xiamengzhou commited on
Commit
507d36a
1 Parent(s): 5605941
special_tokens_map.json CHANGED
@@ -13,6 +13,13 @@
13
  "rstrip": false,
14
  "single_word": false
15
  },
 
 
 
 
 
 
 
16
  "unk_token": {
17
  "content": "<unk>",
18
  "lstrip": false,
 
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
+ "pad_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
  "unk_token": {
24
  "content": "<unk>",
25
  "lstrip": false,
tokenizer.json CHANGED
@@ -134,7 +134,6 @@
134
  "end_of_word_suffix": null,
135
  "fuse_unk": true,
136
  "byte_fallback": true,
137
- "ignore_merges": false,
138
  "vocab": {
139
  "<unk>": 0,
140
  "<s>": 1,
 
134
  "end_of_word_suffix": null,
135
  "fuse_unk": true,
136
  "byte_fallback": true,
 
137
  "vocab": {
138
  "<unk>": 0,
139
  "<s>": 1,
tokenizer_config.json CHANGED
@@ -29,12 +29,12 @@
29
  },
30
  "additional_special_tokens": [],
31
  "bos_token": "<s>",
32
- "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
33
  "clean_up_tokenization_spaces": false,
34
  "eos_token": "</s>",
35
  "legacy": true,
36
- "model_max_length": 1000000000000000019884624838656,
37
- "pad_token": null,
38
  "sp_model_kwargs": {},
39
  "spaces_between_special_tokens": false,
40
  "tokenizer_class": "LlamaTokenizer",
 
29
  },
30
  "additional_special_tokens": [],
31
  "bos_token": "<s>",
32
+ "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 %}",
33
  "clean_up_tokenization_spaces": false,
34
  "eos_token": "</s>",
35
  "legacy": true,
36
+ "model_max_length": 2048,
37
+ "pad_token": "</s>",
38
  "sp_model_kwargs": {},
39
  "spaces_between_special_tokens": false,
40
  "tokenizer_class": "LlamaTokenizer",