Update tokenizer_config.json (#2)
Browse files- Update tokenizer_config.json (751b76f98afbb8e9a26e5d020db64288cd857145)
Co-authored-by: Chujie Zheng <chujiezheng@users.noreply.huggingface.co>
- tokenizer_config.json +36 -1
tokenizer_config.json
CHANGED
|
@@ -1 +1,36 @@
|
|
| 1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token":true,
|
| 3 |
+
"add_eos_token":false,
|
| 4 |
+
"model_max_length":2048,
|
| 5 |
+
"pad_token":null,
|
| 6 |
+
"sp_model_kwargs":{
|
| 7 |
+
|
| 8 |
+
},
|
| 9 |
+
"tokenizer_class":"LlamaTokenizer",
|
| 10 |
+
"clean_up_tokenization_spaces":false,
|
| 11 |
+
"bos_token":{
|
| 12 |
+
"__type":"AddedToken",
|
| 13 |
+
"content":"<s>",
|
| 14 |
+
"lstrip":false,
|
| 15 |
+
"normalized":true,
|
| 16 |
+
"rstrip":false,
|
| 17 |
+
"single_word":false
|
| 18 |
+
},
|
| 19 |
+
"eos_token":{
|
| 20 |
+
"__type":"AddedToken",
|
| 21 |
+
"content":"</s>",
|
| 22 |
+
"lstrip":false,
|
| 23 |
+
"normalized":true,
|
| 24 |
+
"rstrip":false,
|
| 25 |
+
"single_word":false
|
| 26 |
+
},
|
| 27 |
+
"unk_token":{
|
| 28 |
+
"__type":"AddedToken",
|
| 29 |
+
"content":"<unk>",
|
| 30 |
+
"lstrip":false,
|
| 31 |
+
"normalized":true,
|
| 32 |
+
"rstrip":false,
|
| 33 |
+
"single_word":false
|
| 34 |
+
},
|
| 35 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] }}\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 %}"
|
| 36 |
+
}
|