Hugging Face's logo

Alibaba-DAMO-Academy
/
PixelRefer-7B

Video-Text-to-Text
Transformers
PyTorch
English
pixelrefer_qwen2
text-generation
multimodal large language model
large video-language model
Model card Files
xet
Community
2
CircleRadon commited on
Commit
1d53b65
·
verified ·
1 Parent(s): 016f0ef

Add files using upload-large-folder tool

Browse files
Files changed (14) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +28 -0
  3. config.json +52 -0
  4. generation_config.json +7 -0
  5. merges.txt +0 -0
  6. pytorch_model-00001-of-00004.bin +3 -0
  7. pytorch_model-00002-of-00004.bin +3 -0
  8. pytorch_model-00003-of-00004.bin +3 -0
  9. pytorch_model-00004-of-00004.bin +3 -0
  10. pytorch_model.bin.index.json +792 -0
  11. special_tokens_map.json +31 -0
  12. tokenizer.json +3 -0
  13. tokenizer_config.json +244 -0
  14. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<REGION>": 151668,
4
+ "<image>": 151665,
5
+ "<tool_call>": 151657,
6
+ "<|box_end|>": 151649,
7
+ "<|box_start|>": 151648,
8
+ "<|endoftext|>": 151643,
9
+ "<|file_sep|>": 151664,
10
+ "<|fim_middle|>": 151660,
11
+ "<|fim_pad|>": 151662,
12
+ "<|fim_prefix|>": 151659,
13
+ "<|fim_suffix|>": 151661,
14
+ "<|im_end|>": 151645,
15
+ "<|im_start|>": 151644,
16
+ "<|image_pad|>": 151655,
17
+ "<|object_ref_end|>": 151647,
18
+ "<|object_ref_start|>": 151646,
19
+ "<|quad_end|>": 151651,
20
+ "<|quad_start|>": 151650,
21
+ "<|repo_name|>": 151663,
22
+ "<|stream_end|>": 151667,
23
+ "<|stream_start|>": 151666,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "PixelRefer-2B",
3
+ "architectures": [
4
+ "PixelreferQwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 3584,
11
+ "image_aspect_ratio": "qwen2vl",
12
+ "image_size": 28,
13
+ "image_token_index": 151665,
14
+ "image_token_length": 1,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 18944,
17
+ "is_alignment": false,
18
+ "llm_lr": 1e-05,
19
+ "mask_num": 32,
20
+ "max_frames": 180,
21
+ "max_position_embeddings": 32768,
22
+ "max_window_layers": 28,
23
+ "mm_hidden_size": 1152,
24
+ "mm_max_length": 8192,
25
+ "mm_projector_lr": 1e-05,
26
+ "mm_projector_type": "mlp2x_gelu",
27
+ "mm_vision_encoder": "DAMO-NLP-SG/VL3-SigLIP-NaViT",
28
+ "mm_vision_select_feature": "patch",
29
+ "mm_vision_select_layer": -2,
30
+ "model_type": "pixelrefer_qwen2",
31
+ "num_attention_heads": 28,
32
+ "num_hidden_layers": 28,
33
+ "num_key_value_heads": 4,
34
+ "region_encoder_lr": 1e-05,
35
+ "region_token_index": 151668,
36
+ "rms_norm_eps": 1e-06,
37
+ "rope_scaling": null,
38
+ "rope_theta": 1000000.0,
39
+ "sliding_window": null,
40
+ "spatial_merge_size": 2,
41
+ "tie_word_embeddings": false,
42
+ "tokenizer_model_max_length": 16384,
43
+ "tokenizer_padding_side": "right",
44
+ "torch_dtype": "bfloat16",
45
+ "transformers_version": "4.46.3",
46
+ "use_cache": true,
47
+ "use_mm_proj": true,
48
+ "use_sliding_window": false,
49
+ "use_token_compression": true,
50
+ "vision_encoder_lr": 0.0,
51
+ "vocab_size": 151669
52
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151643,
4
+ "do_sample": true,
5
+ "eos_token_id": 151645,
6
+ "transformers_version": "4.46.3"
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model-00001-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62e9296061cecb8dce61877d563f96d3ac3129afc788d246d86f7fcf139fbbf7
3
+ size 4874852822
pytorch_model-00002-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f80c419b62c94e96f8480308f0a86ae8e8aabaaf2cf604a6941255792de82260
3
+ size 4932778600
pytorch_model-00003-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3959552a64593a2c90158fe40401752ea3e1485d1daec1e1377947c1615ba28
3
+ size 4992991356
pytorch_model-00004-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:041cf4f94a7a0513035795288a97ee2772e05aa587fe57a9d87d9a23ceb4a184
3
+ size 1317452732
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,792 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16117796064
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00004-of-00004.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00004.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
13
+ "model.layers.0.self_attn.k_proj.bias": "pytorch_model-00001-of-00004.bin",
14
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
15
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
16
+ "model.layers.0.self_attn.q_proj.bias": "pytorch_model-00001-of-00004.bin",
17
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
18
+ "model.layers.0.self_attn.v_proj.bias": "pytorch_model-00001-of-00004.bin",
19
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
20
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
21
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
22
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
23
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
24
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
25
+ "model.layers.1.self_attn.k_proj.bias": "pytorch_model-00001-of-00004.bin",
26
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
27
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
28
+ "model.layers.1.self_attn.q_proj.bias": "pytorch_model-00001-of-00004.bin",
29
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
30
+ "model.layers.1.self_attn.v_proj.bias": "pytorch_model-00001-of-00004.bin",
31
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
32
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
33
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
34
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
35
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
36
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
37
+ "model.layers.10.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
38
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
39
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
40
+ "model.layers.10.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
41
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
42
+ "model.layers.10.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
43
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
44
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
45
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
46
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
47
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
48
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
49
+ "model.layers.11.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
50
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
51
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
52
+ "model.layers.11.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
53
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
54
+ "model.layers.11.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
55
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
56
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
57
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
58
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
59
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
60
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
61
+ "model.layers.12.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
62
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
63
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
64
+ "model.layers.12.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
65
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
66
+ "model.layers.12.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
67
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
68
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
69
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
70
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
71
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
72
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
73
+ "model.layers.13.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
74
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
75
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
76
+ "model.layers.13.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
77
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
78
+ "model.layers.13.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
79
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
80
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
81
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
82
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
83
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
84
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
85
+ "model.layers.14.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
86
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
87
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
88
+ "model.layers.14.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
89
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
90
+ "model.layers.14.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
91
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
92
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
93
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
94
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
95
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
96
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
97
+ "model.layers.15.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
98
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
99
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
100
+ "model.layers.15.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
101
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
102
+ "model.layers.15.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
103
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
104
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
105
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
106
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
107
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
108
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
109
+ "model.layers.16.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
110
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
111
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
112
+ "model.layers.16.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
113
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
114
+ "model.layers.16.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
115
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
116
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
117
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
118
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
119
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
120
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
121
+ "model.layers.17.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
122
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
123
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
124
+ "model.layers.17.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
125
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
126
+ "model.layers.17.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
127
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
128
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
129
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
130
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
131
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
132
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
133
+ "model.layers.18.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
134
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
135
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
136
+ "model.layers.18.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
137
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
138
+ "model.layers.18.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
139
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
140
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
141
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
142
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
143
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
144
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
145
+ "model.layers.19.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
146
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
147
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
148
+ "model.layers.19.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
149
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
150
+ "model.layers.19.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
151
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
152
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
153
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
154
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
155
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
156
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
157
+ "model.layers.2.self_attn.k_proj.bias": "pytorch_model-00001-of-00004.bin",
158
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
159
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
160
+ "model.layers.2.self_attn.q_proj.bias": "pytorch_model-00001-of-00004.bin",
161
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
162
+ "model.layers.2.self_attn.v_proj.bias": "pytorch_model-00001-of-00004.bin",
163
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
164
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
165
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
166
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
167
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
168
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
169
+ "model.layers.20.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
170
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
171
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
172
+ "model.layers.20.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
173
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
174
+ "model.layers.20.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
175
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
176
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
177
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
178
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
179
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
180
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
181
+ "model.layers.21.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
182
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
183
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
184
+ "model.layers.21.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
185
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
186
+ "model.layers.21.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
187
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
188
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
189
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
190
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
191
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
192
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
193
+ "model.layers.22.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
194
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
195
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
196
+ "model.layers.22.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
197
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
198
+ "model.layers.22.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
199
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
200
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
201
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
202
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
203
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
204
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
205
+ "model.layers.23.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
206
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
207
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
208
+ "model.layers.23.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
209
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
210
+ "model.layers.23.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
211
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
212
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
213
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
214
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
215
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
216
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
217
+ "model.layers.24.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
218
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
219
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
220
+ "model.layers.24.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
221
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
222
+ "model.layers.24.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
223
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
224
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
225
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
226
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
227
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
228
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
229
+ "model.layers.25.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
230
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
231
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
232
+ "model.layers.25.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
233
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
234
+ "model.layers.25.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
235
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
236
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
237
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
238
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
239
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
240
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
241
+ "model.layers.26.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
242
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
243
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
244
+ "model.layers.26.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
245
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
246
+ "model.layers.26.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
247
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
248
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
249
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
250
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
251
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
252
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
253
+ "model.layers.27.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
254
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
255
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
256
+ "model.layers.27.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
257
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
258
+ "model.layers.27.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
259
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
260
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
261
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
262
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
263
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
264
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
265
+ "model.layers.3.self_attn.k_proj.bias": "pytorch_model-00001-of-00004.bin",
266
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
267
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
268
+ "model.layers.3.self_attn.q_proj.bias": "pytorch_model-00001-of-00004.bin",
269
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
270
+ "model.layers.3.self_attn.v_proj.bias": "pytorch_model-00001-of-00004.bin",
271
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
272
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
273
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
274
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
275
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
276
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
277
+ "model.layers.4.self_attn.k_proj.bias": "pytorch_model-00001-of-00004.bin",
278
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
279
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
280
+ "model.layers.4.self_attn.q_proj.bias": "pytorch_model-00001-of-00004.bin",
281
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
282
+ "model.layers.4.self_attn.v_proj.bias": "pytorch_model-00001-of-00004.bin",
283
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
284
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
285
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
286
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
287
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
288
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
289
+ "model.layers.5.self_attn.k_proj.bias": "pytorch_model-00001-of-00004.bin",
290
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
291
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
292
+ "model.layers.5.self_attn.q_proj.bias": "pytorch_model-00001-of-00004.bin",
293
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
294
+ "model.layers.5.self_attn.v_proj.bias": "pytorch_model-00001-of-00004.bin",
295
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
296
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
297
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
298
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
299
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
300
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
301
+ "model.layers.6.self_attn.k_proj.bias": "pytorch_model-00001-of-00004.bin",
302
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
303
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
304
+ "model.layers.6.self_attn.q_proj.bias": "pytorch_model-00001-of-00004.bin",
305
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
306
+ "model.layers.6.self_attn.v_proj.bias": "pytorch_model-00001-of-00004.bin",
307
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
308
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
309
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
310
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
311
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
312
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
313
+ "model.layers.7.self_attn.k_proj.bias": "pytorch_model-00001-of-00004.bin",
314
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
315
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
316
+ "model.layers.7.self_attn.q_proj.bias": "pytorch_model-00001-of-00004.bin",
317
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
318
+ "model.layers.7.self_attn.v_proj.bias": "pytorch_model-00001-of-00004.bin",
319
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
320
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
321
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
322
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
323
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
324
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
325
+ "model.layers.8.self_attn.k_proj.bias": "pytorch_model-00001-of-00004.bin",
326
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
327
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
328
+ "model.layers.8.self_attn.q_proj.bias": "pytorch_model-00001-of-00004.bin",
329
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
330
+ "model.layers.8.self_attn.v_proj.bias": "pytorch_model-00001-of-00004.bin",
331
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
332
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
333
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
334
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
335
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
336
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
337
+ "model.layers.9.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
338
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
339
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
340
+ "model.layers.9.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
341
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
342
+ "model.layers.9.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
343
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
344
+ "model.mm_projector.readout.0.bias": "pytorch_model-00004-of-00004.bin",
345
+ "model.mm_projector.readout.0.weight": "pytorch_model-00004-of-00004.bin",
346
+ "model.mm_projector.readout.2.bias": "pytorch_model-00004-of-00004.bin",
347
+ "model.mm_projector.readout.2.weight": "pytorch_model-00004-of-00004.bin",
348
+ "model.norm.weight": "pytorch_model-00003-of-00004.bin",
349
+ "model.region_encoder.feat_linear.0.bias": "pytorch_model-00004-of-00004.bin",
350
+ "model.region_encoder.feat_linear.0.weight": "pytorch_model-00004-of-00004.bin",
351
+ "model.region_encoder.feat_linear.2.bias": "pytorch_model-00004-of-00004.bin",
352
+ "model.region_encoder.feat_linear.2.weight": "pytorch_model-00004-of-00004.bin",
353
+ "model.region_encoder.pos_linear.bias": "pytorch_model-00004-of-00004.bin",
354
+ "model.region_encoder.pos_linear.weight": "pytorch_model-00004-of-00004.bin",
355
+ "model.vision_encoder.vision_encoder.embeddings.patch_embedding.bias": "pytorch_model-00003-of-00004.bin",
356
+ "model.vision_encoder.vision_encoder.embeddings.patch_embedding.weight": "pytorch_model-00003-of-00004.bin",
357
+ "model.vision_encoder.vision_encoder.encoder.layers.0.layer_norm1.bias": "pytorch_model-00003-of-00004.bin",
358
+ "model.vision_encoder.vision_encoder.encoder.layers.0.layer_norm1.weight": "pytorch_model-00003-of-00004.bin",
359
+ "model.vision_encoder.vision_encoder.encoder.layers.0.layer_norm2.bias": "pytorch_model-00003-of-00004.bin",
360
+ "model.vision_encoder.vision_encoder.encoder.layers.0.layer_norm2.weight": "pytorch_model-00003-of-00004.bin",
361
+ "model.vision_encoder.vision_encoder.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00003-of-00004.bin",
362
+ "model.vision_encoder.vision_encoder.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00003-of-00004.bin",
363
+ "model.vision_encoder.vision_encoder.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00003-of-00004.bin",
364
+ "model.vision_encoder.vision_encoder.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00003-of-00004.bin",
365
+ "model.vision_encoder.vision_encoder.encoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
366
+ "model.vision_encoder.vision_encoder.encoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
367
+ "model.vision_encoder.vision_encoder.encoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00003-of-00004.bin",
368
+ "model.vision_encoder.vision_encoder.encoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00003-of-00004.bin",
369
+ "model.vision_encoder.vision_encoder.encoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
370
+ "model.vision_encoder.vision_encoder.encoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
371
+ "model.vision_encoder.vision_encoder.encoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
372
+ "model.vision_encoder.vision_encoder.encoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
373
+ "model.vision_encoder.vision_encoder.encoder.layers.1.layer_norm1.bias": "pytorch_model-00003-of-00004.bin",
374
+ "model.vision_encoder.vision_encoder.encoder.layers.1.layer_norm1.weight": "pytorch_model-00003-of-00004.bin",
375
+ "model.vision_encoder.vision_encoder.encoder.layers.1.layer_norm2.bias": "pytorch_model-00003-of-00004.bin",
376
+ "model.vision_encoder.vision_encoder.encoder.layers.1.layer_norm2.weight": "pytorch_model-00003-of-00004.bin",
377
+ "model.vision_encoder.vision_encoder.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00003-of-00004.bin",
378
+ "model.vision_encoder.vision_encoder.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00003-of-00004.bin",
379
+ "model.vision_encoder.vision_encoder.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00003-of-00004.bin",
380
+ "model.vision_encoder.vision_encoder.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00003-of-00004.bin",
381
+ "model.vision_encoder.vision_encoder.encoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
382
+ "model.vision_encoder.vision_encoder.encoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
383
+ "model.vision_encoder.vision_encoder.encoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00003-of-00004.bin",
384
+ "model.vision_encoder.vision_encoder.encoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00003-of-00004.bin",
385
+ "model.vision_encoder.vision_encoder.encoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
386
+ "model.vision_encoder.vision_encoder.encoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
387
+ "model.vision_encoder.vision_encoder.encoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
388
+ "model.vision_encoder.vision_encoder.encoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
389
+ "model.vision_encoder.vision_encoder.encoder.layers.10.layer_norm1.bias": "pytorch_model-00003-of-00004.bin",
390
+ "model.vision_encoder.vision_encoder.encoder.layers.10.layer_norm1.weight": "pytorch_model-00003-of-00004.bin",
391
+ "model.vision_encoder.vision_encoder.encoder.layers.10.layer_norm2.bias": "pytorch_model-00003-of-00004.bin",
392
+ "model.vision_encoder.vision_encoder.encoder.layers.10.layer_norm2.weight": "pytorch_model-00003-of-00004.bin",
393
+ "model.vision_encoder.vision_encoder.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00003-of-00004.bin",
394
+ "model.vision_encoder.vision_encoder.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00003-of-00004.bin",
395
+ "model.vision_encoder.vision_encoder.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00003-of-00004.bin",
396
+ "model.vision_encoder.vision_encoder.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00003-of-00004.bin",
397
+ "model.vision_encoder.vision_encoder.encoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
398
+ "model.vision_encoder.vision_encoder.encoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
399
+ "model.vision_encoder.vision_encoder.encoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00003-of-00004.bin",
400
+ "model.vision_encoder.vision_encoder.encoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00003-of-00004.bin",
401
+ "model.vision_encoder.vision_encoder.encoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
402
+ "model.vision_encoder.vision_encoder.encoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
403
+ "model.vision_encoder.vision_encoder.encoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
404
+ "model.vision_encoder.vision_encoder.encoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
405
+ "model.vision_encoder.vision_encoder.encoder.layers.11.layer_norm1.bias": "pytorch_model-00003-of-00004.bin",
406
+ "model.vision_encoder.vision_encoder.encoder.layers.11.layer_norm1.weight": "pytorch_model-00003-of-00004.bin",
407
+ "model.vision_encoder.vision_encoder.encoder.layers.11.layer_norm2.bias": "pytorch_model-00003-of-00004.bin",
408
+ "model.vision_encoder.vision_encoder.encoder.layers.11.layer_norm2.weight": "pytorch_model-00003-of-00004.bin",
409
+ "model.vision_encoder.vision_encoder.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00003-of-00004.bin",
410
+ "model.vision_encoder.vision_encoder.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00003-of-00004.bin",
411
+ "model.vision_encoder.vision_encoder.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00003-of-00004.bin",
412
+ "model.vision_encoder.vision_encoder.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00003-of-00004.bin",
413
+ "model.vision_encoder.vision_encoder.encoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
414
+ "model.vision_encoder.vision_encoder.encoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
415
+ "model.vision_encoder.vision_encoder.encoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00003-of-00004.bin",
416
+ "model.vision_encoder.vision_encoder.encoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00003-of-00004.bin",
417
+ "model.vision_encoder.vision_encoder.encoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
418
+ "model.vision_encoder.vision_encoder.encoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
419
+ "model.vision_encoder.vision_encoder.encoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
420
+ "model.vision_encoder.vision_encoder.encoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
421
+ "model.vision_encoder.vision_encoder.encoder.layers.12.layer_norm1.bias": "pytorch_model-00003-of-00004.bin",
422
+ "model.vision_encoder.vision_encoder.encoder.layers.12.layer_norm1.weight": "pytorch_model-00003-of-00004.bin",
423
+ "model.vision_encoder.vision_encoder.encoder.layers.12.layer_norm2.bias": "pytorch_model-00003-of-00004.bin",
424
+ "model.vision_encoder.vision_encoder.encoder.layers.12.layer_norm2.weight": "pytorch_model-00003-of-00004.bin",
425
+ "model.vision_encoder.vision_encoder.encoder.layers.12.mlp.fc1.bias": "pytorch_model-00003-of-00004.bin",
426
+ "model.vision_encoder.vision_encoder.encoder.layers.12.mlp.fc1.weight": "pytorch_model-00003-of-00004.bin",
427
+ "model.vision_encoder.vision_encoder.encoder.layers.12.mlp.fc2.bias": "pytorch_model-00003-of-00004.bin",
428
+ "model.vision_encoder.vision_encoder.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00003-of-00004.bin",
429
+ "model.vision_encoder.vision_encoder.encoder.layers.12.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
430
+ "model.vision_encoder.vision_encoder.encoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
431
+ "model.vision_encoder.vision_encoder.encoder.layers.12.self_attn.out_proj.bias": "pytorch_model-00003-of-00004.bin",
432
+ "model.vision_encoder.vision_encoder.encoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00003-of-00004.bin",
433
+ "model.vision_encoder.vision_encoder.encoder.layers.12.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
434
+ "model.vision_encoder.vision_encoder.encoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
435
+ "model.vision_encoder.vision_encoder.encoder.layers.12.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
436
+ "model.vision_encoder.vision_encoder.encoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
437
+ "model.vision_encoder.vision_encoder.encoder.layers.13.layer_norm1.bias": "pytorch_model-00003-of-00004.bin",
438
+ "model.vision_encoder.vision_encoder.encoder.layers.13.layer_norm1.weight": "pytorch_model-00003-of-00004.bin",
439
+ "model.vision_encoder.vision_encoder.encoder.layers.13.layer_norm2.bias": "pytorch_model-00003-of-00004.bin",
440
+ "model.vision_encoder.vision_encoder.encoder.layers.13.layer_norm2.weight": "pytorch_model-00003-of-00004.bin",
441
+ "model.vision_encoder.vision_encoder.encoder.layers.13.mlp.fc1.bias": "pytorch_model-00003-of-00004.bin",
442
+ "model.vision_encoder.vision_encoder.encoder.layers.13.mlp.fc1.weight": "pytorch_model-00003-of-00004.bin",
443
+ "model.vision_encoder.vision_encoder.encoder.layers.13.mlp.fc2.bias": "pytorch_model-00003-of-00004.bin",
444
+ "model.vision_encoder.vision_encoder.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00003-of-00004.bin",
445
+ "model.vision_encoder.vision_encoder.encoder.layers.13.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
446
+ "model.vision_encoder.vision_encoder.encoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
447
+ "model.vision_encoder.vision_encoder.encoder.layers.13.self_attn.out_proj.bias": "pytorch_model-00003-of-00004.bin",
448
+ "model.vision_encoder.vision_encoder.encoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00003-of-00004.bin",
449
+ "model.vision_encoder.vision_encoder.encoder.layers.13.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
450
+ "model.vision_encoder.vision_encoder.encoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
451
+ "model.vision_encoder.vision_encoder.encoder.layers.13.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
452
+ "model.vision_encoder.vision_encoder.encoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
453
+ "model.vision_encoder.vision_encoder.encoder.layers.14.layer_norm1.bias": "pytorch_model-00003-of-00004.bin",
454
+ "model.vision_encoder.vision_encoder.encoder.layers.14.layer_norm1.weight": "pytorch_model-00003-of-00004.bin",
455
+ "model.vision_encoder.vision_encoder.encoder.layers.14.layer_norm2.bias": "pytorch_model-00003-of-00004.bin",
456
+ "model.vision_encoder.vision_encoder.encoder.layers.14.layer_norm2.weight": "pytorch_model-00003-of-00004.bin",
457
+ "model.vision_encoder.vision_encoder.encoder.layers.14.mlp.fc1.bias": "pytorch_model-00003-of-00004.bin",
458
+ "model.vision_encoder.vision_encoder.encoder.layers.14.mlp.fc1.weight": "pytorch_model-00003-of-00004.bin",
459
+ "model.vision_encoder.vision_encoder.encoder.layers.14.mlp.fc2.bias": "pytorch_model-00003-of-00004.bin",
460
+ "model.vision_encoder.vision_encoder.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00003-of-00004.bin",
461
+ "model.vision_encoder.vision_encoder.encoder.layers.14.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
462
+ "model.vision_encoder.vision_encoder.encoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
463
+ "model.vision_encoder.vision_encoder.encoder.layers.14.self_attn.out_proj.bias": "pytorch_model-00003-of-00004.bin",
464
+ "model.vision_encoder.vision_encoder.encoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00003-of-00004.bin",
465
+ "model.vision_encoder.vision_encoder.encoder.layers.14.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
466
+ "model.vision_encoder.vision_encoder.encoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
467
+ "model.vision_encoder.vision_encoder.encoder.layers.14.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
468
+ "model.vision_encoder.vision_encoder.encoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
469
+ "model.vision_encoder.vision_encoder.encoder.layers.15.layer_norm1.bias": "pytorch_model-00003-of-00004.bin",
470
+ "model.vision_encoder.vision_encoder.encoder.layers.15.layer_norm1.weight": "pytorch_model-00003-of-00004.bin",
471
+ "model.vision_encoder.vision_encoder.encoder.layers.15.layer_norm2.bias": "pytorch_model-00003-of-00004.bin",
472
+ "model.vision_encoder.vision_encoder.encoder.layers.15.layer_norm2.weight": "pytorch_model-00003-of-00004.bin",
473
+ "model.vision_encoder.vision_encoder.encoder.layers.15.mlp.fc1.bias": "pytorch_model-00003-of-00004.bin",
474
+ "model.vision_encoder.vision_encoder.encoder.layers.15.mlp.fc1.weight": "pytorch_model-00003-of-00004.bin",
475
+ "model.vision_encoder.vision_encoder.encoder.layers.15.mlp.fc2.bias": "pytorch_model-00003-of-00004.bin",
476
+ "model.vision_encoder.vision_encoder.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00003-of-00004.bin",
477
+ "model.vision_encoder.vision_encoder.encoder.layers.15.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
478
+ "model.vision_encoder.vision_encoder.encoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
479
+ "model.vision_encoder.vision_encoder.encoder.layers.15.self_attn.out_proj.bias": "pytorch_model-00003-of-00004.bin",
480
+ "model.vision_encoder.vision_encoder.encoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00003-of-00004.bin",
481
+ "model.vision_encoder.vision_encoder.encoder.layers.15.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
482
+ "model.vision_encoder.vision_encoder.encoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
483
+ "model.vision_encoder.vision_encoder.encoder.layers.15.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
484
+ "model.vision_encoder.vision_encoder.encoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
485
+ "model.vision_encoder.vision_encoder.encoder.layers.16.layer_norm1.bias": "pytorch_model-00003-of-00004.bin",
486
+ "model.vision_encoder.vision_encoder.encoder.layers.16.layer_norm1.weight": "pytorch_model-00003-of-00004.bin",
487
+ "model.vision_encoder.vision_encoder.encoder.layers.16.layer_norm2.bias": "pytorch_model-00003-of-00004.bin",
488
+ "model.vision_encoder.vision_encoder.encoder.layers.16.layer_norm2.weight": "pytorch_model-00003-of-00004.bin",
489
+ "model.vision_encoder.vision_encoder.encoder.layers.16.mlp.fc1.bias": "pytorch_model-00003-of-00004.bin",
490
+ "model.vision_encoder.vision_encoder.encoder.layers.16.mlp.fc1.weight": "pytorch_model-00003-of-00004.bin",
491
+ "model.vision_encoder.vision_encoder.encoder.layers.16.mlp.fc2.bias": "pytorch_model-00003-of-00004.bin",
492
+ "model.vision_encoder.vision_encoder.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00003-of-00004.bin",
493
+ "model.vision_encoder.vision_encoder.encoder.layers.16.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
494
+ "model.vision_encoder.vision_encoder.encoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
495
+ "model.vision_encoder.vision_encoder.encoder.layers.16.self_attn.out_proj.bias": "pytorch_model-00003-of-00004.bin",
496
+ "model.vision_encoder.vision_encoder.encoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00003-of-00004.bin",
497
+ "model.vision_encoder.vision_encoder.encoder.layers.16.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
498
+ "model.vision_encoder.vision_encoder.encoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
499
+ "model.vision_encoder.vision_encoder.encoder.layers.16.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
500
+ "model.vision_encoder.vision_encoder.encoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
501
+ "model.vision_encoder.vision_encoder.encoder.layers.17.layer_norm1.bias": "pytorch_model-00003-of-00004.bin",
502
+ "model.vision_encoder.vision_encoder.encoder.layers.17.layer_norm1.weight": "pytorch_model-00003-of-00004.bin",
503
+ "model.vision_encoder.vision_encoder.encoder.layers.17.layer_norm2.bias": "pytorch_model-00003-of-00004.bin",
504
+ "model.vision_encoder.vision_encoder.encoder.layers.17.layer_norm2.weight": "pytorch_model-00003-of-00004.bin",
505
+ "model.vision_encoder.vision_encoder.encoder.layers.17.mlp.fc1.bias": "pytorch_model-00003-of-00004.bin",
506
+ "model.vision_encoder.vision_encoder.encoder.layers.17.mlp.fc1.weight": "pytorch_model-00003-of-00004.bin",
507
+ "model.vision_encoder.vision_encoder.encoder.layers.17.mlp.fc2.bias": "pytorch_model-00003-of-00004.bin",
508
+ "model.vision_encoder.vision_encoder.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00003-of-00004.bin",
509
+ "model.vision_encoder.vision_encoder.encoder.layers.17.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
510
+ "model.vision_encoder.vision_encoder.encoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
511
+ "model.vision_encoder.vision_encoder.encoder.layers.17.self_attn.out_proj.bias": "pytorch_model-00003-of-00004.bin",
512
+ "model.vision_encoder.vision_encoder.encoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00003-of-00004.bin",
513
+ "model.vision_encoder.vision_encoder.encoder.layers.17.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
514
+ "model.vision_encoder.vision_encoder.encoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
515
+ "model.vision_encoder.vision_encoder.encoder.layers.17.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
516
+ "model.vision_encoder.vision_encoder.encoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
517
+ "model.vision_encoder.vision_encoder.encoder.layers.18.layer_norm1.bias": "pytorch_model-00003-of-00004.bin",
518
+ "model.vision_encoder.vision_encoder.encoder.layers.18.layer_norm1.weight": "pytorch_model-00003-of-00004.bin",
519
+ "model.vision_encoder.vision_encoder.encoder.layers.18.layer_norm2.bias": "pytorch_model-00003-of-00004.bin",
520
+ "model.vision_encoder.vision_encoder.encoder.layers.18.layer_norm2.weight": "pytorch_model-00003-of-00004.bin",
521
+ "model.vision_encoder.vision_encoder.encoder.layers.18.mlp.fc1.bias": "pytorch_model-00003-of-00004.bin",
522
+ "model.vision_encoder.vision_encoder.encoder.layers.18.mlp.fc1.weight": "pytorch_model-00003-of-00004.bin",
523
+ "model.vision_encoder.vision_encoder.encoder.layers.18.mlp.fc2.bias": "pytorch_model-00003-of-00004.bin",
524
+ "model.vision_encoder.vision_encoder.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00003-of-00004.bin",
525
+ "model.vision_encoder.vision_encoder.encoder.layers.18.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
526
+ "model.vision_encoder.vision_encoder.encoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
527
+ "model.vision_encoder.vision_encoder.encoder.layers.18.self_attn.out_proj.bias": "pytorch_model-00003-of-00004.bin",
528
+ "model.vision_encoder.vision_encoder.encoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00003-of-00004.bin",
529
+ "model.vision_encoder.vision_encoder.encoder.layers.18.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
530
+ "model.vision_encoder.vision_encoder.encoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
531
+ "model.vision_encoder.vision_encoder.encoder.layers.18.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
532
+ "model.vision_encoder.vision_encoder.encoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
533
+ "model.vision_encoder.vision_encoder.encoder.layers.19.layer_norm1.bias": "pytorch_model-00003-of-00004.bin",
534
+ "model.vision_encoder.vision_encoder.encoder.layers.19.layer_norm1.weight": "pytorch_model-00003-of-00004.bin",
535
+ "model.vision_encoder.vision_encoder.encoder.layers.19.layer_norm2.bias": "pytorch_model-00003-of-00004.bin",
536
+ "model.vision_encoder.vision_encoder.encoder.layers.19.layer_norm2.weight": "pytorch_model-00003-of-00004.bin",
537
+ "model.vision_encoder.vision_encoder.encoder.layers.19.mlp.fc1.bias": "pytorch_model-00003-of-00004.bin",
538
+ "model.vision_encoder.vision_encoder.encoder.layers.19.mlp.fc1.weight": "pytorch_model-00003-of-00004.bin",
539
+ "model.vision_encoder.vision_encoder.encoder.layers.19.mlp.fc2.bias": "pytorch_model-00003-of-00004.bin",
540
+ "model.vision_encoder.vision_encoder.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00003-of-00004.bin",
541
+ "model.vision_encoder.vision_encoder.encoder.layers.19.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
542
+ "model.vision_encoder.vision_encoder.encoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
543
+ "model.vision_encoder.vision_encoder.encoder.layers.19.self_attn.out_proj.bias": "pytorch_model-00003-of-00004.bin",
544
+ "model.vision_encoder.vision_encoder.encoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00003-of-00004.bin",
545
+ "model.vision_encoder.vision_encoder.encoder.layers.19.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
546
+ "model.vision_encoder.vision_encoder.encoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
547
+ "model.vision_encoder.vision_encoder.encoder.layers.19.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
548
+ "model.vision_encoder.vision_encoder.encoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
549
+ "model.vision_encoder.vision_encoder.encoder.layers.2.layer_norm1.bias": "pytorch_model-00003-of-00004.bin",
550
+ "model.vision_encoder.vision_encoder.encoder.layers.2.layer_norm1.weight": "pytorch_model-00003-of-00004.bin",
551
+ "model.vision_encoder.vision_encoder.encoder.layers.2.layer_norm2.bias": "pytorch_model-00003-of-00004.bin",
552
+ "model.vision_encoder.vision_encoder.encoder.layers.2.layer_norm2.weight": "pytorch_model-00003-of-00004.bin",
553
+ "model.vision_encoder.vision_encoder.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00003-of-00004.bin",
554
+ "model.vision_encoder.vision_encoder.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00003-of-00004.bin",
555
+ "model.vision_encoder.vision_encoder.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00003-of-00004.bin",
556
+ "model.vision_encoder.vision_encoder.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00003-of-00004.bin",
557
+ "model.vision_encoder.vision_encoder.encoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
558
+ "model.vision_encoder.vision_encoder.encoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
559
+ "model.vision_encoder.vision_encoder.encoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00003-of-00004.bin",
560
+ "model.vision_encoder.vision_encoder.encoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00003-of-00004.bin",
561
+ "model.vision_encoder.vision_encoder.encoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
562
+ "model.vision_encoder.vision_encoder.encoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
563
+ "model.vision_encoder.vision_encoder.encoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
564
+ "model.vision_encoder.vision_encoder.encoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
565
+ "model.vision_encoder.vision_encoder.encoder.layers.20.layer_norm1.bias": "pytorch_model-00003-of-00004.bin",
566
+ "model.vision_encoder.vision_encoder.encoder.layers.20.layer_norm1.weight": "pytorch_model-00003-of-00004.bin",
567
+ "model.vision_encoder.vision_encoder.encoder.layers.20.layer_norm2.bias": "pytorch_model-00003-of-00004.bin",
568
+ "model.vision_encoder.vision_encoder.encoder.layers.20.layer_norm2.weight": "pytorch_model-00003-of-00004.bin",
569
+ "model.vision_encoder.vision_encoder.encoder.layers.20.mlp.fc1.bias": "pytorch_model-00003-of-00004.bin",
570
+ "model.vision_encoder.vision_encoder.encoder.layers.20.mlp.fc1.weight": "pytorch_model-00003-of-00004.bin",
571
+ "model.vision_encoder.vision_encoder.encoder.layers.20.mlp.fc2.bias": "pytorch_model-00003-of-00004.bin",
572
+ "model.vision_encoder.vision_encoder.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00003-of-00004.bin",
573
+ "model.vision_encoder.vision_encoder.encoder.layers.20.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
574
+ "model.vision_encoder.vision_encoder.encoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
575
+ "model.vision_encoder.vision_encoder.encoder.layers.20.self_attn.out_proj.bias": "pytorch_model-00003-of-00004.bin",
576
+ "model.vision_encoder.vision_encoder.encoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00003-of-00004.bin",
577
+ "model.vision_encoder.vision_encoder.encoder.layers.20.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
578
+ "model.vision_encoder.vision_encoder.encoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
579
+ "model.vision_encoder.vision_encoder.encoder.layers.20.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
580
+ "model.vision_encoder.vision_encoder.encoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
581
+ "model.vision_encoder.vision_encoder.encoder.layers.21.layer_norm1.bias": "pytorch_model-00003-of-00004.bin",
582
+ "model.vision_encoder.vision_encoder.encoder.layers.21.layer_norm1.weight": "pytorch_model-00003-of-00004.bin",
583
+ "model.vision_encoder.vision_encoder.encoder.layers.21.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
584
+ "model.vision_encoder.vision_encoder.encoder.layers.21.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
585
+ "model.vision_encoder.vision_encoder.encoder.layers.21.mlp.fc1.bias": "pytorch_model-00003-of-00004.bin",
586
+ "model.vision_encoder.vision_encoder.encoder.layers.21.mlp.fc1.weight": "pytorch_model-00003-of-00004.bin",
587
+ "model.vision_encoder.vision_encoder.encoder.layers.21.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
588
+ "model.vision_encoder.vision_encoder.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
589
+ "model.vision_encoder.vision_encoder.encoder.layers.21.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
590
+ "model.vision_encoder.vision_encoder.encoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
591
+ "model.vision_encoder.vision_encoder.encoder.layers.21.self_attn.out_proj.bias": "pytorch_model-00003-of-00004.bin",
592
+ "model.vision_encoder.vision_encoder.encoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00003-of-00004.bin",
593
+ "model.vision_encoder.vision_encoder.encoder.layers.21.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
594
+ "model.vision_encoder.vision_encoder.encoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
595
+ "model.vision_encoder.vision_encoder.encoder.layers.21.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
596
+ "model.vision_encoder.vision_encoder.encoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
597
+ "model.vision_encoder.vision_encoder.encoder.layers.22.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
598
+ "model.vision_encoder.vision_encoder.encoder.layers.22.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
599
+ "model.vision_encoder.vision_encoder.encoder.layers.22.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
600
+ "model.vision_encoder.vision_encoder.encoder.layers.22.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
601
+ "model.vision_encoder.vision_encoder.encoder.layers.22.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
602
+ "model.vision_encoder.vision_encoder.encoder.layers.22.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
603
+ "model.vision_encoder.vision_encoder.encoder.layers.22.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
604
+ "model.vision_encoder.vision_encoder.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
605
+ "model.vision_encoder.vision_encoder.encoder.layers.22.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
606
+ "model.vision_encoder.vision_encoder.encoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
607
+ "model.vision_encoder.vision_encoder.encoder.layers.22.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
608
+ "model.vision_encoder.vision_encoder.encoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
609
+ "model.vision_encoder.vision_encoder.encoder.layers.22.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
610
+ "model.vision_encoder.vision_encoder.encoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
611
+ "model.vision_encoder.vision_encoder.encoder.layers.22.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
612
+ "model.vision_encoder.vision_encoder.encoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
613
+ "model.vision_encoder.vision_encoder.encoder.layers.23.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
614
+ "model.vision_encoder.vision_encoder.encoder.layers.23.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
615
+ "model.vision_encoder.vision_encoder.encoder.layers.23.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
616
+ "model.vision_encoder.vision_encoder.encoder.layers.23.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
617
+ "model.vision_encoder.vision_encoder.encoder.layers.23.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
618
+ "model.vision_encoder.vision_encoder.encoder.layers.23.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
619
+ "model.vision_encoder.vision_encoder.encoder.layers.23.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
620
+ "model.vision_encoder.vision_encoder.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
621
+ "model.vision_encoder.vision_encoder.encoder.layers.23.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
622
+ "model.vision_encoder.vision_encoder.encoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
623
+ "model.vision_encoder.vision_encoder.encoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
624
+ "model.vision_encoder.vision_encoder.encoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
625
+ "model.vision_encoder.vision_encoder.encoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
626
+ "model.vision_encoder.vision_encoder.encoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
627
+ "model.vision_encoder.vision_encoder.encoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
628
+ "model.vision_encoder.vision_encoder.encoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
629
+ "model.vision_encoder.vision_encoder.encoder.layers.24.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
630
+ "model.vision_encoder.vision_encoder.encoder.layers.24.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
631
+ "model.vision_encoder.vision_encoder.encoder.layers.24.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
632
+ "model.vision_encoder.vision_encoder.encoder.layers.24.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
633
+ "model.vision_encoder.vision_encoder.encoder.layers.24.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
634
+ "model.vision_encoder.vision_encoder.encoder.layers.24.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
635
+ "model.vision_encoder.vision_encoder.encoder.layers.24.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
636
+ "model.vision_encoder.vision_encoder.encoder.layers.24.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
637
+ "model.vision_encoder.vision_encoder.encoder.layers.24.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
638
+ "model.vision_encoder.vision_encoder.encoder.layers.24.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
639
+ "model.vision_encoder.vision_encoder.encoder.layers.24.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
640
+ "model.vision_encoder.vision_encoder.encoder.layers.24.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
641
+ "model.vision_encoder.vision_encoder.encoder.layers.24.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
642
+ "model.vision_encoder.vision_encoder.encoder.layers.24.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
643
+ "model.vision_encoder.vision_encoder.encoder.layers.24.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
644
+ "model.vision_encoder.vision_encoder.encoder.layers.24.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
645
+ "model.vision_encoder.vision_encoder.encoder.layers.25.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
646
+ "model.vision_encoder.vision_encoder.encoder.layers.25.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
647
+ "model.vision_encoder.vision_encoder.encoder.layers.25.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
648
+ "model.vision_encoder.vision_encoder.encoder.layers.25.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
649
+ "model.vision_encoder.vision_encoder.encoder.layers.25.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
650
+ "model.vision_encoder.vision_encoder.encoder.layers.25.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
651
+ "model.vision_encoder.vision_encoder.encoder.layers.25.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
652
+ "model.vision_encoder.vision_encoder.encoder.layers.25.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
653
+ "model.vision_encoder.vision_encoder.encoder.layers.25.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
654
+ "model.vision_encoder.vision_encoder.encoder.layers.25.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
655
+ "model.vision_encoder.vision_encoder.encoder.layers.25.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
656
+ "model.vision_encoder.vision_encoder.encoder.layers.25.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
657
+ "model.vision_encoder.vision_encoder.encoder.layers.25.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
658
+ "model.vision_encoder.vision_encoder.encoder.layers.25.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
659
+ "model.vision_encoder.vision_encoder.encoder.layers.25.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
660
+ "model.vision_encoder.vision_encoder.encoder.layers.25.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
661
+ "model.vision_encoder.vision_encoder.encoder.layers.26.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
662
+ "model.vision_encoder.vision_encoder.encoder.layers.26.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
663
+ "model.vision_encoder.vision_encoder.encoder.layers.26.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
664
+ "model.vision_encoder.vision_encoder.encoder.layers.26.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
665
+ "model.vision_encoder.vision_encoder.encoder.layers.26.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
666
+ "model.vision_encoder.vision_encoder.encoder.layers.26.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
667
+ "model.vision_encoder.vision_encoder.encoder.layers.26.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
668
+ "model.vision_encoder.vision_encoder.encoder.layers.26.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
669
+ "model.vision_encoder.vision_encoder.encoder.layers.26.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
670
+ "model.vision_encoder.vision_encoder.encoder.layers.26.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
671
+ "model.vision_encoder.vision_encoder.encoder.layers.26.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
672
+ "model.vision_encoder.vision_encoder.encoder.layers.26.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
673
+ "model.vision_encoder.vision_encoder.encoder.layers.26.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
674
+ "model.vision_encoder.vision_encoder.encoder.layers.26.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
675
+ "model.vision_encoder.vision_encoder.encoder.layers.26.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
676
+ "model.vision_encoder.vision_encoder.encoder.layers.26.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
677
+ "model.vision_encoder.vision_encoder.encoder.layers.3.layer_norm1.bias": "pytorch_model-00003-of-00004.bin",
678
+ "model.vision_encoder.vision_encoder.encoder.layers.3.layer_norm1.weight": "pytorch_model-00003-of-00004.bin",
679
+ "model.vision_encoder.vision_encoder.encoder.layers.3.layer_norm2.bias": "pytorch_model-00003-of-00004.bin",
680
+ "model.vision_encoder.vision_encoder.encoder.layers.3.layer_norm2.weight": "pytorch_model-00003-of-00004.bin",
681
+ "model.vision_encoder.vision_encoder.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00003-of-00004.bin",
682
+ "model.vision_encoder.vision_encoder.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00003-of-00004.bin",
683
+ "model.vision_encoder.vision_encoder.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00003-of-00004.bin",
684
+ "model.vision_encoder.vision_encoder.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00003-of-00004.bin",
685
+ "model.vision_encoder.vision_encoder.encoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
686
+ "model.vision_encoder.vision_encoder.encoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
687
+ "model.vision_encoder.vision_encoder.encoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00003-of-00004.bin",
688
+ "model.vision_encoder.vision_encoder.encoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00003-of-00004.bin",
689
+ "model.vision_encoder.vision_encoder.encoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
690
+ "model.vision_encoder.vision_encoder.encoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
691
+ "model.vision_encoder.vision_encoder.encoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
692
+ "model.vision_encoder.vision_encoder.encoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
693
+ "model.vision_encoder.vision_encoder.encoder.layers.4.layer_norm1.bias": "pytorch_model-00003-of-00004.bin",
694
+ "model.vision_encoder.vision_encoder.encoder.layers.4.layer_norm1.weight": "pytorch_model-00003-of-00004.bin",
695
+ "model.vision_encoder.vision_encoder.encoder.layers.4.layer_norm2.bias": "pytorch_model-00003-of-00004.bin",
696
+ "model.vision_encoder.vision_encoder.encoder.layers.4.layer_norm2.weight": "pytorch_model-00003-of-00004.bin",
697
+ "model.vision_encoder.vision_encoder.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00003-of-00004.bin",
698
+ "model.vision_encoder.vision_encoder.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00003-of-00004.bin",
699
+ "model.vision_encoder.vision_encoder.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00003-of-00004.bin",
700
+ "model.vision_encoder.vision_encoder.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00003-of-00004.bin",
701
+ "model.vision_encoder.vision_encoder.encoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
702
+ "model.vision_encoder.vision_encoder.encoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
703
+ "model.vision_encoder.vision_encoder.encoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00003-of-00004.bin",
704
+ "model.vision_encoder.vision_encoder.encoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00003-of-00004.bin",
705
+ "model.vision_encoder.vision_encoder.encoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
706
+ "model.vision_encoder.vision_encoder.encoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
707
+ "model.vision_encoder.vision_encoder.encoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
708
+ "model.vision_encoder.vision_encoder.encoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
709
+ "model.vision_encoder.vision_encoder.encoder.layers.5.layer_norm1.bias": "pytorch_model-00003-of-00004.bin",
710
+ "model.vision_encoder.vision_encoder.encoder.layers.5.layer_norm1.weight": "pytorch_model-00003-of-00004.bin",
711
+ "model.vision_encoder.vision_encoder.encoder.layers.5.layer_norm2.bias": "pytorch_model-00003-of-00004.bin",
712
+ "model.vision_encoder.vision_encoder.encoder.layers.5.layer_norm2.weight": "pytorch_model-00003-of-00004.bin",
713
+ "model.vision_encoder.vision_encoder.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00003-of-00004.bin",
714
+ "model.vision_encoder.vision_encoder.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00003-of-00004.bin",
715
+ "model.vision_encoder.vision_encoder.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00003-of-00004.bin",
716
+ "model.vision_encoder.vision_encoder.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00003-of-00004.bin",
717
+ "model.vision_encoder.vision_encoder.encoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
718
+ "model.vision_encoder.vision_encoder.encoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
719
+ "model.vision_encoder.vision_encoder.encoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00003-of-00004.bin",
720
+ "model.vision_encoder.vision_encoder.encoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00003-of-00004.bin",
721
+ "model.vision_encoder.vision_encoder.encoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
722
+ "model.vision_encoder.vision_encoder.encoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
723
+ "model.vision_encoder.vision_encoder.encoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
724
+ "model.vision_encoder.vision_encoder.encoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
725
+ "model.vision_encoder.vision_encoder.encoder.layers.6.layer_norm1.bias": "pytorch_model-00003-of-00004.bin",
726
+ "model.vision_encoder.vision_encoder.encoder.layers.6.layer_norm1.weight": "pytorch_model-00003-of-00004.bin",
727
+ "model.vision_encoder.vision_encoder.encoder.layers.6.layer_norm2.bias": "pytorch_model-00003-of-00004.bin",
728
+ "model.vision_encoder.vision_encoder.encoder.layers.6.layer_norm2.weight": "pytorch_model-00003-of-00004.bin",
729
+ "model.vision_encoder.vision_encoder.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00003-of-00004.bin",
730
+ "model.vision_encoder.vision_encoder.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00003-of-00004.bin",
731
+ "model.vision_encoder.vision_encoder.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00003-of-00004.bin",
732
+ "model.vision_encoder.vision_encoder.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00003-of-00004.bin",
733
+ "model.vision_encoder.vision_encoder.encoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
734
+ "model.vision_encoder.vision_encoder.encoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
735
+ "model.vision_encoder.vision_encoder.encoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00003-of-00004.bin",
736
+ "model.vision_encoder.vision_encoder.encoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00003-of-00004.bin",
737
+ "model.vision_encoder.vision_encoder.encoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
738
+ "model.vision_encoder.vision_encoder.encoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
739
+ "model.vision_encoder.vision_encoder.encoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
740
+ "model.vision_encoder.vision_encoder.encoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
741
+ "model.vision_encoder.vision_encoder.encoder.layers.7.layer_norm1.bias": "pytorch_model-00003-of-00004.bin",
742
+ "model.vision_encoder.vision_encoder.encoder.layers.7.layer_norm1.weight": "pytorch_model-00003-of-00004.bin",
743
+ "model.vision_encoder.vision_encoder.encoder.layers.7.layer_norm2.bias": "pytorch_model-00003-of-00004.bin",
744
+ "model.vision_encoder.vision_encoder.encoder.layers.7.layer_norm2.weight": "pytorch_model-00003-of-00004.bin",
745
+ "model.vision_encoder.vision_encoder.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00003-of-00004.bin",
746
+ "model.vision_encoder.vision_encoder.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00003-of-00004.bin",
747
+ "model.vision_encoder.vision_encoder.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00003-of-00004.bin",
748
+ "model.vision_encoder.vision_encoder.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00003-of-00004.bin",
749
+ "model.vision_encoder.vision_encoder.encoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
750
+ "model.vision_encoder.vision_encoder.encoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
751
+ "model.vision_encoder.vision_encoder.encoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00003-of-00004.bin",
752
+ "model.vision_encoder.vision_encoder.encoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00003-of-00004.bin",
753
+ "model.vision_encoder.vision_encoder.encoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
754
+ "model.vision_encoder.vision_encoder.encoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
755
+ "model.vision_encoder.vision_encoder.encoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
756
+ "model.vision_encoder.vision_encoder.encoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
757
+ "model.vision_encoder.vision_encoder.encoder.layers.8.layer_norm1.bias": "pytorch_model-00003-of-00004.bin",
758
+ "model.vision_encoder.vision_encoder.encoder.layers.8.layer_norm1.weight": "pytorch_model-00003-of-00004.bin",
759
+ "model.vision_encoder.vision_encoder.encoder.layers.8.layer_norm2.bias": "pytorch_model-00003-of-00004.bin",
760
+ "model.vision_encoder.vision_encoder.encoder.layers.8.layer_norm2.weight": "pytorch_model-00003-of-00004.bin",
761
+ "model.vision_encoder.vision_encoder.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00003-of-00004.bin",
762
+ "model.vision_encoder.vision_encoder.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00003-of-00004.bin",
763
+ "model.vision_encoder.vision_encoder.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00003-of-00004.bin",
764
+ "model.vision_encoder.vision_encoder.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00003-of-00004.bin",
765
+ "model.vision_encoder.vision_encoder.encoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
766
+ "model.vision_encoder.vision_encoder.encoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
767
+ "model.vision_encoder.vision_encoder.encoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00003-of-00004.bin",
768
+ "model.vision_encoder.vision_encoder.encoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00003-of-00004.bin",
769
+ "model.vision_encoder.vision_encoder.encoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
770
+ "model.vision_encoder.vision_encoder.encoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
771
+ "model.vision_encoder.vision_encoder.encoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
772
+ "model.vision_encoder.vision_encoder.encoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
773
+ "model.vision_encoder.vision_encoder.encoder.layers.9.layer_norm1.bias": "pytorch_model-00003-of-00004.bin",
774
+ "model.vision_encoder.vision_encoder.encoder.layers.9.layer_norm1.weight": "pytorch_model-00003-of-00004.bin",
775
+ "model.vision_encoder.vision_encoder.encoder.layers.9.layer_norm2.bias": "pytorch_model-00003-of-00004.bin",
776
+ "model.vision_encoder.vision_encoder.encoder.layers.9.layer_norm2.weight": "pytorch_model-00003-of-00004.bin",
777
+ "model.vision_encoder.vision_encoder.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00003-of-00004.bin",
778
+ "model.vision_encoder.vision_encoder.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00003-of-00004.bin",
779
+ "model.vision_encoder.vision_encoder.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00003-of-00004.bin",
780
+ "model.vision_encoder.vision_encoder.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00003-of-00004.bin",
781
+ "model.vision_encoder.vision_encoder.encoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
782
+ "model.vision_encoder.vision_encoder.encoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
783
+ "model.vision_encoder.vision_encoder.encoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00003-of-00004.bin",
784
+ "model.vision_encoder.vision_encoder.encoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00003-of-00004.bin",
785
+ "model.vision_encoder.vision_encoder.encoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
786
+ "model.vision_encoder.vision_encoder.encoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
787
+ "model.vision_encoder.vision_encoder.encoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
788
+ "model.vision_encoder.vision_encoder.encoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
789
+ "model.vision_encoder.vision_encoder.post_layernorm.bias": "pytorch_model-00004-of-00004.bin",
790
+ "model.vision_encoder.vision_encoder.post_layernorm.weight": "pytorch_model-00004-of-00004.bin"
791
+ }
792
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3817610c30c713832ef11e31691f5d18050f0bddbc2dbd2265620939afeedf43
3
+ size 11422643
tokenizer_config.json ADDED
@@ -0,0 +1,244 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<image>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ },
189
+ "151666": {
190
+ "content": "<|stream_start|>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": true
196
+ },
197
+ "151667": {
198
+ "content": "<|stream_end|>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": true
204
+ },
205
+ "151668": {
206
+ "content": "<REGION>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": true
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "auto_map": {
230
+ "AutoProcessor": "/lustre/fs11/portfolios/llmservice/users/zhidingy/wsh-ws/playground/region/checkpoint/VideoLLaMA3-7B-Image--processing_videollama3.Videollama3Qwen2Processor"
231
+ },
232
+ "bos_token": null,
233
+ "chat_template": "\n{%- set identifier = 'im' %}\n{% for message in messages %}\n {% if message['role'] == 'stream' %}\n {% set identifier = 'stream' %}\n {% else %}\n {% set identifier = 'im' %}\n {% endif %}\n {{- '<|' + identifier + '_start|>' + message['role'] + '\n' -}}\n {% if message['content'] is string %}\n {{- message['content'] + '<|' + identifier + '_end|>\n' -}}\n {% else %}\n {% for content in message['content'] %}\n {% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}\n {% if 'time' in content %}\n {{- 'Time ' + content['time'] | round(1) | string + 's: ' -}}\n {% endif %}\n\n {{- '<image>\n' -}}\n\n {% elif content['type'] == 'video' or 'video' in content or 'video_url' in content %}\n {% for i in range(content['num_frames']) %}\n {% if 'time' in content %}\n {{- 'Time ' + content['time'][i] | round(1) | string + 's:' -}}\n {% endif %}\n {% if i < content['num_frames'] - 1 %}\n\n {{- '<image>,' -}}\n\n {% else %}\n\n {{- '<image>\n' -}}\n\n {% endif %}\n {% endfor %}\n {% elif 'text' in content %}\n {{- content['text'] -}}\n {% endif %}\n {% endfor %}\n {{- '<|' + identifier + '_end|>\n' -}}\n {% endif %}\n{% endfor %}\n{% if add_generation_prompt %}\n {{- '<|im_start|>assistant\n' -}}\n{% endif %}\n",
234
+ "clean_up_tokenization_spaces": false,
235
+ "eos_token": "<|im_end|>",
236
+ "errors": "replace",
237
+ "model_max_length": 16384,
238
+ "pad_token": "<|endoftext|>",
239
+ "padding_side": "right",
240
+ "processor_class": "Videollama3Qwen2Processor",
241
+ "split_special_tokens": false,
242
+ "tokenizer_class": "Qwen2Tokenizer",
243
+ "unk_token": null
244
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff