Hugging Face's logo

BytArch
/
source-mini

Text Generation
Transformers
Safetensors
English
llama
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
BytArch commited on
Commit
2df2ff4
·
verified ·
1 Parent(s): ae995b9

Upload fine-tuned model and tokenizer

Browse files
Files changed (32) hide show
  1. checkpoint-33/config.json +31 -0
  2. checkpoint-33/generation_config.json +6 -0
  3. checkpoint-33/merges.txt +0 -0
  4. checkpoint-33/model.safetensors +3 -0
  5. checkpoint-33/optimizer.pt +3 -0
  6. checkpoint-33/rng_state.pth +3 -0
  7. checkpoint-33/scheduler.pt +3 -0
  8. checkpoint-33/special_tokens_map.json +43 -0
  9. checkpoint-33/tokenizer.json +0 -0
  10. checkpoint-33/tokenizer_config.json +169 -0
  11. checkpoint-33/trainer_state.json +33 -0
  12. checkpoint-33/training_args.bin +3 -0
  13. checkpoint-33/vocab.json +0 -0
  14. checkpoint-66/config.json +31 -0
  15. checkpoint-66/generation_config.json +6 -0
  16. checkpoint-66/merges.txt +0 -0
  17. checkpoint-66/model.safetensors +3 -0
  18. checkpoint-66/optimizer.pt +3 -0
  19. checkpoint-66/rng_state.pth +3 -0
  20. checkpoint-66/scheduler.pt +3 -0
  21. checkpoint-66/special_tokens_map.json +43 -0
  22. checkpoint-66/tokenizer.json +0 -0
  23. checkpoint-66/tokenizer_config.json +169 -0
  24. checkpoint-66/trainer_state.json +41 -0
  25. checkpoint-66/training_args.bin +3 -0
  26. checkpoint-66/vocab.json +0 -0
  27. config.json +8 -15
  28. generation_config.json +2 -3
  29. model.safetensors +2 -2
  30. special_tokens_map.json +19 -10
  31. tokenizer_config.json +19 -4
  32. training_args.bin +1 -1
checkpoint-33/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_interleaved": false,
25
+ "rope_scaling": null,
26
+ "rope_theta": 100000,
27
+ "tie_word_embeddings": true,
28
+ "transformers_version": "4.56.0",
29
+ "use_cache": true,
30
+ "vocab_size": 49152
31
+ }
checkpoint-33/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "transformers_version": "4.56.0"
6
+ }
checkpoint-33/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-33/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c13a82e1113aecfa5a835ffc399ebc78834bfed2a9471b5a0df75ac82d80989c
3
+ size 1447317080
checkpoint-33/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4a808e1a67e21773be4d6ed07a50f1af824b8bf7c533c4e52a8ff5d08be2132
3
+ size 2894805579
checkpoint-33/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1971a7f5a4b2dbf37c7eaedcc9ddd90b7f2853c5557f35719c1a2082903b821
3
+ size 14455
checkpoint-33/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ae2b722cc30748967cbf8d31b4deabb1ef7fc763be3139f86b488e56e0fbefd
3
+ size 1465
checkpoint-33/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
+ }
checkpoint-33/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-33/tokenizer_config.json ADDED
@@ -0,0 +1,169 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "tokenizer_class": "GPT2Tokenizer",
167
+ "unk_token": "<|endoftext|>",
168
+ "vocab_size": 49152
169
+ }
checkpoint-33/trainer_state.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 33,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [],
12
+ "logging_steps": 50,
13
+ "max_steps": 66,
14
+ "num_input_tokens_seen": 0,
15
+ "num_train_epochs": 2,
16
+ "save_steps": 500,
17
+ "stateful_callbacks": {
18
+ "TrainerControl": {
19
+ "args": {
20
+ "should_epoch_stop": false,
21
+ "should_evaluate": false,
22
+ "should_log": false,
23
+ "should_save": true,
24
+ "should_training_stop": false
25
+ },
26
+ "attributes": {}
27
+ }
28
+ },
29
+ "total_flos": 498367054310400.0,
30
+ "train_batch_size": 8,
31
+ "trial_name": null,
32
+ "trial_params": null
33
+ }
checkpoint-33/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e53a0033678bb06cbfe72f2c6cc0dd49bd175000df23b3b707b9e7df1db2480d
3
+ size 5713
checkpoint-33/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-66/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_interleaved": false,
25
+ "rope_scaling": null,
26
+ "rope_theta": 100000,
27
+ "tie_word_embeddings": true,
28
+ "transformers_version": "4.56.0",
29
+ "use_cache": true,
30
+ "vocab_size": 49152
31
+ }
checkpoint-66/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "transformers_version": "4.56.0"
6
+ }
checkpoint-66/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-66/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd77b31b573ba4f99911950d8367bab15fd2bf98d2ae85c8c8fa22563068efcc
3
+ size 1447317080
checkpoint-66/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd52bee0c92087cd8303e77dfccdf11574bf0ebc3cea8864c9d748395ed71004
3
+ size 2894805579
checkpoint-66/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dc8c6913278f9c517962f5aa36e8b395dff7d28049918ddd24f3bbc58af2ae5
3
+ size 14455
checkpoint-66/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e53313a4c270fc58d84709a54609c670b94786a66a6aae599442e6218bd5fc22
3
+ size 1465
checkpoint-66/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
+ }
checkpoint-66/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-66/tokenizer_config.json ADDED
@@ -0,0 +1,169 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "tokenizer_class": "GPT2Tokenizer",
167
+ "unk_token": "<|endoftext|>",
168
+ "vocab_size": 49152
169
+ }
checkpoint-66/trainer_state.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 66,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.523076923076923,
14
+ "grad_norm": 0.8240295648574829,
15
+ "learning_rate": 1.287878787878788e-05,
16
+ "loss": 1.3741,
17
+ "step": 50
18
+ }
19
+ ],
20
+ "logging_steps": 50,
21
+ "max_steps": 66,
22
+ "num_input_tokens_seen": 0,
23
+ "num_train_epochs": 2,
24
+ "save_steps": 500,
25
+ "stateful_callbacks": {
26
+ "TrainerControl": {
27
+ "args": {
28
+ "should_epoch_stop": false,
29
+ "should_evaluate": false,
30
+ "should_log": false,
31
+ "should_save": true,
32
+ "should_training_stop": true
33
+ },
34
+ "attributes": {}
35
+ }
36
+ },
37
+ "total_flos": 1000011348864000.0,
38
+ "train_batch_size": 8,
39
+ "trial_name": null,
40
+ "trial_params": null
41
+ }
checkpoint-66/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e53a0033678bb06cbfe72f2c6cc0dd49bd175000df23b3b707b9e7df1db2480d
3
+ size 5713
checkpoint-66/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
config.json CHANGED
@@ -4,34 +4,27 @@
4
  ],
5
  "attention_bias": false,
6
  "attention_dropout": 0.0,
7
- "bos_token_id": 1,
8
  "dtype": "float32",
9
- "eos_token_id": 2,
10
  "head_dim": 64,
11
  "hidden_act": "silu",
12
- "hidden_size": 576,
13
- "initializer_range": 0.041666666666666664,
14
- "intermediate_size": 1536,
15
  "is_llama_config": true,
16
  "max_position_embeddings": 8192,
17
  "mlp_bias": false,
18
  "model_type": "llama",
19
- "num_attention_heads": 9,
20
- "num_hidden_layers": 30,
21
- "num_key_value_heads": 3,
22
- "pad_token_id": 2,
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.js_config": {
30
- "kv_cache_dtype": {
31
- "fp16": "float16",
32
- "q4f16": "float16"
33
- }
34
- },
35
  "transformers_version": "4.56.0",
36
  "use_cache": true,
37
  "vocab_size": 49152
 
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
  "pretraining_tp": 1,
23
  "rms_norm_eps": 1e-05,
24
  "rope_interleaved": false,
25
  "rope_scaling": null,
26
  "rope_theta": 100000,
27
  "tie_word_embeddings": true,
 
 
 
 
 
 
28
  "transformers_version": "4.56.0",
29
  "use_cache": true,
30
  "vocab_size": 49152
generation_config.json CHANGED
@@ -1,7 +1,6 @@
1
  {
2
  "_from_model_config": true,
3
- "bos_token_id": 1,
4
- "eos_token_id": 2,
5
- "pad_token_id": 2,
6
  "transformers_version": "4.56.0"
7
  }
 
1
  {
2
  "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
 
5
  "transformers_version": "4.56.0"
6
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:41f20b1a2938e2dbedd545a2303520f38374bd526e5b0223401da96bab248def
3
- size 538090408
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd77b31b573ba4f99911950d8367bab15fd2bf98d2ae85c8c8fa22563068efcc
3
+ size 1447317080
special_tokens_map.json CHANGED
@@ -1,29 +1,38 @@
1
  {
2
  "additional_special_tokens": [
 
3
  "<|im_start|>",
4
- "<|im_end|>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  ],
6
  "bos_token": {
7
- "content": "<|im_start|>",
8
  "lstrip": false,
9
  "normalized": false,
10
  "rstrip": false,
11
  "single_word": false
12
  },
13
  "eos_token": {
14
- "content": "<|im_end|>",
15
- "lstrip": false,
16
- "normalized": false,
17
- "rstrip": false,
18
- "single_word": false
19
- },
20
- "pad_token": {
21
- "content": "<|im_end|>",
22
  "lstrip": false,
23
  "normalized": false,
24
  "rstrip": false,
25
  "single_word": false
26
  },
 
27
  "unk_token": {
28
  "content": "<|endoftext|>",
29
  "lstrip": false,
 
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,
tokenizer_config.json CHANGED
@@ -139,15 +139,30 @@
139
  }
140
  },
141
  "additional_special_tokens": [
 
142
  "<|im_start|>",
143
- "<|im_end|>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
144
  ],
145
- "bos_token": "<|im_start|>",
146
  "clean_up_tokenization_spaces": false,
147
- "eos_token": "<|im_end|>",
148
  "extra_special_tokens": {},
149
  "model_max_length": 8192,
150
- "pad_token": "<|im_end|>",
151
  "tokenizer_class": "GPT2Tokenizer",
152
  "unk_token": "<|endoftext|>",
153
  "vocab_size": 49152
 
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
  "tokenizer_class": "GPT2Tokenizer",
167
  "unk_token": "<|endoftext|>",
168
  "vocab_size": 49152
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f366c39c95cb7c8fd5c1e9f6deb3d5dfeef41a2048299ebd2541a2940ab9951
3
  size 5713
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e53a0033678bb06cbfe72f2c6cc0dd49bd175000df23b3b707b9e7df1db2480d
3
  size 5713