encoder.layers.6.attn.proj.weight": "model-00001-of-00004.safetensors",
525
+ "vision_model.encoder.layers.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
526
+ "vision_model.encoder.layers.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
527
+ "vision_model.encoder.layers.6.ls1": "model-00001-of-00004.safetensors",
528
+ "vision_model.encoder.layers.6.ls2": "model-00001-of-00004.safetensors",
529
+ "vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00004.safetensors",
530
+ "vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
531
+ "vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00004.safetensors",
532
+ "vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
533
+ "vision_model.encoder.layers.6.norm1.bias": "model-00001-of-00004.safetensors",
534
+ "vision_model.encoder.layers.6.norm1.weight": "model-00001-of-00004.safetensors",
535
+ "vision_model.encoder.layers.6.norm2.bias": "model-00001-of-00004.safetensors",
536
+ "vision_model.encoder.layers.6.norm2.weight": "model-00001-of-00004.safetensors",
537
+ "vision_model.encoder.layers.7.attn.proj.bias": "model-00001-of-00004.safetensors",
538
+ "vision_model.encoder.layers.7.attn.proj.weight": "model-00001-of-00004.safetensors",
539
+ "vision_model.encoder.layers.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
540
+ "vision_model.encoder.layers.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
541
+ "vision_model.encoder.layers.7.ls1": "model-00001-of-00004.safetensors",
542
+ "vision_model.encoder.layers.7.ls2": "model-00001-of-00004.safetensors",
543
+ "vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00004.safetensors",
544
+ "vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
545
+ "vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00004.safetensors",
546
+ "vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
547
+ "vision_model.encoder.layers.7.norm1.bias": "model-00001-of-00004.safetensors",
548
+ "vision_model.encoder.layers.7.norm1.weight": "model-00001-of-00004.safetensors",
549
+ "vision_model.encoder.layers.7.norm2.bias": "model-00001-of-00004.safetensors",
550
+ "vision_model.encoder.layers.7.norm2.weight": "model-00001-of-00004.safetensors",
551
+ "vision_model.encoder.layers.8.attn.proj.bias": "model-00001-of-00004.safetensors",
552
+ "vision_model.encoder.layers.8.attn.proj.weight": "model-00001-of-00004.safetensors",
553
+ "vision_model.encoder.layers.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
554
+ "vision_model.encoder.layers.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
555
+ "vision_model.encoder.layers.8.ls1": "model-00001-of-00004.safetensors",
556
+ "vision_model.encoder.layers.8.ls2": "model-00001-of-00004.safetensors",
557
+ "vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00004.safetensors",
558
+ "vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
559
+ "vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00004.safetensors",
560
+ "vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
561
+ "vision_model.encoder.layers.8.norm1.bias": "model-00001-of-00004.safetensors",
562
+ "vision_model.encoder.layers.8.norm1.weight": "model-00001-of-00004.safetensors",
563
+ "vision_model.encoder.layers.8.norm2.bias": "model-00001-of-00004.safetensors",
564
+ "vision_model.encoder.layers.8.norm2.weight": "model-00001-of-00004.safetensors",
565
+ "vision_model.encoder.layers.9.attn.proj.bias": "model-00001-of-00004.safetensors",
566
+ "vision_model.encoder.layers.9.attn.proj.weight": "model-00001-of-00004.safetensors",
567
+ "vision_model.encoder.layers.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
568
+ "vision_model.encoder.layers.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
569
+ "vision_model.encoder.layers.9.ls1": "model-00001-of-00004.safetensors",
570
+ "vision_model.encoder.layers.9.ls2": "model-00001-of-00004.safetensors",
571
+ "vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00004.safetensors",
572
+ "vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
573
+ "vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00004.safetensors",
574
+ "vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
575
+ "vision_model.encoder.layers.9.norm1.bias": "model-00001-of-00004.safetensors",
576
+ "vision_model.encoder.layers.9.norm1.weight": "model-00001-of-00004.safetensors",
577
+ "vision_model.encoder.layers.9.norm2.bias": "model-00001-of-00004.safetensors",
578
+ "vision_model.encoder.layers.9.norm2.weight": "model-00001-of-00004.safetensors"
579
+ }
580
+ }
runs/Apr06_03-40-24_brev-mnism5o8g/events.out.tfevents.1775446875.brev-mnism5o8g.2636796.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:435425532f99a47b9af5209e9351ad61fcf5148823e4a42f0d704f56514dd02f
3
+ size 28278
special_tokens_map.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|action_start|>",
6
+ "<|action_end|>",
7
+ "<|interpreter|>",
8
+ "<|plugin|>",
9
+ "<img>",
10
+ "</img>",
11
+ "<IMG_CONTEXT>",
12
+ "<quad>",
13
+ "</quad>",
14
+ "<ref>",
15
+ "</ref>",
16
+ "<box>",
17
+ "</box>",
18
+ {
19
+ "content": "<prm>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ }
25
+ ],
26
+ "bos_token": {
27
+ "content": "<s>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ },
33
+ "eos_token": {
34
+ "content": "</s>",
35
+ "lstrip": false,
36
+ "normalized": false,
37
+ "rstrip": false,
38
+ "single_word": false
39
+ },
40
+ "pad_token": {
41
+ "content": "</s>",
42
+ "lstrip": false,
43
+ "normalized": false,
44
+ "rstrip": false,
45
+ "single_word": false
46
+ },
47
+ "unk_token": {
48
+ "content": "<unk>",
49
+ "lstrip": false,
50
+ "normalized": false,
51
+ "rstrip": false,
52
+ "single_word": false
53
+ }
54
+ }
tokenization_internlm2.py ADDED
@@ -0,0 +1,235 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Copyright (c) The InternLM team and The HuggingFace Inc. team. All rights reserved.
2
+ #
3
+ # This code is based on transformers/src/transformers/models/llama/tokenization_llama.py
4
+ #
5
+ # Licensed under the Apache License, Version 2.0 (the "License");
6
+ # you may not use this file except in compliance with the License.
7
+ # You may obtain a copy of the License at
8
+ #
9
+ # http://www.apache.org/licenses/LICENSE-2.0
10
+ #
11
+ # Unless required by applicable law or agreed to in writing, software
12
+ # distributed under the License is distributed on an "AS IS" BASIS,
13
+ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14
+ # See the License for the specific language governing permissions and
15
+ # limitations under the License.
16
+
17
+ """Tokenization classes for InternLM."""
18
+ import os
19
+ from shutil import copyfile
20
+ from typing import Any, Dict, List, Optional, Tuple
21
+
22
+ import sentencepiece as spm
23
+ from transformers.tokenization_utils import PreTrainedTokenizer
24
+ from transformers.utils import logging
25
+
26
+ logger = logging.get_logger(__name__)
27
+
28
+ VOCAB_FILES_NAMES = {'vocab_file': './tokenizer.model'}
29
+
30
+ PRETRAINED_VOCAB_FILES_MAP = {}
31
+
32
+
33
+ # Modified from transformers.model.llama.tokenization_llama.LlamaTokenizer
34
+ class InternLM2Tokenizer(PreTrainedTokenizer):
35
+ """
36
+ Construct a InternLM2 tokenizer. Based on byte-level Byte-Pair-Encoding.
37
+
38
+ Args:
39
+ vocab_file (`str`):
40
+ Path to the vocabulary file.
41
+ """
42
+
43
+ vocab_files_names = VOCAB_FILES_NAMES
44
+ pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
45
+ model_input_names = ['input_ids', 'attention_mask']
46
+ _auto_class = 'AutoTokenizer'
47
+
48
+ def __init__(
49
+ self,
50
+ vocab_file,
51
+ unk_token='<unk>',
52
+ bos_token='<s>',
53
+ eos_token='</s>',
54
+ pad_token='</s>',
55
+ sp_model_kwargs: Optional[Dict[str, Any]] = None,
56
+ add_bos_token=True,
57
+ add_eos_token=False,
58
+ decode_with_prefix_space=False,
59
+ clean_up_tokenization_spaces=False,
60
+ **kwargs,
61
+ ):
62
+ self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs
63
+ self.vocab_file = vocab_file
64
+ self.add_bos_token = add_bos_token
65
+ self.add_eos_token = add_eos_token
66
+ self.decode_with_prefix_space = decode_with_prefix_space
67
+ self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
68
+ self.sp_model.Load(vocab_file)
69
+ self._no_prefix_space_tokens = None
70
+ super().__init__(
71
+ bos_token=bos_token,
72
+ eos_token=eos_token,
73
+ unk_token=unk_token,
74
+ pad_token=pad_token,
75
+ clean_up_tokenization_spaces=clean_up_tokenization_spaces,
76
+ **kwargs,
77
+ )
78
+
79
+ @property
80
+ def no_prefix_space_tokens(self):
81
+ if self._no_prefix_space_tokens is None:
82
+ vocab = self.convert_ids_to_tokens(list(range(self.vocab_size)))
83
+ self._no_prefix_space_tokens = {i for i, tok in enumerate(vocab) if not tok.startswith('▁')}
84
+ return self._no_prefix_space_tokens
85
+
86
+ @property
87
+ def vocab_size(self):
88
+ """Returns vocab size"""
89
+ return self.sp_model.get_piece_size()
90
+
91
+ @property
92
+ def bos_token_id(self) -> Optional[int]:
93
+ return self.sp_model.bos_id()
94
+
95
+ @property
96
+ def eos_token_id(self) -> Optional[int]:
97
+ return self.sp_model.eos_id()
98
+
99
+ def get_vocab(self):
100
+ """Returns vocab as a dict"""
101
+ vocab = {self.convert_ids_to_tokens(i): i for i in range(self.vocab_size)}
102
+ vocab.update(self.added_tokens_encoder)
103
+ return vocab
104
+
105
+ def _tokenize(self, text):
106
+ """Returns a tokenized string."""
107
+ return self.sp_model.encode(text, out_type=str)
108
+
109
+ def _convert_token_to_id(self, token):
110
+ """Converts a token (str) in an id using the vocab."""
111
+ return self.sp_model.piece_to_id(token)
112
+
113
+ def _convert_id_to_token(self, index):
114
+ """Converts an index (integer) in a token (str) using the vocab."""
115
+ token = self.sp_model.IdToPiece(index)
116
+ return token
117
+
118
+ def _maybe_add_prefix_space(self, tokens, decoded):
119
+ if tokens and tokens[0] not in self.no_prefix_space_tokens:
120
+ return ' ' + decoded
121
+ else:
122
+ return decoded
123
+
124
+ def convert_tokens_to_string(self, tokens):
125
+ """Converts a sequence of tokens (string) in a single string."""
126
+ current_sub_tokens = []
127
+ out_string = ''
128
+ prev_is_special = False
129
+ for token in tokens:
130
+ # make sure that special tokens are not decoded using sentencepiece model
131
+ if token in self.all_special_tokens:
132
+ if not prev_is_special:
133
+ out_string += ' '
134
+ out_string += self.sp_model.decode(current_sub_tokens) + token
135
+ prev_is_special = True
136
+ current_sub_tokens = []
137
+ else:
138
+ current_sub_tokens.append(token)
139
+ prev_is_special = False
140
+ out_string += self.sp_model.decode(current_sub_tokens)
141
+ out_string = self.clean_up_tokenization(out_string)
142
+ out_string = self._maybe_add_prefix_space(tokens=tokens, decoded=out_string)
143
+ return out_string[1:]
144
+
145
+ def save_vocabulary(self, save_directory, filename_prefix: Optional[str] = None) -> Tuple[str]:
146
+ """
147
+ Save the vocabulary and special tokens file to a directory.
148
+
149
+ Args:
150
+ save_directory (`str`):
151
+ The directory in which to save the vocabulary.
152
+
153
+ Returns:
154
+ `Tuple(str)`: Paths to the files saved.
155
+ """
156
+ if not os.path.isdir(save_directory):
157
+ logger.error(f'Vocabulary path ({save_directory}) should be a directory')
158
+ return
159
+ out_vocab_file = os.path.join(
160
+ save_directory, (filename_prefix + '-' if filename_prefix else '') + VOCAB_FILES_NAMES['vocab_file']
161
+ )
162
+
163
+ if os.path.abspath(self.vocab_file) != os.path.abspath(out_vocab_file) and os.path.isfile(self.vocab_file):
164
+ copyfile(self.vocab_file, out_vocab_file)
165
+ elif not os.path.isfile(self.vocab_file):
166
+ with open(out_vocab_file, 'wb') as fi:
167
+ content_spiece_model = self.sp_model.serialized_model_proto()
168
+ fi.write(content_spiece_model)
169
+
170
+ return (out_vocab_file,)
171
+
172
+ def build_inputs_with_special_tokens(self, token_ids_0, token_ids_1=None):
173
+ if self.add_bos_token:
174
+ bos_token_ids = [self.bos_token_id]
175
+ else:
176
+ bos_token_ids = []
177
+
178
+ output = bos_token_ids + token_ids_0
179
+
180
+ if token_ids_1 is not None:
181
+ output = output + token_ids_1
182
+
183
+ if self.add_eos_token:
184
+ output = output + [self.eos_token_id]
185
+
186
+ return output
187
+
188
+ def get_special_tokens_mask(
189
+ self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None, already_has_special_tokens: bool = False
190
+ ) -> List[int]:
191
+ """
192
+ Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding
193
+ special tokens using the tokenizer `prepare_for_model` method.
194
+
195
+ Args:
196
+ token_ids_0 (`List[int]`):
197
+ List of IDs.
198
+ token_ids_1 (`List[int]`, *optional*):
199
+ Optional second list of IDs for sequence pairs.
200
+ already_has_special_tokens (`bool`, *optional*, defaults to `False`):
201
+ Whether or not the token list is already formatted with special tokens for the model.
202
+
203
+ Returns:
204
+ `List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
205
+ """
206
+ if already_has_special_tokens:
207
+ return super().get_special_tokens_mask(
208
+ token_ids_0=token_ids_0, token_ids_1=token_ids_1, already_has_special_tokens=True
209
+ )
210
+
211
+ if token_ids_1 is None:
212
+ return [1] + ([0] * len(token_ids_0)) + [1]
213
+ return [1] + ([0] * len(token_ids_0)) + [1, 1] + ([0] * len(token_ids_1)) + [1]
214
+
215
+ def create_token_type_ids_from_sequences(
216
+ self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
217
+ ) -> List[int]:
218
+ """
219
+ Create a mask from the two sequences passed to be used in a sequence-pair classification task. T5 does not make
220
+ use of token type ids, therefore a list of zeros is returned.
221
+
222
+ Args:
223
+ token_ids_0 (`List[int]`):
224
+ List of IDs.
225
+ token_ids_1 (`List[int]`, *optional*):
226
+ Optional second list of IDs for sequence pairs.
227
+
228
+ Returns:
229
+ `List[int]`: List of zeros.
230
+ """
231
+ eos = [self.eos_token_id]
232
+
233
+ if token_ids_1 is None:
234
+ return len(token_ids_0 + eos) * [0]
235
+ return len(token_ids_0 + eos + token_ids_1 + eos) * [0]
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f868398fc4e05ee1e8aeba95ddf18ddcc45b8bce55d5093bead5bbf80429b48b
3
+ size 1477754
tokenizer_config.json ADDED
@@ -0,0 +1,189 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "92538": {
28
+ "content": "<|plugin|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "92539": {
36
+ "content": "<|interpreter|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "92540": {
44
+ "content": "<|action_end|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "92541": {
52
+ "content": "<|action_start|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "92542": {
60
+ "content": "<|im_end|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "92543": {
68
+ "content": "<|im_start|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "92544": {
76
+ "content": "<img>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "92545": {
84
+ "content": "</img>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "92546": {
92
+ "content": "<IMG_CONTEXT>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "92547": {
100
+ "content": "<quad>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "92548": {
108
+ "content": "</quad>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "92549": {
116
+ "content": "<ref>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "92550": {
124
+ "content": "</ref>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "92551": {
132
+ "content": "<box>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "92552": {
140
+ "content": "</box>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "92553": {
148
+ "content": "<prm>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ }
155
+ },
156
+ "additional_special_tokens": [
157
+ "<|im_start|>",
158
+ "<|im_end|>",
159
+ "<|action_start|>",
160
+ "<|action_end|>",
161
+ "<|interpreter|>",
162
+ "<|plugin|>",
163
+ "<img>",
164
+ "</img>",
165
+ "<IMG_CONTEXT>",
166
+ "<quad>",
167
+ "</quad>",
168
+ "<ref>",
169
+ "</ref>",
170
+ "<box>",
171
+ "</box>",
172
+ "<prm>"
173
+ ],
174
+ "auto_map": {
175
+ "AutoTokenizer": [
176
+ "tokenization_internlm2.InternLM2Tokenizer",
177
+ null
178
+ ]
179
+ },
180
+ "bos_token": "<s>",
181
+ "chat_template": "{{ bos_token }}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
182
+ "clean_up_tokenization_spaces": false,
183
+ "eos_token": "</s>",
184
+ "extra_special_tokens": {},
185
+ "model_max_length": 8192,
186
+ "pad_token": "</s>",
187
+ "tokenizer_class": "InternLM2Tokenizer",
188
+ "unk_token": "<unk>"
189
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9926144756277696,
3
+ "total_flos": 2.4692764709042835e+20,
4
+ "train_loss": 3.329987657921655,
5
+ "train_runtime": 7432.7063,
6
+ "train_samples": 43323,
7
+ "train_samples_per_second": 5.829,
8
+ "train_steps_per_second": 0.011
9
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b51f13a383cffb413ff7951e403fc4324c59ea047b57ad6b157ee6196c8552d3
3
+ size 7544
training_log.txt ADDED
The diff for this file is too large to render. See raw diff