mamiksik commited on
Commit
e3faefa
1 Parent(s): cf7f2e5

End of training glittering-fireworks-202

Browse files
merges.txt CHANGED
@@ -1,4 +1,4 @@
1
- #version: 0.2
2
  Ġ t
3
  Ġ a
4
  h e
 
1
+ #version: 0.2 - Trained by `huggingface/tokenizers`
2
  Ġ t
3
  Ġ a
4
  h e
special_tokens_map.json CHANGED
@@ -2,7 +2,13 @@
2
  "bos_token": "<s>",
3
  "cls_token": "<s>",
4
  "eos_token": "</s>",
5
- "mask_token": "<mask>",
 
 
 
 
 
 
6
  "pad_token": "<pad>",
7
  "sep_token": "</s>",
8
  "unk_token": "<unk>"
 
2
  "bos_token": "<s>",
3
  "cls_token": "<s>",
4
  "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
  "pad_token": "<pad>",
13
  "sep_token": "</s>",
14
  "unk_token": "<unk>"
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -51,8 +51,9 @@
51
  "rstrip": false,
52
  "single_word": false
53
  },
54
- "special_tokens_map_file": "/Users/martin/.cache/huggingface/hub/models--microsoft--codebert-base-mlm/snapshots/71b41964e82666ecdb8c72b11d8a02395e6fcda5/special_tokens_map.json",
55
  "tokenizer_class": "RobertaTokenizer",
 
56
  "unk_token": {
57
  "__type": "AddedToken",
58
  "content": "<unk>",
@@ -60,5 +61,6 @@
60
  "normalized": true,
61
  "rstrip": false,
62
  "single_word": false
63
- }
 
64
  }
 
51
  "rstrip": false,
52
  "single_word": false
53
  },
54
+ "special_tokens_map_file": "/home/s2498103/.cache/huggingface/hub/models--microsoft--codebert-base-mlm/snapshots/71b41964e82666ecdb8c72b11d8a02395e6fcda5/special_tokens_map.json",
55
  "tokenizer_class": "RobertaTokenizer",
56
+ "trim_offsets": true,
57
  "unk_token": {
58
  "__type": "AddedToken",
59
  "content": "<unk>",
 
61
  "normalized": true,
62
  "rstrip": false,
63
  "single_word": false
64
+ },
65
+ "use_fast": true
66
  }
vocab.json CHANGED
The diff for this file is too large to render. See raw diff