Hugging Face's logo

MarkProMaster229
/
InternetLanguage

Safetensors
Russian
gpt2
conversational
internet-language
slang
experimental
research
education
casual
2ch
rugpt
Model card Files
xet
Community
MarkProMaster229 commited on
Commit
6a7a951
·
verified ·
1 Parent(s): 6820768

new

Browse files
Files changed (8) hide show
  1. config.json +3 -3
  2. generation_config.json +5 -3
  3. model.safetensors +1 -1
  4. special_tokens_map.json +7 -1
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +5 -0
  7. training_args.bin +2 -2
  8. vocab.json +0 -0
config.json CHANGED
@@ -5,6 +5,7 @@
5
  ],
6
  "attn_pdrop": 0.1,
7
  "bos_token_id": 1,
 
8
  "embd_pdrop": 0.1,
9
  "eos_token_id": 2,
10
  "gradient_checkpointing": false,
@@ -23,7 +24,7 @@
23
  "n_inner": null,
24
  "n_layer": 12,
25
  "n_positions": 2048,
26
- "pad_token_id": 0,
27
  "reorder_and_upcast_attn": false,
28
  "resid_pdrop": 0.1,
29
  "scale_attn_by_inverse_layer_idx": false,
@@ -33,8 +34,7 @@
33
  "summary_proj_to_labels": true,
34
  "summary_type": "cls_index",
35
  "summary_use_proj": true,
36
- "torch_dtype": "float32",
37
- "transformers_version": "4.52.4",
38
  "use_cache": true,
39
  "vocab_size": 50257
40
  }
 
5
  ],
6
  "attn_pdrop": 0.1,
7
  "bos_token_id": 1,
8
+ "dtype": "float32",
9
  "embd_pdrop": 0.1,
10
  "eos_token_id": 2,
11
  "gradient_checkpointing": false,
 
24
  "n_inner": null,
25
  "n_layer": 12,
26
  "n_positions": 2048,
27
+ "pad_token_id": 2,
28
  "reorder_and_upcast_attn": false,
29
  "resid_pdrop": 0.1,
30
  "scale_attn_by_inverse_layer_idx": false,
 
34
  "summary_proj_to_labels": true,
35
  "summary_type": "cls_index",
36
  "summary_use_proj": true,
37
+ "transformers_version": "4.57.3",
 
38
  "use_cache": true,
39
  "vocab_size": 50257
40
  }
generation_config.json CHANGED
@@ -1,7 +1,9 @@
1
  {
2
  "_from_model_config": true,
3
  "bos_token_id": 1,
4
- "eos_token_id": 2,
5
- "pad_token_id": 0,
6
- "transformers_version": "4.52.4"
 
 
7
  }
 
1
  {
2
  "_from_model_config": true,
3
  "bos_token_id": 1,
4
+ "eos_token_id": [
5
+ 2
6
+ ],
7
+ "pad_token_id": 2,
8
+ "transformers_version": "4.57.3"
9
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c315e975b88b1a4451f38d8fe92965799e8b364c835be4dbdd1762b3823d977c
3
  size 500919936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:941af006c53b04c8b3d79d6a92c9d95357ad1a9d1f0e35a3fe441bd7b3025b7b
3
  size 500919936
special_tokens_map.json CHANGED
@@ -20,7 +20,13 @@
20
  "rstrip": false,
21
  "single_word": false
22
  },
23
- "pad_token": "</s>",
 
 
 
 
 
 
24
  "unk_token": {
25
  "content": "<unk>",
26
  "lstrip": false,
 
20
  "rstrip": false,
21
  "single_word": false
22
  },
23
+ "pad_token": {
24
+ "content": "</s>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
  "unk_token": {
31
  "content": "<unk>",
32
  "lstrip": false,
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -49,11 +49,16 @@
49
  "errors": "replace",
50
  "extra_special_tokens": {},
51
  "mask_token": "<mask>",
 
52
  "model_max_length": 2048,
 
53
  "pad_token": "</s>",
 
54
  "padding_side": "left",
 
55
  "tokenizer_class": "GPT2Tokenizer",
56
  "truncation_side": "left",
 
57
  "trust_remote_code": false,
58
  "unk_token": "<unk>"
59
  }
 
49
  "errors": "replace",
50
  "extra_special_tokens": {},
51
  "mask_token": "<mask>",
52
+ "max_length": 128,
53
  "model_max_length": 2048,
54
+ "pad_to_multiple_of": null,
55
  "pad_token": "</s>",
56
+ "pad_token_type_id": 0,
57
  "padding_side": "left",
58
+ "stride": 0,
59
  "tokenizer_class": "GPT2Tokenizer",
60
  "truncation_side": "left",
61
+ "truncation_strategy": "longest_first",
62
  "trust_remote_code": false,
63
  "unk_token": "<unk>"
64
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:799f468600eb7d15c4e6dadcb31f6a81d66af87e10abcb142c666aa51a0864bd
3
- size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5219e41e4dceacec8a12f41d37a63963f260daaa24f2ceec3aa4813f0f19a9b
3
+ size 5368
vocab.json CHANGED
The diff for this file is too large to render. See raw diff