Hugging Face's logo

trl-internal-testing
/
dummy-GPT2-correct-vocab

Text Generation
Transformers
Safetensors
gpt2
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
1
qgallouedec HF staff commited on
Commit
f1469fb
•
1 Parent(s): 9ca7622

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +3 -21
  2. tokenizer.json +1 -1
  3. tokenizer_config.json +2 -2
special_tokens_map.json CHANGED
@@ -1,23 +1,5 @@
1
  {
2
- "bos_token": {
3
- "content": "<|endoftext|>",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "eos_token": {
10
- "content": "<|endoftext|>",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "unk_token": {
17
- "content": "<|endoftext|>",
18
- "lstrip": false,
19
- "normalized": false,
20
- "rstrip": false,
21
- "single_word": false
22
- }
23
  }
 
1
  {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "unk_token": "<|endoftext|>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  }
tokenizer.json CHANGED
@@ -9,7 +9,7 @@
9
  "single_word": false,
10
  "lstrip": false,
11
  "rstrip": false,
12
- "normalized": false,
13
  "special": true
14
  }
15
  ],
 
9
  "single_word": false,
10
  "lstrip": false,
11
  "rstrip": false,
12
+ "normalized": true,
13
  "special": true
14
  }
15
  ],
tokenizer_config.json CHANGED
@@ -4,14 +4,14 @@
4
  "50256": {
5
  "content": "<|endoftext|>",
6
  "lstrip": false,
7
- "normalized": false,
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
  "model_max_length": 1024,
17
  "tokenizer_class": "GPT2Tokenizer",
 
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": true,
15
  "eos_token": "<|endoftext|>",
16
  "model_max_length": 1024,
17
  "tokenizer_class": "GPT2Tokenizer",