salmankhanpm commited on
Commit
92f98fa
·
verified ·
1 Parent(s): a8678ef

Upload tokenizer_config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +27 -0
tokenizer_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "additional_special_tokens": {
6
+ },
7
+ "backend": "tokenizers",
8
+ "bos_token": "<s>",
9
+ "clean_up_tokenization_spaces": false,
10
+ "eos_token": "</s>",
11
+ "eot_token": "▁<EOT>",
12
+ "extra_special_tokens": {},
13
+ "fill_token": "<FILL_ME>",
14
+ "is_local": false,
15
+ "legacy": null,
16
+ "middle_token": "▁<MID>",
17
+ "model_max_length": 16384,
18
+ "pad_token": "<unk>",
19
+ "padding_side": "left",
20
+ "prefix_token": "▁<PRE>",
21
+ "sp_model_kwargs": {},
22
+ "suffix_token": "▁<SUF>",
23
+ "tokenizer_class": "CodeLlamaTokenizer",
24
+ "unk_token": "<unk>",
25
+ "use_default_system_prompt": false,
26
+ "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content | trim + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content | trim + ' ' + eos_token }}{% endif %}{% endfor %}"
27
+ }