Hugging Face's logo

Setpember
/
gpt2large-MIMIC-attack

Text Generation
Transformers
Safetensors
gpt2
Generated from Trainer
text-generation-inference
Model card Files
xet
Community
Setpember commited on
Commit
5b262b0
·
verified ·
1 Parent(s): 6f06d97

Upload folder using huggingface_hub

Browse files
Files changed (28) hide show
  1. checkpoint-62000/config.json +38 -0
  2. checkpoint-62000/generation_config.json +6 -0
  3. checkpoint-62000/merges.txt +0 -0
  4. checkpoint-62000/model.safetensors +3 -0
  5. checkpoint-62000/optimizer.pt +3 -0
  6. checkpoint-62000/rng_state.pth +3 -0
  7. checkpoint-62000/scaler.pt +3 -0
  8. checkpoint-62000/scheduler.pt +3 -0
  9. checkpoint-62000/special_tokens_map.json +6 -0
  10. checkpoint-62000/tokenizer.json +0 -0
  11. checkpoint-62000/tokenizer_config.json +21 -0
  12. checkpoint-62000/trainer_state.json +0 -0
  13. checkpoint-62000/training_args.bin +3 -0
  14. checkpoint-62000/vocab.json +0 -0
  15. checkpoint-62180/config.json +38 -0
  16. checkpoint-62180/generation_config.json +6 -0
  17. checkpoint-62180/merges.txt +0 -0
  18. checkpoint-62180/model.safetensors +3 -0
  19. checkpoint-62180/optimizer.pt +3 -0
  20. checkpoint-62180/rng_state.pth +3 -0
  21. checkpoint-62180/scaler.pt +3 -0
  22. checkpoint-62180/scheduler.pt +3 -0
  23. checkpoint-62180/special_tokens_map.json +6 -0
  24. checkpoint-62180/tokenizer.json +0 -0
  25. checkpoint-62180/tokenizer_config.json +21 -0
  26. checkpoint-62180/trainer_state.json +0 -0
  27. checkpoint-62180/training_args.bin +3 -0
  28. checkpoint-62180/vocab.json +0 -0
checkpoint-62000/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_ctx": 1024,
14
+ "n_embd": 1280,
15
+ "n_head": 20,
16
+ "n_inner": null,
17
+ "n_layer": 36,
18
+ "n_positions": 1024,
19
+ "reorder_and_upcast_attn": false,
20
+ "resid_pdrop": 0.1,
21
+ "scale_attn_by_inverse_layer_idx": false,
22
+ "scale_attn_weights": true,
23
+ "summary_activation": null,
24
+ "summary_first_dropout": 0.1,
25
+ "summary_proj_to_labels": true,
26
+ "summary_type": "cls_index",
27
+ "summary_use_proj": true,
28
+ "task_specific_params": {
29
+ "text-generation": {
30
+ "do_sample": true,
31
+ "max_length": 50
32
+ }
33
+ },
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.52.4",
36
+ "use_cache": true,
37
+ "vocab_size": 50257
38
+ }
checkpoint-62000/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": "4.52.4"
6
+ }
checkpoint-62000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-62000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3cd6fac1062de47504b78ab98afad258615711d223f4f09afaad096552a0c48
3
+ size 3096165928
checkpoint-62000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89cc4bf1e58b5c02c832eb04a64e52164c6c142ca675ab42f5aa278c9292a18d
3
+ size 6192613990
checkpoint-62000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da997f7ab6e735cb87dd2eeb2e813bff5de53bf3d98ff321e6d81931f14efe97
3
+ size 14244
checkpoint-62000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a46acce178f6d1151d507d0b13a82a7cc93932fdb58679d9d1bceb71d4a8ca3
3
+ size 988
checkpoint-62000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d8e7ad2637bbab8c82c6e41b17aeb82e91e7cdf224d12089f69e5420e09671a
3
+ size 1064
checkpoint-62000/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
checkpoint-62000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-62000/tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": false,
15
+ "eos_token": "<|endoftext|>",
16
+ "extra_special_tokens": {},
17
+ "model_max_length": 1024,
18
+ "pad_token": "<|endoftext|>",
19
+ "tokenizer_class": "GPT2Tokenizer",
20
+ "unk_token": "<|endoftext|>"
21
+ }
checkpoint-62000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-62000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db0949917c5ba886e7bc4d4f88a5d1ae410b72f4b7845b4e5c992caf95bee997
3
+ size 5240
checkpoint-62000/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-62180/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_ctx": 1024,
14
+ "n_embd": 1280,
15
+ "n_head": 20,
16
+ "n_inner": null,
17
+ "n_layer": 36,
18
+ "n_positions": 1024,
19
+ "reorder_and_upcast_attn": false,
20
+ "resid_pdrop": 0.1,
21
+ "scale_attn_by_inverse_layer_idx": false,
22
+ "scale_attn_weights": true,
23
+ "summary_activation": null,
24
+ "summary_first_dropout": 0.1,
25
+ "summary_proj_to_labels": true,
26
+ "summary_type": "cls_index",
27
+ "summary_use_proj": true,
28
+ "task_specific_params": {
29
+ "text-generation": {
30
+ "do_sample": true,
31
+ "max_length": 50
32
+ }
33
+ },
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.52.4",
36
+ "use_cache": true,
37
+ "vocab_size": 50257
38
+ }
checkpoint-62180/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": "4.52.4"
6
+ }
checkpoint-62180/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-62180/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:371f5c1aafe9736d6e4595d8c9edd2ec5c98965adf2ab3e7761e12dd8d977ebc
3
+ size 3096165928
checkpoint-62180/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7034fa9d771d2d471c9cbec14c94b02329b8c422ca7165ca7b0a4ec4d26c294b
3
+ size 6192613990
checkpoint-62180/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f47d3c0517185d4d6be399785b53b685584a160fa1bce48beb383f2044a27ec9
3
+ size 14244
checkpoint-62180/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e1d73885dd0f021cb5392681c028c46bb4d8f9d7c6f26470d370ef294c37403
3
+ size 988
checkpoint-62180/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a68c7ce6f2da248c2d4d02379e75e3737024720f536eca469d52619b1f56956f
3
+ size 1064
checkpoint-62180/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
checkpoint-62180/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-62180/tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": false,
15
+ "eos_token": "<|endoftext|>",
16
+ "extra_special_tokens": {},
17
+ "model_max_length": 1024,
18
+ "pad_token": "<|endoftext|>",
19
+ "tokenizer_class": "GPT2Tokenizer",
20
+ "unk_token": "<|endoftext|>"
21
+ }
checkpoint-62180/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-62180/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db0949917c5ba886e7bc4d4f88a5d1ae410b72f4b7845b4e5c992caf95bee997
3
+ size 5240
checkpoint-62180/vocab.json ADDED
The diff for this file is too large to render. See raw diff