Hugging Face's logo

x2-world
/
recipe-bert

Safetensors
gpt2
Model card Files
xet
Community
x2-world commited on
Commit
8af2afc
·
verified ·
1 Parent(s): 8a658e0

Upload causal LM outputs

Browse files
Files changed (9) hide show
  1. config.json +31 -18
  2. generation_config.json +9 -0
  3. merges.txt +0 -0
  4. model.safetensors +2 -2
  5. special_tokens_map.json +4 -5
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +10 -45
  8. training_args.bin +1 -1
  9. vocab.json +0 -0
config.json CHANGED
@@ -1,26 +1,39 @@
1
  {
 
2
  "architectures": [
3
- "BertForSequenceClassification"
4
  ],
5
- "attention_probs_dropout_prob": 0.1,
6
- "classifier_dropout": null,
7
  "dtype": "float32",
8
- "gradient_checkpointing": false,
9
- "hidden_act": "gelu",
10
- "hidden_dropout_prob": 0.1,
11
- "hidden_size": 768,
12
  "initializer_range": 0.02,
13
- "intermediate_size": 3072,
14
- "layer_norm_eps": 1e-12,
15
- "max_position_embeddings": 512,
16
- "model_type": "bert",
17
- "num_attention_heads": 12,
18
- "num_hidden_layers": 12,
19
- "pad_token_id": 0,
20
- "position_embedding_type": "absolute",
21
- "problem_type": "single_label_classification",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
22
  "transformers_version": "4.56.0",
23
- "type_vocab_size": 2,
24
  "use_cache": true,
25
- "vocab_size": 30522
26
  }
 
1
  {
2
+ "activation_function": "gelu_new",
3
  "architectures": [
4
+ "GPT2LMHeadModel"
5
  ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 50256,
8
  "dtype": "float32",
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": 1024,
20
+ "pad_token_id": 50256,
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
  "transformers_version": "4.56.0",
 
37
  "use_cache": true,
38
+ "vocab_size": 50257
39
  }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": [
5
+ 50256
6
+ ],
7
+ "pad_token_id": 50256,
8
+ "transformers_version": "4.56.0"
9
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7fdc1a961e70a3cac2a652f812db2788819790fb33fc9e6257f4ee92facde732
3
- size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1383d628c83f3fad29f1a4f87586e460d9f443f475869da362a963853e78890
3
+ size 497774208
special_tokens_map.json CHANGED
@@ -1,7 +1,6 @@
1
  {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
7
  }
 
1
  {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
 
6
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,56 +1,21 @@
1
  {
 
2
  "added_tokens_decoder": {
3
- "0": {
4
- "content": "[PAD]",
5
  "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false,
9
- "special": true
10
- },
11
- "100": {
12
- "content": "[UNK]",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false,
17
- "special": true
18
- },
19
- "101": {
20
- "content": "[CLS]",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "102": {
28
- "content": "[SEP]",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- },
35
- "103": {
36
- "content": "[MASK]",
37
- "lstrip": false,
38
- "normalized": false,
39
  "rstrip": false,
40
  "single_word": false,
41
  "special": true
42
  }
43
  },
 
44
  "clean_up_tokenization_spaces": false,
45
- "cls_token": "[CLS]",
46
- "do_lower_case": true,
47
  "extra_special_tokens": {},
48
- "mask_token": "[MASK]",
49
- "model_max_length": 512,
50
- "pad_token": "[PAD]",
51
- "sep_token": "[SEP]",
52
- "strip_accents": null,
53
- "tokenize_chinese_chars": true,
54
- "tokenizer_class": "BertTokenizer",
55
- "unk_token": "[UNK]"
56
  }
 
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
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:95793db67d5c9adaf7b99796888b5288b0277549a7fc48713a1cad9011a018fc
3
  size 5713
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc3828de2d467dbbe30ade60e11e159b270d93af1b39e96c09e75e2d85edf715
3
  size 5713
vocab.json ADDED
The diff for this file is too large to render. See raw diff