rishiraj commited on
Commit
7e5076e
1 Parent(s): 0091493

Upload tokenizer

Browse files
Files changed (2) hide show
  1. special_tokens_map.json +0 -1
  2. tokenizer_config.json +2 -3
special_tokens_map.json CHANGED
@@ -13,7 +13,6 @@
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
- "pad_token": "</s>",
17
  "unk_token": {
18
  "content": "<unk>",
19
  "lstrip": false,
 
13
  "rstrip": false,
14
  "single_word": false
15
  },
 
16
  "unk_token": {
17
  "content": "<unk>",
18
  "lstrip": false,
tokenizer_config.json CHANGED
@@ -28,12 +28,11 @@
28
  }
29
  },
30
  "bos_token": "<s>",
31
- "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
32
  "clean_up_tokenization_spaces": false,
33
  "eos_token": "</s>",
34
  "legacy": true,
35
- "model_max_length": 2048,
36
- "pad_token": "</s>",
37
  "sp_model_kwargs": {},
38
  "spaces_between_special_tokens": false,
39
  "tokenizer_class": "LlamaTokenizer",
 
28
  }
29
  },
30
  "bos_token": "<s>",
 
31
  "clean_up_tokenization_spaces": false,
32
  "eos_token": "</s>",
33
  "legacy": true,
34
+ "model_max_length": 1000000000000000019884624838656,
35
+ "pad_token": null,
36
  "sp_model_kwargs": {},
37
  "spaces_between_special_tokens": false,
38
  "tokenizer_class": "LlamaTokenizer",