Hugging Face's logo

Shamima
/
ngram-gpt2-exp4-intermediate

Safetensors
Model card Files
xet
Community
Shamima commited on
Commit
7e5e9e3
·
verified ·
1 Parent(s): 16ecf10

upload trained models

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. checkpoint-0-10000/added_tokens.json +5 -0
  2. checkpoint-0-10000/config.json +31 -0
  3. checkpoint-0-10000/generation_config.json +6 -0
  4. checkpoint-0-10000/merges.txt +0 -0
  5. checkpoint-0-10000/model.safetensors +3 -0
  6. checkpoint-0-10000/special_tokens_map.json +24 -0
  7. checkpoint-0-10000/tokenizer.json +0 -0
  8. checkpoint-0-10000/tokenizer_config.json +45 -0
  9. checkpoint-0-10000/training_state.pt +3 -0
  10. checkpoint-0-10000/vocab.json +0 -0
  11. checkpoint-0-20000/added_tokens.json +5 -0
  12. checkpoint-0-20000/config.json +31 -0
  13. checkpoint-0-20000/generation_config.json +6 -0
  14. checkpoint-0-20000/merges.txt +0 -0
  15. checkpoint-0-20000/model.safetensors +3 -0
  16. checkpoint-0-20000/special_tokens_map.json +24 -0
  17. checkpoint-0-20000/tokenizer.json +0 -0
  18. checkpoint-0-20000/tokenizer_config.json +45 -0
  19. checkpoint-0-20000/training_state.pt +3 -0
  20. checkpoint-0-20000/vocab.json +0 -0
  21. checkpoint-0-30000/added_tokens.json +5 -0
  22. checkpoint-0-30000/config.json +31 -0
  23. checkpoint-0-30000/generation_config.json +6 -0
  24. checkpoint-0-30000/merges.txt +0 -0
  25. checkpoint-0-30000/model.safetensors +3 -0
  26. checkpoint-0-30000/special_tokens_map.json +24 -0
  27. checkpoint-0-30000/tokenizer.json +0 -0
  28. checkpoint-0-30000/tokenizer_config.json +45 -0
  29. checkpoint-0-30000/training_state.pt +3 -0
  30. checkpoint-0-30000/vocab.json +0 -0
  31. checkpoint-0-40000/added_tokens.json +5 -0
  32. checkpoint-0-40000/config.json +31 -0
  33. checkpoint-0-40000/generation_config.json +6 -0
  34. checkpoint-0-40000/merges.txt +0 -0
  35. checkpoint-0-40000/model.safetensors +3 -0
  36. checkpoint-0-40000/special_tokens_map.json +24 -0
  37. checkpoint-0-40000/tokenizer.json +0 -0
  38. checkpoint-0-40000/tokenizer_config.json +45 -0
  39. checkpoint-0-40000/training_state.pt +3 -0
  40. checkpoint-0-40000/vocab.json +0 -0
  41. checkpoint-1-0/added_tokens.json +5 -0
  42. checkpoint-1-0/config.json +31 -0
  43. checkpoint-1-0/generation_config.json +6 -0
  44. checkpoint-1-0/merges.txt +0 -0
  45. checkpoint-1-0/model.safetensors +3 -0
  46. checkpoint-1-0/special_tokens_map.json +24 -0
  47. checkpoint-1-0/tokenizer.json +0 -0
  48. checkpoint-1-0/tokenizer_config.json +45 -0
  49. checkpoint-1-0/training_state.pt +3 -0
  50. checkpoint-1-0/vocab.json +0 -0
checkpoint-0-10000/added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<EOS>": 50258,
3
+ "<|BOS|>": 50257,
4
+ "<|PAD|>": 50259
5
+ }
checkpoint-0-10000/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 50256,
8
+ "embd_pdrop": 0.1,
9
+ "eos_token_id": 50256,
10
+ "initializer_range": 0.02,
11
+ "layer_norm_epsilon": 1e-05,
12
+ "model_type": "gpt2",
13
+ "n_embd": 768,
14
+ "n_head": 12,
15
+ "n_inner": null,
16
+ "n_layer": 12,
17
+ "n_positions": 512,
18
+ "reorder_and_upcast_attn": false,
19
+ "resid_pdrop": 0.1,
20
+ "scale_attn_by_inverse_layer_idx": false,
21
+ "scale_attn_weights": true,
22
+ "summary_activation": null,
23
+ "summary_first_dropout": 0.1,
24
+ "summary_proj_to_labels": true,
25
+ "summary_type": "cls_index",
26
+ "summary_use_proj": true,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.53.2",
29
+ "use_cache": true,
30
+ "vocab_size": 50260
31
+ }
checkpoint-0-10000/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.53.2"
6
+ }
checkpoint-0-10000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-0-10000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e48e96f2e26ddc881bb58dde2e1cf284ad8033ce0dbd80bee96cdf11bf0fa5e
3
+ size 496210560
checkpoint-0-10000/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|BOS|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<EOS>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|PAD|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": "<|endoftext|>"
24
+ }
checkpoint-0-10000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-0-10000/tokenizer_config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "50257": {
13
+ "content": "<|BOS|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "50258": {
21
+ "content": "<EOS>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "50259": {
29
+ "content": "<|PAD|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ }
36
+ },
37
+ "bos_token": "<|BOS|>",
38
+ "clean_up_tokenization_spaces": false,
39
+ "eos_token": "<EOS>",
40
+ "extra_special_tokens": {},
41
+ "model_max_length": 1024,
42
+ "pad_token": "<|PAD|>",
43
+ "tokenizer_class": "GPT2Tokenizer",
44
+ "unk_token": "<|endoftext|>"
45
+ }
checkpoint-0-10000/training_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fe4da0f1a29ff513c5d01b70375ed19ae3a12ed3aa5fe5f7b83f3b693e1cc45
3
+ size 992518202
checkpoint-0-10000/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-0-20000/added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<EOS>": 50258,
3
+ "<|BOS|>": 50257,
4
+ "<|PAD|>": 50259
5
+ }
checkpoint-0-20000/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 50256,
8
+ "embd_pdrop": 0.1,
9
+ "eos_token_id": 50256,
10
+ "initializer_range": 0.02,
11
+ "layer_norm_epsilon": 1e-05,
12
+ "model_type": "gpt2",
13
+ "n_embd": 768,
14
+ "n_head": 12,
15
+ "n_inner": null,
16
+ "n_layer": 12,
17
+ "n_positions": 512,
18
+ "reorder_and_upcast_attn": false,
19
+ "resid_pdrop": 0.1,
20
+ "scale_attn_by_inverse_layer_idx": false,
21
+ "scale_attn_weights": true,
22
+ "summary_activation": null,
23
+ "summary_first_dropout": 0.1,
24
+ "summary_proj_to_labels": true,
25
+ "summary_type": "cls_index",
26
+ "summary_use_proj": true,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.53.2",
29
+ "use_cache": true,
30
+ "vocab_size": 50260
31
+ }
checkpoint-0-20000/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.53.2"
6
+ }
checkpoint-0-20000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-0-20000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d311433cae4ee9de498fc15dfcf316b3dd27f34ad7d10414677f8efba187417
3
+ size 496210560
checkpoint-0-20000/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|BOS|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<EOS>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|PAD|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": "<|endoftext|>"
24
+ }
checkpoint-0-20000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-0-20000/tokenizer_config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "50257": {
13
+ "content": "<|BOS|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "50258": {
21
+ "content": "<EOS>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "50259": {
29
+ "content": "<|PAD|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ }
36
+ },
37
+ "bos_token": "<|BOS|>",
38
+ "clean_up_tokenization_spaces": false,
39
+ "eos_token": "<EOS>",
40
+ "extra_special_tokens": {},
41
+ "model_max_length": 1024,
42
+ "pad_token": "<|PAD|>",
43
+ "tokenizer_class": "GPT2Tokenizer",
44
+ "unk_token": "<|endoftext|>"
45
+ }
checkpoint-0-20000/training_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cb6c731021d8fa8e4da400e56159786aba598a221e049c8793c35c0629c3eea
3
+ size 992518202
checkpoint-0-20000/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-0-30000/added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<EOS>": 50258,
3
+ "<|BOS|>": 50257,
4
+ "<|PAD|>": 50259
5
+ }
checkpoint-0-30000/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 50256,
8
+ "embd_pdrop": 0.1,
9
+ "eos_token_id": 50256,
10
+ "initializer_range": 0.02,
11
+ "layer_norm_epsilon": 1e-05,
12
+ "model_type": "gpt2",
13
+ "n_embd": 768,
14
+ "n_head": 12,
15
+ "n_inner": null,
16
+ "n_layer": 12,
17
+ "n_positions": 512,
18
+ "reorder_and_upcast_attn": false,
19
+ "resid_pdrop": 0.1,
20
+ "scale_attn_by_inverse_layer_idx": false,
21
+ "scale_attn_weights": true,
22
+ "summary_activation": null,
23
+ "summary_first_dropout": 0.1,
24
+ "summary_proj_to_labels": true,
25
+ "summary_type": "cls_index",
26
+ "summary_use_proj": true,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.53.2",
29
+ "use_cache": true,
30
+ "vocab_size": 50260
31
+ }
checkpoint-0-30000/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.53.2"
6
+ }
checkpoint-0-30000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-0-30000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0df9d5bbf50f38db42302fb8d15ef8ce62fc42e437fbdc641ada854e6207b8a
3
+ size 496210560
checkpoint-0-30000/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|BOS|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<EOS>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|PAD|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": "<|endoftext|>"
24
+ }
checkpoint-0-30000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-0-30000/tokenizer_config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "50257": {
13
+ "content": "<|BOS|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "50258": {
21
+ "content": "<EOS>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "50259": {
29
+ "content": "<|PAD|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ }
36
+ },
37
+ "bos_token": "<|BOS|>",
38
+ "clean_up_tokenization_spaces": false,
39
+ "eos_token": "<EOS>",
40
+ "extra_special_tokens": {},
41
+ "model_max_length": 1024,
42
+ "pad_token": "<|PAD|>",
43
+ "tokenizer_class": "GPT2Tokenizer",
44
+ "unk_token": "<|endoftext|>"
45
+ }
checkpoint-0-30000/training_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cd11384b7f984e3a242b047d9745e2064203607fb469bab313e2ce66c7f3769
3
+ size 992518202
checkpoint-0-30000/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-0-40000/added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<EOS>": 50258,
3
+ "<|BOS|>": 50257,
4
+ "<|PAD|>": 50259
5
+ }
checkpoint-0-40000/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 50256,
8
+ "embd_pdrop": 0.1,
9
+ "eos_token_id": 50256,
10
+ "initializer_range": 0.02,
11
+ "layer_norm_epsilon": 1e-05,
12
+ "model_type": "gpt2",
13
+ "n_embd": 768,
14
+ "n_head": 12,
15
+ "n_inner": null,
16
+ "n_layer": 12,
17
+ "n_positions": 512,
18
+ "reorder_and_upcast_attn": false,
19
+ "resid_pdrop": 0.1,
20
+ "scale_attn_by_inverse_layer_idx": false,
21
+ "scale_attn_weights": true,
22
+ "summary_activation": null,
23
+ "summary_first_dropout": 0.1,
24
+ "summary_proj_to_labels": true,
25
+ "summary_type": "cls_index",
26
+ "summary_use_proj": true,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.53.2",
29
+ "use_cache": true,
30
+ "vocab_size": 50260
31
+ }
checkpoint-0-40000/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.53.2"
6
+ }
checkpoint-0-40000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-0-40000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56538a3c7604cf85c0b489846900532914a8b4128f2f52cfb801a4c16b0bee52
3
+ size 496210560
checkpoint-0-40000/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|BOS|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<EOS>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|PAD|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": "<|endoftext|>"
24
+ }
checkpoint-0-40000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-0-40000/tokenizer_config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "50257": {
13
+ "content": "<|BOS|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "50258": {
21
+ "content": "<EOS>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "50259": {
29
+ "content": "<|PAD|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ }
36
+ },
37
+ "bos_token": "<|BOS|>",
38
+ "clean_up_tokenization_spaces": false,
39
+ "eos_token": "<EOS>",
40
+ "extra_special_tokens": {},
41
+ "model_max_length": 1024,
42
+ "pad_token": "<|PAD|>",
43
+ "tokenizer_class": "GPT2Tokenizer",
44
+ "unk_token": "<|endoftext|>"
45
+ }
checkpoint-0-40000/training_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:217112304a6ff39eb1a4a7974342e54643dfa7abee41b70790f1bdb7b7e606fd
3
+ size 992518202
checkpoint-0-40000/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1-0/added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<EOS>": 50258,
3
+ "<|BOS|>": 50257,
4
+ "<|PAD|>": 50259
5
+ }
checkpoint-1-0/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 50256,
8
+ "embd_pdrop": 0.1,
9
+ "eos_token_id": 50256,
10
+ "initializer_range": 0.02,
11
+ "layer_norm_epsilon": 1e-05,
12
+ "model_type": "gpt2",
13
+ "n_embd": 768,
14
+ "n_head": 12,
15
+ "n_inner": null,
16
+ "n_layer": 12,
17
+ "n_positions": 512,
18
+ "reorder_and_upcast_attn": false,
19
+ "resid_pdrop": 0.1,
20
+ "scale_attn_by_inverse_layer_idx": false,
21
+ "scale_attn_weights": true,
22
+ "summary_activation": null,
23
+ "summary_first_dropout": 0.1,
24
+ "summary_proj_to_labels": true,
25
+ "summary_type": "cls_index",
26
+ "summary_use_proj": true,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.53.2",
29
+ "use_cache": true,
30
+ "vocab_size": 50260
31
+ }
checkpoint-1-0/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.53.2"
6
+ }
checkpoint-1-0/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1-0/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59d10ae8c775e73cf8dcb6f8e5e80666d099a2372905a307787494ae1c9f277d
3
+ size 496210560
checkpoint-1-0/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|BOS|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<EOS>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|PAD|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": "<|endoftext|>"
24
+ }
checkpoint-1-0/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1-0/tokenizer_config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "50257": {
13
+ "content": "<|BOS|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "50258": {
21
+ "content": "<EOS>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "50259": {
29
+ "content": "<|PAD|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ }
36
+ },
37
+ "bos_token": "<|BOS|>",
38
+ "clean_up_tokenization_spaces": false,
39
+ "eos_token": "<EOS>",
40
+ "extra_special_tokens": {},
41
+ "model_max_length": 1024,
42
+ "pad_token": "<|PAD|>",
43
+ "tokenizer_class": "GPT2Tokenizer",
44
+ "unk_token": "<|endoftext|>"
45
+ }
checkpoint-1-0/training_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5ddb7b2ce2cfbb0d2d73acd4853ca2e3e9528481849b09cf1c481f9700f1561
3
+ size 992518202
checkpoint-1-0/vocab.json ADDED
The diff for this file is too large to render. See raw diff