Hugging Face's logo

lamrin8224
/
articles_gpt2

Text Generation
Transformers
PyTorch
gpt2
text-generation-inference
Model card Files
xet
 Community
1
lamrin8224 commited on
Commit
93905bb
·
verified ·
1 Parent(s): 8bab153

Upload folder using huggingface_hub

Browse files
Files changed (37) hide show
  1. checkpoint-1000/config.json +36 -0
  2. checkpoint-1000/optimizer.pt +3 -0
  3. checkpoint-1000/pytorch_model.bin +3 -0
  4. checkpoint-1000/scheduler.pt +3 -0
  5. checkpoint-1000/trainer_state.json +28 -0
  6. checkpoint-1000/training_args.bin +3 -0
  7. checkpoint-1500/config.json +36 -0
  8. checkpoint-1500/optimizer.pt +3 -0
  9. checkpoint-1500/pytorch_model.bin +3 -0
  10. checkpoint-1500/scheduler.pt +3 -0
  11. checkpoint-1500/trainer_state.json +34 -0
  12. checkpoint-1500/training_args.bin +3 -0
  13. checkpoint-2000/config.json +36 -0
  14. checkpoint-2000/optimizer.pt +3 -0
  15. checkpoint-2000/pytorch_model.bin +3 -0
  16. checkpoint-2000/scheduler.pt +3 -0
  17. checkpoint-2000/trainer_state.json +40 -0
  18. checkpoint-2000/training_args.bin +3 -0
  19. checkpoint-2500/config.json +36 -0
  20. checkpoint-2500/optimizer.pt +3 -0
  21. checkpoint-2500/pytorch_model.bin +3 -0
  22. checkpoint-2500/scheduler.pt +3 -0
  23. checkpoint-2500/trainer_state.json +46 -0
  24. checkpoint-2500/training_args.bin +3 -0
  25. checkpoint-500/config.json +36 -0
  26. checkpoint-500/optimizer.pt +3 -0
  27. checkpoint-500/pytorch_model.bin +3 -0
  28. checkpoint-500/scheduler.pt +3 -0
  29. checkpoint-500/trainer_state.json +22 -0
  30. checkpoint-500/training_args.bin +3 -0
  31. config.json +36 -0
  32. merges.txt +0 -0
  33. pytorch_model.bin +3 -0
  34. special_tokens_map.json +1 -0
  35. tokenizer_config.json +1 -0
  36. training_args.bin +3 -0
  37. vocab.json +0 -0
checkpoint-1000/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "gradient_checkpointing": false,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_ctx": 1024,
16
+ "n_embd": 768,
17
+ "n_head": 12,
18
+ "n_inner": null,
19
+ "n_layer": 12,
20
+ "n_positions": 1024,
21
+ "resid_pdrop": 0.1,
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
+ "task_specific_params": {
28
+ "text-generation": {
29
+ "do_sample": true,
30
+ "max_length": 50
31
+ }
32
+ },
33
+ "transformers_version": "4.5.1",
34
+ "use_cache": true,
35
+ "vocab_size": 50257
36
+ }
checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb552d691579a985af8bbeb473ccedf3fa1badf66bd51c56fa6d0d5de9bfef92
3
+ size 995611287
checkpoint-1000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54529ed706ea35d0774e9c55d36bad2177d279bd838e7a01ec70c1803cf620cd
3
+ size 510408315
checkpoint-1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65d985aa5fa7f96f55e308692cf8f9b9ebb6b0bc09a65dd50e86d5656314b7e5
3
+ size 623
checkpoint-1000/trainer_state.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.9920318725099602,
5
+ "global_step": 1000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "learning_rate": 4.00398406374502e-05,
13
+ "loss": 3.6087,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 1.99,
18
+ "learning_rate": 3.00796812749004e-05,
19
+ "loss": 3.242,
20
+ "step": 1000
21
+ }
22
+ ],
23
+ "max_steps": 2510,
24
+ "num_train_epochs": 5,
25
+ "total_flos": 1528351802523648.0,
26
+ "trial_name": null,
27
+ "trial_params": null
28
+ }
checkpoint-1000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4daf1a81ff5405b3e107d846931aef68f65bd8b41b07f9bfc197cc2b6752a2ea
3
+ size 2351
checkpoint-1500/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "gradient_checkpointing": false,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_ctx": 1024,
16
+ "n_embd": 768,
17
+ "n_head": 12,
18
+ "n_inner": null,
19
+ "n_layer": 12,
20
+ "n_positions": 1024,
21
+ "resid_pdrop": 0.1,
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
+ "task_specific_params": {
28
+ "text-generation": {
29
+ "do_sample": true,
30
+ "max_length": 50
31
+ }
32
+ },
33
+ "transformers_version": "4.5.1",
34
+ "use_cache": true,
35
+ "vocab_size": 50257
36
+ }
checkpoint-1500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46ddc653f49376bfe12c7c95f8ee0c54b129f86c68329a53d2e67c78407a5955
3
+ size 995611287
checkpoint-1500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33746d5d9702d787b0eff4fb07ccd81fa452b835d2be9d88b52efee81894f01c
3
+ size 510408315
checkpoint-1500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:055aead58de9e916ba06ab68fc8fb79dea44441ff0687603f042abb9c8f9377d
3
+ size 623
checkpoint-1500/trainer_state.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.9880478087649402,
5
+ "global_step": 1500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "learning_rate": 4.00398406374502e-05,
13
+ "loss": 3.6087,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 1.99,
18
+ "learning_rate": 3.00796812749004e-05,
19
+ "loss": 3.242,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 2.99,
24
+ "learning_rate": 2.01195219123506e-05,
25
+ "loss": 3.0879,
26
+ "step": 1500
27
+ }
28
+ ],
29
+ "max_steps": 2510,
30
+ "num_train_epochs": 5,
31
+ "total_flos": 2292145424695296.0,
32
+ "trial_name": null,
33
+ "trial_params": null
34
+ }
checkpoint-1500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4daf1a81ff5405b3e107d846931aef68f65bd8b41b07f9bfc197cc2b6752a2ea
3
+ size 2351
checkpoint-2000/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "gradient_checkpointing": false,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_ctx": 1024,
16
+ "n_embd": 768,
17
+ "n_head": 12,
18
+ "n_inner": null,
19
+ "n_layer": 12,
20
+ "n_positions": 1024,
21
+ "resid_pdrop": 0.1,
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
+ "task_specific_params": {
28
+ "text-generation": {
29
+ "do_sample": true,
30
+ "max_length": 50
31
+ }
32
+ },
33
+ "transformers_version": "4.5.1",
34
+ "use_cache": true,
35
+ "vocab_size": 50257
36
+ }
checkpoint-2000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77ff8db2d4ccc1a8842d88fb6f5f74119dff50f74ffac330f77f71d1ae8e7830
3
+ size 995611287
checkpoint-2000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42be8068fcdc55688a53ea8bfd2b9e5b95a155cf49aafd93f27b0324919583d0
3
+ size 510408315
checkpoint-2000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f386075610e8d830c19be2a324388e2bc4a321f3dfad61a5a26471d14a912c48
3
+ size 623
checkpoint-2000/trainer_state.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.9840637450199203,
5
+ "global_step": 2000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "learning_rate": 4.00398406374502e-05,
13
+ "loss": 3.6087,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 1.99,
18
+ "learning_rate": 3.00796812749004e-05,
19
+ "loss": 3.242,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 2.99,
24
+ "learning_rate": 2.01195219123506e-05,
25
+ "loss": 3.0879,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 3.98,
30
+ "learning_rate": 1.0159362549800798e-05,
31
+ "loss": 2.9902,
32
+ "step": 2000
33
+ }
34
+ ],
35
+ "max_steps": 2510,
36
+ "num_train_epochs": 5,
37
+ "total_flos": 3055939046866944.0,
38
+ "trial_name": null,
39
+ "trial_params": null
40
+ }
checkpoint-2000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4daf1a81ff5405b3e107d846931aef68f65bd8b41b07f9bfc197cc2b6752a2ea
3
+ size 2351
checkpoint-2500/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "gradient_checkpointing": false,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_ctx": 1024,
16
+ "n_embd": 768,
17
+ "n_head": 12,
18
+ "n_inner": null,
19
+ "n_layer": 12,
20
+ "n_positions": 1024,
21
+ "resid_pdrop": 0.1,
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
+ "task_specific_params": {
28
+ "text-generation": {
29
+ "do_sample": true,
30
+ "max_length": 50
31
+ }
32
+ },
33
+ "transformers_version": "4.5.1",
34
+ "use_cache": true,
35
+ "vocab_size": 50257
36
+ }
checkpoint-2500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:804d672410b51a73aae44bb5d3700ee810c5757d0d3e129729a5ea189cd633df
3
+ size 995611287
checkpoint-2500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e647f6dc37c89c54041fb818b59bbb2869d4e2c194384bfcf3e26539539c9191
3
+ size 510408315
checkpoint-2500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb3ba70b6baf7349452de153560a79836352adad02dd9dd6b93ac1a0bfa64fc5
3
+ size 623
checkpoint-2500/trainer_state.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.9800796812749,
5
+ "global_step": 2500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "learning_rate": 4.00398406374502e-05,
13
+ "loss": 3.6087,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 1.99,
18
+ "learning_rate": 3.00796812749004e-05,
19
+ "loss": 3.242,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 2.99,
24
+ "learning_rate": 2.01195219123506e-05,
25
+ "loss": 3.0879,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 3.98,
30
+ "learning_rate": 1.0159362549800798e-05,
31
+ "loss": 2.9902,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 4.98,
36
+ "learning_rate": 1.99203187250996e-07,
37
+ "loss": 2.9376,
38
+ "step": 2500
39
+ }
40
+ ],
41
+ "max_steps": 2510,
42
+ "num_train_epochs": 5,
43
+ "total_flos": 3819732669038592.0,
44
+ "trial_name": null,
45
+ "trial_params": null
46
+ }
checkpoint-2500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4daf1a81ff5405b3e107d846931aef68f65bd8b41b07f9bfc197cc2b6752a2ea
3
+ size 2351
checkpoint-500/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "gradient_checkpointing": false,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_ctx": 1024,
16
+ "n_embd": 768,
17
+ "n_head": 12,
18
+ "n_inner": null,
19
+ "n_layer": 12,
20
+ "n_positions": 1024,
21
+ "resid_pdrop": 0.1,
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
+ "task_specific_params": {
28
+ "text-generation": {
29
+ "do_sample": true,
30
+ "max_length": 50
31
+ }
32
+ },
33
+ "transformers_version": "4.5.1",
34
+ "use_cache": true,
35
+ "vocab_size": 50257
36
+ }
checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13e7c1173b1b302eccd1df85adb7e264e20ac713c33acb067f62e564d25de3e8
3
+ size 995611287
checkpoint-500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50e9a4fac5b3595613b24273f13fd414238cb7f9bc7ad54090f6f6270fd8e396
3
+ size 510408315
checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a973005d918b454d0104032202a454a4d22b75a3834290b73cd401b8032d5a5
3
+ size 623
checkpoint-500/trainer_state.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9960159362549801,
5
+ "global_step": 500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "learning_rate": 4.00398406374502e-05,
13
+ "loss": 3.6087,
14
+ "step": 500
15
+ }
16
+ ],
17
+ "max_steps": 2510,
18
+ "num_train_epochs": 5,
19
+ "total_flos": 764558180352000.0,
20
+ "trial_name": null,
21
+ "trial_params": null
22
+ }
checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4daf1a81ff5405b3e107d846931aef68f65bd8b41b07f9bfc197cc2b6752a2ea
3
+ size 2351
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "gradient_checkpointing": false,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_ctx": 1024,
16
+ "n_embd": 768,
17
+ "n_head": 12,
18
+ "n_inner": null,
19
+ "n_layer": 12,
20
+ "n_positions": 1024,
21
+ "resid_pdrop": 0.1,
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
+ "task_specific_params": {
28
+ "text-generation": {
29
+ "do_sample": true,
30
+ "max_length": 50
31
+ }
32
+ },
33
+ "transformers_version": "4.5.1",
34
+ "use_cache": true,
35
+ "vocab_size": 50257
36
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f1ab4cce04c1a3ca92b9b77e897e88d63ebd4d1d4d488304dff91997f3a66b7
3
+ size 510408315
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"errors": "replace", "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "tokenizer_file": "/root/.cache/huggingface/transformers/16a2f78023c8dc511294f0c97b5e10fde3ef9889ad6d11ffaa2a00714e73926e.cf2d0ecb83b6df91b3dbb53f1d1e4c311578bfd3aa0e04934215a49bf9898df0", "name_or_path": "gpt2"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4daf1a81ff5405b3e107d846931aef68f65bd8b41b07f9bfc197cc2b6752a2ea
3
+ size 2351
vocab.json ADDED
The diff for this file is too large to render. See raw diff