Hugging Face's logo

israel
/
AmhWordPieceTokenizer

Amharic
Amharic
Word Piece Tokenizer
Tokenizer
Model card Files Community
Israel Abebe Azime commited on
Commit
c802e5d
•
1 Parent(s): 9f5c288

add tokenizer

Browse files
Files changed (5) hide show
  1. .gitattributes +1 -0
  2. special_tokens_map.json +5 -3
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +9 -8
  5. vocab.txt +0 -0
.gitattributes CHANGED
@@ -30,3 +30,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
30
  *.zip filter=lfs diff=lfs merge=lfs -text
31
  *.zst filter=lfs diff=lfs merge=lfs -text
32
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
30
  *.zip filter=lfs diff=lfs merge=lfs -text
31
  *.zst filter=lfs diff=lfs merge=lfs -text
32
  *tfevents* filter=lfs diff=lfs merge=lfs -text
33
+ vocab.txt filter=lfs diff=lfs merge=lfs -text
special_tokens_map.json CHANGED
@@ -1,5 +1,7 @@
1
  {
2
- "bos_token": "<|endoftext|>",
3
- "eos_token": "<|endoftext|>",
4
- "unk_token": "<|endoftext|>"
 
 
5
  }
 
1
  {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,10 +1,11 @@
1
  {
2
- "add_prefix_space": false,
3
- "bos_token": "<|endoftext|>",
4
- "eos_token": "<|endoftext|>",
5
- "model_max_length": 1024,
6
- "name_or_path": "gpt2",
7
- "special_tokens_map_file": null,
8
- "tokenizer_class": "GPT2Tokenizer",
9
- "unk_token": "<|endoftext|>"
 
10
  }
 
1
  {
2
+ "cls_token": "[CLS]",
3
+ "do_lower_case": true,
4
+ "mask_token": "[MASK]",
5
+ "pad_token": "[PAD]",
6
+ "sep_token": "[SEP]",
7
+ "strip_accents": null,
8
+ "tokenize_chinese_chars": true,
9
+ "tokenizer_class": "BertTokenizer",
10
+ "unk_token": "[UNK]"
11
  }
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff