Text Generation
Transformers
PyTorch
Safetensors
gpt2
conversational
text-generation-inference
Inference Endpoints
timpal0l commited on
Commit
84fa965
1 Parent(s): 5234e8e

Update tokenizer_config.json

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +46 -2
tokenizer_config.json CHANGED
@@ -1,6 +1,50 @@
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "model_max_length": 2048,
 
3
  "padding_side": "left",
 
 
 
4
  "truncation_side": "left",
5
- "chat_template": "{{ eos_token }}{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ 'User: ' + message['content']}}{% else %}{{ 'Bot: ' + message['content']}}{% endif %}{{ message['text'] }}{{ bos_token }}{% endfor %}Bot:"
6
- }
 
1
  {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<pad>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<unk>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<|endoftext|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "bos_token": "<s>",
37
+ "chat_template": "{{ eos_token }}{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ 'User: ' + message['content']}}{% else %}{{ 'Bot: ' + message['content']}}{% endif %}{{ message['text'] }}{{ bos_token }}{% endfor %}Bot:",
38
+ "clean_up_tokenization_spaces": true,
39
+ "do_lower_case": false,
40
+ "eos_token": "<|endoftext|>",
41
+ "keep_accents": false,
42
  "model_max_length": 2048,
43
+ "pad_token": "<pad>",
44
  "padding_side": "left",
45
+ "remove_space": false,
46
+ "sp_model_kwargs": {},
47
+ "tokenizer_class": "GPTSw3Tokenizer",
48
  "truncation_side": "left",
49
+ "unk_token": "<unk>"
50
+ }