Hugging Face's logo

Th3BossC
/
DialoGPT-medium-AICLUB_NITC

Text Generation
Transformers
PyTorch
gpt2
text-generation-inference
Inference Endpoints
Model card Files Community
1
Th3BossC commited on
Commit
c12384a
·
1 Parent(s): 58c1a19

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +21 -3
  2. tokenizer.json +1 -1
  3. tokenizer_config.json +27 -3
special_tokens_map.json CHANGED
@@ -1,6 +1,24 @@
1
  {
2
- "bos_token": "<|endoftext|>",
3
- "eos_token": "<|endoftext|>",
 
 
 
 
 
 
 
 
 
 
 
 
4
  "pad_token": "<|endoftext|>",
5
- "unk_token": "<|endoftext|>"
 
 
 
 
 
 
6
  }
 
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": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
  }
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
@@ -1,9 +1,33 @@
1
  {
 
2
  "add_prefix_space": false,
3
- "bos_token": "<|endoftext|>",
 
 
 
 
 
 
 
4
  "clean_up_tokenization_spaces": true,
5
- "eos_token": "<|endoftext|>",
 
 
 
 
 
 
 
 
6
  "model_max_length": 1024,
 
7
  "tokenizer_class": "GPT2Tokenizer",
8
- "unk_token": "<|endoftext|>"
 
 
 
 
 
 
 
9
  }
 
1
  {
2
+ "add_bos_token": false,
3
  "add_prefix_space": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
  "clean_up_tokenization_spaces": true,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "<|endoftext|>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "errors": "replace",
22
  "model_max_length": 1024,
23
+ "pad_token": null,
24
  "tokenizer_class": "GPT2Tokenizer",
25
+ "unk_token": {
26
+ "__type": "AddedToken",
27
+ "content": "<|endoftext|>",
28
+ "lstrip": false,
29
+ "normalized": true,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
  }