timhoek commited on
Commit
3f60323
·
verified ·
1 Parent(s): c385810

Upload tokenizer

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +1 -4
tokenizer_config.json CHANGED
@@ -1,7 +1,6 @@
1
  {
2
  "add_bos_token": true,
3
  "add_eos_token": false,
4
- "add_prefix_space": null,
5
  "added_tokens_decoder": {
6
  "0": {
7
  "content": "<unk>",
@@ -38,11 +37,9 @@
38
  },
39
  "additional_special_tokens": [],
40
  "bos_token": "<s>",
41
- "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
42
  "clean_up_tokenization_spaces": false,
43
  "eos_token": "<|im_end|>",
44
- "legacy": true,
45
- "model_max_length": 2048,
46
  "pad_token": "<|im_end|>",
47
  "sp_model_kwargs": {},
48
  "spaces_between_special_tokens": false,
 
1
  {
2
  "add_bos_token": true,
3
  "add_eos_token": false,
 
4
  "added_tokens_decoder": {
5
  "0": {
6
  "content": "<unk>",
 
37
  },
38
  "additional_special_tokens": [],
39
  "bos_token": "<s>",
 
40
  "clean_up_tokenization_spaces": false,
41
  "eos_token": "<|im_end|>",
42
+ "model_max_length": 1000000000000000019884624838656,
 
43
  "pad_token": "<|im_end|>",
44
  "sp_model_kwargs": {},
45
  "spaces_between_special_tokens": false,