ai-forever commited on
Commit
29c5693
1 Parent(s): 8a25067

Update tokenizer_config

Browse files
Files changed (3) hide show
  1. config.json +3 -2
  2. special_tokens_map.json +31 -0
  3. tokenizer_config.json +58 -0
config.json CHANGED
@@ -4,9 +4,9 @@
4
  "GPT2LMHeadModel"
5
  ],
6
  "attn_pdrop": 0.1,
7
- "bos_token_id": 50256,
8
  "embd_pdrop": 0.1,
9
- "eos_token_id": 50256,
10
  "gradient_checkpointing": false,
11
  "initializer_range": 0.02,
12
  "layer_norm_epsilon": 1e-05,
@@ -17,6 +17,7 @@
17
  "n_inner": null,
18
  "n_layer": 24,
19
  "n_positions": 2048,
 
20
  "resid_pdrop": 0.1,
21
  "summary_activation": null,
22
  "summary_first_dropout": 0.1,
 
4
  "GPT2LMHeadModel"
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,
11
  "initializer_range": 0.02,
12
  "layer_norm_epsilon": 1e-05,
 
17
  "n_inner": null,
18
  "n_layer": 24,
19
  "n_positions": 2048,
20
+ "pad_token_id": 0,
21
  "resid_pdrop": 0.1,
22
  "summary_activation": null,
23
  "summary_first_dropout": 0.1,
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<mask>",
17
+ "pad_token": {
18
+ "content": "<pad>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "unk_token": {
25
+ "content": "<unk>",
26
+ "lstrip": false,
27
+ "normalized": true,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<pad>",
53
+ "padding_side": "left",
54
+ "tokenizer_class": "GPT2Tokenizer",
55
+ "truncation_side": "left",
56
+ "trust_remote_code": false,
57
+ "unk_token": "<unk>"
58
+ }