Hugging Face's logo

Smilyai-labs
/
Smily-ultra-1

Text Generation
Transformers
Safetensors
English
gpt_neo
transformer
chatbot
Model card Files
xet
Community
boning123 commited on
Commit
f09f8dd
·
verified ·
1 Parent(s): 4c487ec

Upload folder using huggingface_hub

Browse files
Files changed (35) hide show
  1. checkpoint-800/config.json +54 -0
  2. checkpoint-800/generation_config.json +6 -0
  3. checkpoint-800/merges.txt +0 -0
  4. checkpoint-800/model.safetensors +3 -0
  5. checkpoint-800/optimizer.pt +3 -0
  6. checkpoint-800/rng_state.pth +3 -0
  7. checkpoint-800/scheduler.pt +3 -0
  8. checkpoint-800/special_tokens_map.json +24 -0
  9. checkpoint-800/tokenizer.json +0 -0
  10. checkpoint-800/tokenizer_config.json +23 -0
  11. checkpoint-800/trainer_state.json +90 -0
  12. checkpoint-800/training_args.bin +3 -0
  13. checkpoint-800/vocab.json +0 -0
  14. checkpoint-810/config.json +54 -0
  15. checkpoint-810/generation_config.json +6 -0
  16. checkpoint-810/merges.txt +0 -0
  17. checkpoint-810/model.safetensors +3 -0
  18. checkpoint-810/optimizer.pt +3 -0
  19. checkpoint-810/rng_state.pth +3 -0
  20. checkpoint-810/scheduler.pt +3 -0
  21. checkpoint-810/special_tokens_map.json +24 -0
  22. checkpoint-810/tokenizer.json +0 -0
  23. checkpoint-810/tokenizer_config.json +23 -0
  24. checkpoint-810/trainer_state.json +90 -0
  25. checkpoint-810/training_args.bin +3 -0
  26. checkpoint-810/vocab.json +0 -0
  27. config.json +54 -0
  28. generation_config.json +6 -0
  29. merges.txt +0 -0
  30. model.safetensors +3 -0
  31. special_tokens_map.json +24 -0
  32. tokenizer.json +0 -0
  33. tokenizer_config.json +23 -0
  34. training_args.bin +3 -0
  35. vocab.json +0 -0
checkpoint-800/config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPTNeoForCausalLM"
5
+ ],
6
+ "attention_dropout": 0,
7
+ "attention_layers": [
8
+ "global",
9
+ "local",
10
+ "global",
11
+ "local",
12
+ "global",
13
+ "local",
14
+ "global",
15
+ "local",
16
+ "global",
17
+ "local",
18
+ "global",
19
+ "local"
20
+ ],
21
+ "attention_types": [
22
+ [
23
+ [
24
+ "global",
25
+ "local"
26
+ ],
27
+ 6
28
+ ]
29
+ ],
30
+ "bos_token_id": 50256,
31
+ "classifier_dropout": 0.1,
32
+ "embed_dropout": 0,
33
+ "eos_token_id": 50256,
34
+ "gradient_checkpointing": false,
35
+ "hidden_size": 768,
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": null,
38
+ "layer_norm_epsilon": 1e-05,
39
+ "max_position_embeddings": 2048,
40
+ "model_type": "gpt_neo",
41
+ "num_heads": 12,
42
+ "num_layers": 12,
43
+ "resid_dropout": 0,
44
+ "summary_activation": null,
45
+ "summary_first_dropout": 0.1,
46
+ "summary_proj_to_labels": true,
47
+ "summary_type": "cls_index",
48
+ "summary_use_proj": true,
49
+ "torch_dtype": "float32",
50
+ "transformers_version": "4.51.3",
51
+ "use_cache": true,
52
+ "vocab_size": 50257,
53
+ "window_size": 256
54
+ }
checkpoint-800/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": "4.51.3"
6
+ }
checkpoint-800/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-800/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bced287c91a2a9a7c2d4fbba2cfadbb3ad4b81cdbd61a575a9ca93a228a0107
3
+ size 500811336
checkpoint-800/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d0319fe5e8aff5173d5edc184448afffb27995645d2ab1bcbe098e312740083
3
+ size 1001722938
checkpoint-800/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cf9097d4513154245c48236b6ec5137b7ee2a21c9f58f2cba798ea275c6026f
3
+ size 14244
checkpoint-800/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ca05cea7352bf686592087ef8d93eb2c53d518cccb92e3a33d7b0e263a472f2
3
+ size 1064
checkpoint-800/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
checkpoint-800/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-800/tokenizer_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "50256": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ }
13
+ },
14
+ "bos_token": "<|endoftext|>",
15
+ "clean_up_tokenization_spaces": true,
16
+ "eos_token": "<|endoftext|>",
17
+ "errors": "replace",
18
+ "extra_special_tokens": {},
19
+ "model_max_length": 2048,
20
+ "pad_token": "<|endoftext|>",
21
+ "tokenizer_class": "GPT2Tokenizer",
22
+ "unk_token": "<|endoftext|>"
23
+ }
checkpoint-800/trainer_state.json ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.962962962962963,
6
+ "eval_steps": 500,
7
+ "global_step": 800,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.37037037037037035,
14
+ "grad_norm": 7.28477144241333,
15
+ "learning_rate": 4.388888888888889e-05,
16
+ "loss": 0.5289,
17
+ "step": 100
18
+ },
19
+ {
20
+ "epoch": 0.7407407407407407,
21
+ "grad_norm": 1.0851131677627563,
22
+ "learning_rate": 3.771604938271605e-05,
23
+ "loss": 0.0582,
24
+ "step": 200
25
+ },
26
+ {
27
+ "epoch": 1.1111111111111112,
28
+ "grad_norm": 3.6556451320648193,
29
+ "learning_rate": 3.1543209876543214e-05,
30
+ "loss": 0.0499,
31
+ "step": 300
32
+ },
33
+ {
34
+ "epoch": 1.4814814814814814,
35
+ "grad_norm": 1.600995659828186,
36
+ "learning_rate": 2.5370370370370372e-05,
37
+ "loss": 0.0436,
38
+ "step": 400
39
+ },
40
+ {
41
+ "epoch": 1.8518518518518519,
42
+ "grad_norm": 1.711982011795044,
43
+ "learning_rate": 1.9197530864197534e-05,
44
+ "loss": 0.045,
45
+ "step": 500
46
+ },
47
+ {
48
+ "epoch": 2.2222222222222223,
49
+ "grad_norm": 0.9681500792503357,
50
+ "learning_rate": 1.3024691358024694e-05,
51
+ "loss": 0.0407,
52
+ "step": 600
53
+ },
54
+ {
55
+ "epoch": 2.5925925925925926,
56
+ "grad_norm": 1.1934666633605957,
57
+ "learning_rate": 6.851851851851852e-06,
58
+ "loss": 0.0346,
59
+ "step": 700
60
+ },
61
+ {
62
+ "epoch": 2.962962962962963,
63
+ "grad_norm": 1.1116873025894165,
64
+ "learning_rate": 6.790123456790124e-07,
65
+ "loss": 0.0334,
66
+ "step": 800
67
+ }
68
+ ],
69
+ "logging_steps": 100,
70
+ "max_steps": 810,
71
+ "num_input_tokens_seen": 0,
72
+ "num_train_epochs": 3,
73
+ "save_steps": 200,
74
+ "stateful_callbacks": {
75
+ "TrainerControl": {
76
+ "args": {
77
+ "should_epoch_stop": false,
78
+ "should_evaluate": false,
79
+ "should_log": false,
80
+ "should_save": true,
81
+ "should_training_stop": false
82
+ },
83
+ "attributes": {}
84
+ }
85
+ },
86
+ "total_flos": 208965677875200.0,
87
+ "train_batch_size": 4,
88
+ "trial_name": null,
89
+ "trial_params": null
90
+ }
checkpoint-800/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9653affe52a7f12827554a2bd9a423dcc68feab81a9982998344f42b6ff5d9b
3
+ size 5304
checkpoint-800/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-810/config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPTNeoForCausalLM"
5
+ ],
6
+ "attention_dropout": 0,
7
+ "attention_layers": [
8
+ "global",
9
+ "local",
10
+ "global",
11
+ "local",
12
+ "global",
13
+ "local",
14
+ "global",
15
+ "local",
16
+ "global",
17
+ "local",
18
+ "global",
19
+ "local"
20
+ ],
21
+ "attention_types": [
22
+ [
23
+ [
24
+ "global",
25
+ "local"
26
+ ],
27
+ 6
28
+ ]
29
+ ],
30
+ "bos_token_id": 50256,
31
+ "classifier_dropout": 0.1,
32
+ "embed_dropout": 0,
33
+ "eos_token_id": 50256,
34
+ "gradient_checkpointing": false,
35
+ "hidden_size": 768,
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": null,
38
+ "layer_norm_epsilon": 1e-05,
39
+ "max_position_embeddings": 2048,
40
+ "model_type": "gpt_neo",
41
+ "num_heads": 12,
42
+ "num_layers": 12,
43
+ "resid_dropout": 0,
44
+ "summary_activation": null,
45
+ "summary_first_dropout": 0.1,
46
+ "summary_proj_to_labels": true,
47
+ "summary_type": "cls_index",
48
+ "summary_use_proj": true,
49
+ "torch_dtype": "float32",
50
+ "transformers_version": "4.51.3",
51
+ "use_cache": true,
52
+ "vocab_size": 50257,
53
+ "window_size": 256
54
+ }
checkpoint-810/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": "4.51.3"
6
+ }
checkpoint-810/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-810/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d115fc8e53835bfbc5339671f7555ad7e2edf0359bebef1ce91e92b1e487ace
3
+ size 500811336
checkpoint-810/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac1797ca3f259070fcbbd346db97492d734c4052a4eef9c0ae5e379bf0d459c5
3
+ size 1001722938
checkpoint-810/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cf9097d4513154245c48236b6ec5137b7ee2a21c9f58f2cba798ea275c6026f
3
+ size 14244
checkpoint-810/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f80051c6ad6bab0a1b148aecb28a1ade8e9369c4ee655b6d33031329cdbc076d
3
+ size 1064
checkpoint-810/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
checkpoint-810/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-810/tokenizer_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "50256": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ }
13
+ },
14
+ "bos_token": "<|endoftext|>",
15
+ "clean_up_tokenization_spaces": true,
16
+ "eos_token": "<|endoftext|>",
17
+ "errors": "replace",
18
+ "extra_special_tokens": {},
19
+ "model_max_length": 2048,
20
+ "pad_token": "<|endoftext|>",
21
+ "tokenizer_class": "GPT2Tokenizer",
22
+ "unk_token": "<|endoftext|>"
23
+ }
checkpoint-810/trainer_state.json ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 810,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.37037037037037035,
14
+ "grad_norm": 7.28477144241333,
15
+ "learning_rate": 4.388888888888889e-05,
16
+ "loss": 0.5289,
17
+ "step": 100
18
+ },
19
+ {
20
+ "epoch": 0.7407407407407407,
21
+ "grad_norm": 1.0851131677627563,
22
+ "learning_rate": 3.771604938271605e-05,
23
+ "loss": 0.0582,
24
+ "step": 200
25
+ },
26
+ {
27
+ "epoch": 1.1111111111111112,
28
+ "grad_norm": 3.6556451320648193,
29
+ "learning_rate": 3.1543209876543214e-05,
30
+ "loss": 0.0499,
31
+ "step": 300
32
+ },
33
+ {
34
+ "epoch": 1.4814814814814814,
35
+ "grad_norm": 1.600995659828186,
36
+ "learning_rate": 2.5370370370370372e-05,
37
+ "loss": 0.0436,
38
+ "step": 400
39
+ },
40
+ {
41
+ "epoch": 1.8518518518518519,
42
+ "grad_norm": 1.711982011795044,
43
+ "learning_rate": 1.9197530864197534e-05,
44
+ "loss": 0.045,
45
+ "step": 500
46
+ },
47
+ {
48
+ "epoch": 2.2222222222222223,
49
+ "grad_norm": 0.9681500792503357,
50
+ "learning_rate": 1.3024691358024694e-05,
51
+ "loss": 0.0407,
52
+ "step": 600
53
+ },
54
+ {
55
+ "epoch": 2.5925925925925926,
56
+ "grad_norm": 1.1934666633605957,
57
+ "learning_rate": 6.851851851851852e-06,
58
+ "loss": 0.0346,
59
+ "step": 700
60
+ },
61
+ {
62
+ "epoch": 2.962962962962963,
63
+ "grad_norm": 1.1116873025894165,
64
+ "learning_rate": 6.790123456790124e-07,
65
+ "loss": 0.0334,
66
+ "step": 800
67
+ }
68
+ ],
69
+ "logging_steps": 100,
70
+ "max_steps": 810,
71
+ "num_input_tokens_seen": 0,
72
+ "num_train_epochs": 3,
73
+ "save_steps": 200,
74
+ "stateful_callbacks": {
75
+ "TrainerControl": {
76
+ "args": {
77
+ "should_epoch_stop": false,
78
+ "should_evaluate": false,
79
+ "should_log": false,
80
+ "should_save": true,
81
+ "should_training_stop": true
82
+ },
83
+ "attributes": {}
84
+ }
85
+ },
86
+ "total_flos": 211577748848640.0,
87
+ "train_batch_size": 4,
88
+ "trial_name": null,
89
+ "trial_params": null
90
+ }
checkpoint-810/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9653affe52a7f12827554a2bd9a423dcc68feab81a9982998344f42b6ff5d9b
3
+ size 5304
checkpoint-810/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPTNeoForCausalLM"
5
+ ],
6
+ "attention_dropout": 0,
7
+ "attention_layers": [
8
+ "global",
9
+ "local",
10
+ "global",
11
+ "local",
12
+ "global",
13
+ "local",
14
+ "global",
15
+ "local",
16
+ "global",
17
+ "local",
18
+ "global",
19
+ "local"
20
+ ],
21
+ "attention_types": [
22
+ [
23
+ [
24
+ "global",
25
+ "local"
26
+ ],
27
+ 6
28
+ ]
29
+ ],
30
+ "bos_token_id": 50256,
31
+ "classifier_dropout": 0.1,
32
+ "embed_dropout": 0,
33
+ "eos_token_id": 50256,
34
+ "gradient_checkpointing": false,
35
+ "hidden_size": 768,
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": null,
38
+ "layer_norm_epsilon": 1e-05,
39
+ "max_position_embeddings": 2048,
40
+ "model_type": "gpt_neo",
41
+ "num_heads": 12,
42
+ "num_layers": 12,
43
+ "resid_dropout": 0,
44
+ "summary_activation": null,
45
+ "summary_first_dropout": 0.1,
46
+ "summary_proj_to_labels": true,
47
+ "summary_type": "cls_index",
48
+ "summary_use_proj": true,
49
+ "torch_dtype": "float32",
50
+ "transformers_version": "4.51.3",
51
+ "use_cache": true,
52
+ "vocab_size": 50257,
53
+ "window_size": 256
54
+ }
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": "4.51.3"
6
+ }
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 sha256:1d115fc8e53835bfbc5339671f7555ad7e2edf0359bebef1ce91e92b1e487ace
3
+ size 500811336
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "50256": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ }
13
+ },
14
+ "bos_token": "<|endoftext|>",
15
+ "clean_up_tokenization_spaces": true,
16
+ "eos_token": "<|endoftext|>",
17
+ "errors": "replace",
18
+ "extra_special_tokens": {},
19
+ "model_max_length": 2048,
20
+ "pad_token": "<|endoftext|>",
21
+ "tokenizer_class": "GPT2Tokenizer",
22
+ "unk_token": "<|endoftext|>"
23
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9653affe52a7f12827554a2bd9a423dcc68feab81a9982998344f42b6ff5d9b
3
+ size 5304
vocab.json ADDED
The diff for this file is too large to render. See raw diff