Hugging Face's logo

darshanmakwana
/
storage

ONNX
Safetensors
Model card Files Community
darshanmakwana commited on
Commit
b6e4caa
·
verified ·
1 Parent(s): 855d8c4

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. out/checkpoint-16000/config.json +40 -0
  2. out/checkpoint-16000/generation_config.json +7 -0
  3. out/checkpoint-16000/model.safetensors +3 -0
  4. out/checkpoint-16000/optimizer.pt +3 -0
  5. out/checkpoint-16000/rng_state.pth +3 -0
  6. out/checkpoint-16000/scheduler.pt +3 -0
  7. out/checkpoint-16000/special_tokens_map.json +9 -0
  8. out/checkpoint-16000/tokenizer.json +0 -0
  9. out/checkpoint-16000/tokenizer_config.json +0 -0
  10. out/checkpoint-16000/trainer_state.json +0 -0
  11. out/checkpoint-16000/training_args.bin +3 -0
  12. out/checkpoint-17000/config.json +40 -0
  13. out/checkpoint-17000/generation_config.json +7 -0
  14. out/checkpoint-17000/model.safetensors +3 -0
  15. out/checkpoint-17000/optimizer.pt +3 -0
  16. out/checkpoint-17000/rng_state.pth +3 -0
  17. out/checkpoint-17000/scheduler.pt +3 -0
  18. out/checkpoint-17000/special_tokens_map.json +9 -0
  19. out/checkpoint-17000/tokenizer.json +0 -0
  20. out/checkpoint-17000/tokenizer_config.json +0 -0
  21. out/checkpoint-17000/trainer_state.json +0 -0
  22. out/checkpoint-17000/training_args.bin +3 -0
  23. out/checkpoint-18000/config.json +40 -0
  24. out/checkpoint-18000/generation_config.json +7 -0
  25. out/checkpoint-18000/model.safetensors +3 -0
  26. out/checkpoint-18000/optimizer.pt +3 -0
  27. out/checkpoint-18000/rng_state.pth +3 -0
  28. out/checkpoint-18000/scheduler.pt +3 -0
  29. out/checkpoint-18000/special_tokens_map.json +9 -0
  30. out/checkpoint-18000/tokenizer.json +0 -0
  31. out/checkpoint-18000/tokenizer_config.json +0 -0
  32. out/checkpoint-18000/trainer_state.json +0 -0
  33. out/checkpoint-18000/training_args.bin +3 -0
  34. out/checkpoint-19000/config.json +40 -0
  35. out/checkpoint-19000/generation_config.json +7 -0
  36. out/checkpoint-19000/model.safetensors +3 -0
  37. out/checkpoint-19000/optimizer.pt +3 -0
  38. out/checkpoint-19000/rng_state.pth +3 -0
  39. out/checkpoint-19000/scheduler.pt +3 -0
  40. out/checkpoint-19000/special_tokens_map.json +9 -0
  41. out/checkpoint-19000/tokenizer.json +0 -0
  42. out/checkpoint-19000/tokenizer_config.json +0 -0
  43. out/checkpoint-19000/trainer_state.json +0 -0
  44. out/checkpoint-19000/training_args.bin +3 -0
  45. out/checkpoint-20000/config.json +40 -0
  46. out/checkpoint-20000/generation_config.json +7 -0
  47. out/checkpoint-20000/model.safetensors +3 -0
  48. out/checkpoint-20000/optimizer.pt +3 -0
  49. out/checkpoint-20000/rng_state.pth +3 -0
  50. out/checkpoint-20000/scheduler.pt +3 -0
out/checkpoint-16000/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./models/checkpoint-10000",
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
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1877,
20
+ "pad_token_id": 1026,
21
+ "reorder_and_upcast_attn": false,
22
+ "resid_pdrop": 0.1,
23
+ "scale_attn_by_inverse_layer_idx": false,
24
+ "scale_attn_weights": true,
25
+ "summary_activation": null,
26
+ "summary_first_dropout": 0.1,
27
+ "summary_proj_to_labels": true,
28
+ "summary_type": "cls_index",
29
+ "summary_use_proj": true,
30
+ "task_specific_params": {
31
+ "text-generation": {
32
+ "do_sample": true,
33
+ "max_length": 50
34
+ }
35
+ },
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.41.2",
38
+ "use_cache": true,
39
+ "vocab_size": 6027
40
+ }
out/checkpoint-16000/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "pad_token_id": 1026,
6
+ "transformers_version": "4.41.2"
7
+ }
out/checkpoint-16000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:790d92381e9ac59216e77171ddbe07f0a1801bf7a2b92d973502b74c82d92d8f
3
+ size 364520064
out/checkpoint-16000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:575b6bd6a3caa7784c5ada6c62b42891bd7e2b3de474d707eee963ec0a1baff3
3
+ size 729134010
out/checkpoint-16000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e65fc304061e243c3d875844eb1e2de46e5ebf63e7c98f252c80699f6db03b0
3
+ size 14244
out/checkpoint-16000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3522b54b582fe1a5f40833ed1a75ccde72e3cb67b2e108505119d9a09a4655ae
3
+ size 1064
out/checkpoint-16000/special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "pad_token": {
3
+ "content": "<|padding|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ }
9
+ }
out/checkpoint-16000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
out/checkpoint-16000/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
out/checkpoint-16000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
out/checkpoint-16000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c2928f4418c9a306cbe65ca0c1b156ae660c125ec9122008a9f527a50891704
3
+ size 5112
out/checkpoint-17000/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./models/checkpoint-10000",
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
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1877,
20
+ "pad_token_id": 1026,
21
+ "reorder_and_upcast_attn": false,
22
+ "resid_pdrop": 0.1,
23
+ "scale_attn_by_inverse_layer_idx": false,
24
+ "scale_attn_weights": true,
25
+ "summary_activation": null,
26
+ "summary_first_dropout": 0.1,
27
+ "summary_proj_to_labels": true,
28
+ "summary_type": "cls_index",
29
+ "summary_use_proj": true,
30
+ "task_specific_params": {
31
+ "text-generation": {
32
+ "do_sample": true,
33
+ "max_length": 50
34
+ }
35
+ },
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.41.2",
38
+ "use_cache": true,
39
+ "vocab_size": 6027
40
+ }
out/checkpoint-17000/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "pad_token_id": 1026,
6
+ "transformers_version": "4.41.2"
7
+ }
out/checkpoint-17000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5908bb23ce4d95c4debe9c87c955d1579afdd895efad2abeb078daa82d143cee
3
+ size 364520064
out/checkpoint-17000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8d2bca9516f1245ba29b1c950023e320c69fe514fac1ec3de7ccb5d512c40a9
3
+ size 729134010
out/checkpoint-17000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a86bcf45382dcd681026439a76f0ba22431207f858c90bfa5b701cb621ac2f37
3
+ size 14244
out/checkpoint-17000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c90565d609d17b685b7ce614ba9856a01495c88aaa563cceed5b159cc71e24fc
3
+ size 1064
out/checkpoint-17000/special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "pad_token": {
3
+ "content": "<|padding|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ }
9
+ }
out/checkpoint-17000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
out/checkpoint-17000/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
out/checkpoint-17000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
out/checkpoint-17000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c2928f4418c9a306cbe65ca0c1b156ae660c125ec9122008a9f527a50891704
3
+ size 5112
out/checkpoint-18000/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./models/checkpoint-10000",
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
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1877,
20
+ "pad_token_id": 1026,
21
+ "reorder_and_upcast_attn": false,
22
+ "resid_pdrop": 0.1,
23
+ "scale_attn_by_inverse_layer_idx": false,
24
+ "scale_attn_weights": true,
25
+ "summary_activation": null,
26
+ "summary_first_dropout": 0.1,
27
+ "summary_proj_to_labels": true,
28
+ "summary_type": "cls_index",
29
+ "summary_use_proj": true,
30
+ "task_specific_params": {
31
+ "text-generation": {
32
+ "do_sample": true,
33
+ "max_length": 50
34
+ }
35
+ },
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.41.2",
38
+ "use_cache": true,
39
+ "vocab_size": 6027
40
+ }
out/checkpoint-18000/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "pad_token_id": 1026,
6
+ "transformers_version": "4.41.2"
7
+ }
out/checkpoint-18000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:198fc04ddbaa953c5bcc9a4e3599dd47c8c90f85dddfd34a59e22b5a84b6a590
3
+ size 364520064
out/checkpoint-18000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35be891a7563a210bf433f95cd5e7c0ac2001a1c82dfded1743d075e7bcf189c
3
+ size 729134010
out/checkpoint-18000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f6db0bb394067f9edd733615c5d1f1d6ecc586cc8ad6604014075d45f865eb6
3
+ size 14244
out/checkpoint-18000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09e257775ded399712f9738ac755f4bbc39ac3bdaa44edd0cf546d60bda535ba
3
+ size 1064
out/checkpoint-18000/special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "pad_token": {
3
+ "content": "<|padding|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ }
9
+ }
out/checkpoint-18000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
out/checkpoint-18000/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
out/checkpoint-18000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
out/checkpoint-18000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c2928f4418c9a306cbe65ca0c1b156ae660c125ec9122008a9f527a50891704
3
+ size 5112
out/checkpoint-19000/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./models/checkpoint-10000",
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
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1877,
20
+ "pad_token_id": 1026,
21
+ "reorder_and_upcast_attn": false,
22
+ "resid_pdrop": 0.1,
23
+ "scale_attn_by_inverse_layer_idx": false,
24
+ "scale_attn_weights": true,
25
+ "summary_activation": null,
26
+ "summary_first_dropout": 0.1,
27
+ "summary_proj_to_labels": true,
28
+ "summary_type": "cls_index",
29
+ "summary_use_proj": true,
30
+ "task_specific_params": {
31
+ "text-generation": {
32
+ "do_sample": true,
33
+ "max_length": 50
34
+ }
35
+ },
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.41.2",
38
+ "use_cache": true,
39
+ "vocab_size": 6027
40
+ }
out/checkpoint-19000/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "pad_token_id": 1026,
6
+ "transformers_version": "4.41.2"
7
+ }
out/checkpoint-19000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3e11468e1acb3fae967bb255a9fa4df68708ee3d58154ff4fa1e59f0c0b958a
3
+ size 364520064
out/checkpoint-19000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:662d02c50a885048d10fc2072649021701469d88c40afebf2f833e9be89aa710
3
+ size 729134010
out/checkpoint-19000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57e1e994b500aad62a1a11a9a4c291a77ef34a0bdb5ac056c07bfd1c2d3241f0
3
+ size 14244
out/checkpoint-19000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a8dbd9359bf168f116b41245dd391aa41b350b02d0581ee33c1787e65d68039
3
+ size 1064
out/checkpoint-19000/special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "pad_token": {
3
+ "content": "<|padding|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ }
9
+ }
out/checkpoint-19000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
out/checkpoint-19000/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
out/checkpoint-19000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
out/checkpoint-19000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c2928f4418c9a306cbe65ca0c1b156ae660c125ec9122008a9f527a50891704
3
+ size 5112
out/checkpoint-20000/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./models/checkpoint-10000",
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
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1877,
20
+ "pad_token_id": 1026,
21
+ "reorder_and_upcast_attn": false,
22
+ "resid_pdrop": 0.1,
23
+ "scale_attn_by_inverse_layer_idx": false,
24
+ "scale_attn_weights": true,
25
+ "summary_activation": null,
26
+ "summary_first_dropout": 0.1,
27
+ "summary_proj_to_labels": true,
28
+ "summary_type": "cls_index",
29
+ "summary_use_proj": true,
30
+ "task_specific_params": {
31
+ "text-generation": {
32
+ "do_sample": true,
33
+ "max_length": 50
34
+ }
35
+ },
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.41.2",
38
+ "use_cache": true,
39
+ "vocab_size": 6027
40
+ }
out/checkpoint-20000/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "pad_token_id": 1026,
6
+ "transformers_version": "4.41.2"
7
+ }
out/checkpoint-20000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d31b3734b3cffed46c557d3becb7e65e90b4ab55ebc18eff64ff3aad4999d24
3
+ size 364520064
out/checkpoint-20000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:894f39d8501ad12d19c12229534224ad092f71d7fad8682f34f0d8b975b60eb8
3
+ size 729134010
out/checkpoint-20000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c870fe7abda53c93097dd06715dc0179f87f4864ac260a67d000db16ffe7298d
3
+ size 14244
out/checkpoint-20000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12bf461c5e4bed04e168cc27aed066d45328f7ff5de3945fde4b51483e103707
3
+ size 1064