Hugging Face's logo

Parveshiiii
/
Auto-Completer-0.1

Text Generation
Transformers
Safetensors
English
llama
auto-completion
long-context
smollm2
fine-tuned
text-generation-inference
Model card Files
xet
Community
Parveshiiii commited on
Commit
68ef181
·
verified ·
1 Parent(s): 2f78596

Upload folder using huggingface_hub

Browse files
Files changed (15) hide show
  1. chat_template.jinja +3 -0
  2. config.json +33 -0
  3. generation_config.json +10 -0
  4. merges.txt +0 -0
  5. model.safetensors +3 -0
  6. optimizer.pt +3 -0
  7. rng_state.pth +3 -0
  8. scaler.pt +3 -0
  9. scheduler.pt +3 -0
  10. special_tokens_map.json +43 -0
  11. tokenizer.json +0 -0
  12. tokenizer_config.json +170 -0
  13. trainer_state.json +118 -0
  14. training_args.bin +3 -0
  15. vocab.json +0 -0
chat_template.jinja ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {% for message in messages %}{{'<|' + message['role'] + '|>
2
+ ' + message['content'] + '<|endoftext|>' + '
3
+ '}}{% endfor %}
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "dtype": "float32",
9
+ "eos_token_id": 0,
10
+ "head_dim": 64,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 960,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 2560,
15
+ "is_llama_config": true,
16
+ "max_position_embeddings": 8192,
17
+ "mlp_bias": false,
18
+ "model_type": "llama",
19
+ "num_attention_heads": 15,
20
+ "num_hidden_layers": 32,
21
+ "num_key_value_heads": 5,
22
+ "pad_token_id": 0,
23
+ "pretraining_tp": 1,
24
+ "rms_norm_eps": 1e-05,
25
+ "rope_interleaved": false,
26
+ "rope_scaling": null,
27
+ "rope_theta": 100000,
28
+ "tie_word_embeddings": true,
29
+ "transformers_version": "4.56.1",
30
+ "unsloth_version": "2025.9.2",
31
+ "use_cache": true,
32
+ "vocab_size": 49152
33
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": [
5
+ 0
6
+ ],
7
+ "max_length": 8192,
8
+ "pad_token_id": 0,
9
+ "transformers_version": "4.56.1"
10
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6470b8122de339f31c46ef39f21ff7ee8b1e388febd525c63c25bcaa07b94091
3
+ size 1447317080
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56fb67b2dfeb6e5640a0e896a1acf6b112cec71b1870023b761c66d2f334bcc8
3
+ size 1017266153
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1d565802a8e26c4e8a31328752b7a7fdc186d9401aa008e65697d0ad8c22e33
3
+ size 14645
scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c146ae1cf47c9929c1f0cc98e903ce1070f0c3ea64421f26971b053d42844b7
3
+ size 1383
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dd468a12037943abc731ea6bb19f58d78121bbf9a8793bca485cff41de78943
3
+ size 1465
special_tokens_map.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "<|im_start|>",
5
+ "<|im_end|>",
6
+ "<repo_name>",
7
+ "<reponame>",
8
+ "<file_sep>",
9
+ "<filename>",
10
+ "<gh_stars>",
11
+ "<issue_start>",
12
+ "<issue_comment>",
13
+ "<issue_closed>",
14
+ "<jupyter_start>",
15
+ "<jupyter_text>",
16
+ "<jupyter_code>",
17
+ "<jupyter_output>",
18
+ "<jupyter_script>",
19
+ "<empty_output>"
20
+ ],
21
+ "bos_token": {
22
+ "content": "<|endoftext|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "eos_token": {
29
+ "content": "<|endoftext|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ },
35
+ "pad_token": "<|endoftext|>",
36
+ "unk_token": {
37
+ "content": "<|endoftext|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false
42
+ }
43
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,170 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<repo_name>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<reponame>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": "<file_sep>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "6": {
53
+ "content": "<filename>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "7": {
61
+ "content": "<gh_stars>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "8": {
69
+ "content": "<issue_start>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "9": {
77
+ "content": "<issue_comment>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "10": {
85
+ "content": "<issue_closed>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "11": {
93
+ "content": "<jupyter_start>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "12": {
101
+ "content": "<jupyter_text>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "13": {
109
+ "content": "<jupyter_code>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "14": {
117
+ "content": "<jupyter_output>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "15": {
125
+ "content": "<jupyter_script>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "16": {
133
+ "content": "<empty_output>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ }
140
+ },
141
+ "additional_special_tokens": [
142
+ "<|endoftext|>",
143
+ "<|im_start|>",
144
+ "<|im_end|>",
145
+ "<repo_name>",
146
+ "<reponame>",
147
+ "<file_sep>",
148
+ "<filename>",
149
+ "<gh_stars>",
150
+ "<issue_start>",
151
+ "<issue_comment>",
152
+ "<issue_closed>",
153
+ "<jupyter_start>",
154
+ "<jupyter_text>",
155
+ "<jupyter_code>",
156
+ "<jupyter_output>",
157
+ "<jupyter_script>",
158
+ "<empty_output>"
159
+ ],
160
+ "bos_token": "<|endoftext|>",
161
+ "clean_up_tokenization_spaces": false,
162
+ "eos_token": "<|endoftext|>",
163
+ "extra_special_tokens": {},
164
+ "model_max_length": 8192,
165
+ "pad_token": "<|endoftext|>",
166
+ "padding_side": "right",
167
+ "tokenizer_class": "GPT2Tokenizer",
168
+ "unk_token": "<|endoftext|>",
169
+ "vocab_size": 49152
170
+ }
trainer_state.json ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.064,
6
+ "eval_steps": 500,
7
+ "global_step": 60,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.005333333333333333,
14
+ "grad_norm": 2.473487615585327,
15
+ "learning_rate": 8.000000000000001e-06,
16
+ "loss": 1.5026,
17
+ "step": 5
18
+ },
19
+ {
20
+ "epoch": 0.010666666666666666,
21
+ "grad_norm": 1.7626956701278687,
22
+ "learning_rate": 1.8e-05,
23
+ "loss": 1.2897,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.016,
28
+ "grad_norm": 1.4719895124435425,
29
+ "learning_rate": 1.8400000000000003e-05,
30
+ "loss": 1.1938,
31
+ "step": 15
32
+ },
33
+ {
34
+ "epoch": 0.021333333333333333,
35
+ "grad_norm": 1.7403711080551147,
36
+ "learning_rate": 1.64e-05,
37
+ "loss": 1.053,
38
+ "step": 20
39
+ },
40
+ {
41
+ "epoch": 0.02666666666666667,
42
+ "grad_norm": 1.3212436437606812,
43
+ "learning_rate": 1.4400000000000001e-05,
44
+ "loss": 0.9868,
45
+ "step": 25
46
+ },
47
+ {
48
+ "epoch": 0.032,
49
+ "grad_norm": 1.5049668550491333,
50
+ "learning_rate": 1.2400000000000002e-05,
51
+ "loss": 1.0184,
52
+ "step": 30
53
+ },
54
+ {
55
+ "epoch": 0.037333333333333336,
56
+ "grad_norm": 1.661024570465088,
57
+ "learning_rate": 1.04e-05,
58
+ "loss": 1.0196,
59
+ "step": 35
60
+ },
61
+ {
62
+ "epoch": 0.042666666666666665,
63
+ "grad_norm": 1.2448593378067017,
64
+ "learning_rate": 8.400000000000001e-06,
65
+ "loss": 0.9717,
66
+ "step": 40
67
+ },
68
+ {
69
+ "epoch": 0.048,
70
+ "grad_norm": 1.1254949569702148,
71
+ "learning_rate": 6.4000000000000006e-06,
72
+ "loss": 0.9946,
73
+ "step": 45
74
+ },
75
+ {
76
+ "epoch": 0.05333333333333334,
77
+ "grad_norm": 1.125860333442688,
78
+ "learning_rate": 4.4e-06,
79
+ "loss": 0.9414,
80
+ "step": 50
81
+ },
82
+ {
83
+ "epoch": 0.058666666666666666,
84
+ "grad_norm": 0.8565727472305298,
85
+ "learning_rate": 2.4000000000000003e-06,
86
+ "loss": 0.9027,
87
+ "step": 55
88
+ },
89
+ {
90
+ "epoch": 0.064,
91
+ "grad_norm": 1.1848433017730713,
92
+ "learning_rate": 4.0000000000000003e-07,
93
+ "loss": 0.9667,
94
+ "step": 60
95
+ }
96
+ ],
97
+ "logging_steps": 5,
98
+ "max_steps": 60,
99
+ "num_input_tokens_seen": 0,
100
+ "num_train_epochs": 1,
101
+ "save_steps": 500,
102
+ "stateful_callbacks": {
103
+ "TrainerControl": {
104
+ "args": {
105
+ "should_epoch_stop": false,
106
+ "should_evaluate": false,
107
+ "should_log": false,
108
+ "should_save": true,
109
+ "should_training_stop": true
110
+ },
111
+ "attributes": {}
112
+ }
113
+ },
114
+ "total_flos": 346753161216000.0,
115
+ "train_batch_size": 1,
116
+ "trial_name": null,
117
+ "trial_params": null
118
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d851047ca15cdfbe119580dd4a1f8e4fc565e43d90fa19bb216f03de386233d
3
+ size 6225
vocab.json ADDED
The diff for this file is too large to render. See raw diff