Roaoch commited on
Commit
fb06de1
1 Parent(s): 938b506

Upload folder using huggingface_hub

Browse files
config.json CHANGED
@@ -5,26 +5,18 @@
5
  "GPT2LMHeadModel"
6
  ],
7
  "attn_pdrop": 0.1,
8
- "bos_token_id": 1,
9
  "embd_pdrop": 0.1,
10
- "eos_token_id": 2,
11
- "gradient_checkpointing": false,
12
- "id2label": {
13
- "0": "LABEL_0"
14
- },
15
  "initializer_range": 0.02,
16
- "label2id": {
17
- "LABEL_0": 0
18
- },
19
  "layer_norm_epsilon": 1e-05,
20
  "model_type": "gpt2",
21
- "n_ctx": 2048,
22
  "n_embd": 768,
23
  "n_head": 12,
24
  "n_inner": null,
25
  "n_layer": 12,
26
- "n_positions": 2048,
27
- "pad_token_id": 0,
28
  "reorder_and_upcast_attn": false,
29
  "resid_pdrop": 0.1,
30
  "scale_attn_by_inverse_layer_idx": false,
@@ -34,8 +26,14 @@
34
  "summary_proj_to_labels": true,
35
  "summary_type": "cls_index",
36
  "summary_use_proj": true,
 
 
 
 
 
 
37
  "torch_dtype": "float32",
38
  "transformers_version": "4.41.2",
39
  "use_cache": true,
40
- "vocab_size": 50264
41
  }
 
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": 1024,
 
20
  "reorder_and_upcast_attn": false,
21
  "resid_pdrop": 0.1,
22
  "scale_attn_by_inverse_layer_idx": false,
 
26
  "summary_proj_to_labels": true,
27
  "summary_type": "cls_index",
28
  "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50
33
+ }
34
+ },
35
  "torch_dtype": "float32",
36
  "transformers_version": "4.41.2",
37
  "use_cache": true,
38
+ "vocab_size": 50257
39
  }
generation_config.json CHANGED
@@ -1,7 +1,6 @@
1
  {
2
  "_from_model_config": true,
3
- "bos_token_id": 1,
4
- "eos_token_id": 2,
5
- "pad_token_id": 0,
6
  "transformers_version": "4.41.2"
7
  }
 
1
  {
2
  "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
 
5
  "transformers_version": "4.41.2"
6
  }
merges.txt CHANGED
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:b9dbe459fae6022f2ffbea330c9d2a0e0eb0a4555a36726e9097dbbe9a5c5c2c
3
- size 500941440
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9c92d5a48cdafca66aa66f12a40ad0c448f557afdd53e5ce9ed2a1aa1ce6131
3
+ size 497777468
special_tokens_map.json CHANGED
@@ -1,28 +1,27 @@
1
  {
2
  "bos_token": {
3
- "content": "<s>",
4
  "lstrip": false,
5
  "normalized": true,
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
  "eos_token": {
10
- "content": "</s>",
11
  "lstrip": false,
12
  "normalized": true,
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
- "mask_token": {
17
- "content": "<mask>",
18
  "lstrip": false,
19
- "normalized": false,
20
  "rstrip": false,
21
  "single_word": false
22
  },
23
- "pad_token": "</s>",
24
  "unk_token": {
25
- "content": "<unk>",
26
  "lstrip": false,
27
  "normalized": true,
28
  "rstrip": false,
 
1
  {
2
  "bos_token": {
3
+ "content": "<|endoftext|>",
4
  "lstrip": false,
5
  "normalized": true,
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
  "eos_token": {
10
+ "content": "<|endoftext|>",
11
  "lstrip": false,
12
  "normalized": true,
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
  "lstrip": false,
19
+ "normalized": true,
20
  "rstrip": false,
21
  "single_word": false
22
  },
 
23
  "unk_token": {
24
+ "content": "<|endoftext|>",
25
  "lstrip": false,
26
  "normalized": true,
27
  "rstrip": false,
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,58 +1,27 @@
1
  {
2
- "add_bos_token": false,
3
  "add_prefix_space": false,
4
  "added_tokens_decoder": {
5
  "0": {
6
- "content": "<pad>",
7
  "lstrip": false,
8
  "normalized": true,
9
  "rstrip": false,
10
  "single_word": false,
11
  "special": true
12
- },
13
- "1": {
14
- "content": "<s>",
15
- "lstrip": false,
16
- "normalized": true,
17
- "rstrip": false,
18
- "single_word": false,
19
- "special": true
20
- },
21
- "2": {
22
- "content": "</s>",
23
- "lstrip": false,
24
- "normalized": true,
25
- "rstrip": false,
26
- "single_word": false,
27
- "special": true
28
- },
29
- "3": {
30
- "content": "<unk>",
31
- "lstrip": false,
32
- "normalized": true,
33
- "rstrip": false,
34
- "single_word": false,
35
- "special": true
36
- },
37
- "4": {
38
- "content": "<mask>",
39
- "lstrip": false,
40
- "normalized": false,
41
- "rstrip": false,
42
- "single_word": false,
43
- "special": true
44
  }
45
  },
46
- "bos_token": "<s>",
47
  "clean_up_tokenization_spaces": true,
48
- "eos_token": "</s>",
49
- "errors": "replace",
50
- "mask_token": "<mask>",
51
- "model_max_length": 2048,
52
- "pad_token": "</s>",
 
53
  "padding_side": "left",
 
54
  "tokenizer_class": "GPT2Tokenizer",
55
- "truncation_side": "left",
56
- "trust_remote_code": false,
57
- "unk_token": "<unk>"
58
  }
 
1
  {
 
2
  "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
  "0": {
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": true,
15
+ "eos_token": "<|endoftext|>",
16
+ "max_length": 1024,
17
+ "model_max_length": 1024,
18
+ "pad_to_multiple_of": null,
19
+ "pad_token": "<|endoftext|>",
20
+ "pad_token_type_id": 0,
21
  "padding_side": "left",
22
+ "stride": 0,
23
  "tokenizer_class": "GPT2Tokenizer",
24
+ "truncation_side": "right",
25
+ "truncation_strategy": "longest_first",
26
+ "unk_token": "<|endoftext|>"
27
  }
vocab.json CHANGED
The diff for this file is too large to render. See raw diff