Update tokenizer_config.json
Browse files- tokenizer_config.json +33 -33
tokenizer_config.json
CHANGED
|
@@ -1,34 +1,34 @@
|
|
| 1 |
{
|
| 2 |
-
"add_bos_token": true,
|
| 3 |
-
"add_eos_token": false,
|
| 4 |
-
"model_max_length":
|
| 5 |
-
"pad_token": null,
|
| 6 |
-
"sp_model_kwargs": {},
|
| 7 |
-
"tokenizer_class": "LlamaTokenizer",
|
| 8 |
-
"clean_up_tokenization_spaces": false,
|
| 9 |
-
"bos_token": {
|
| 10 |
-
"__type": "AddedToken",
|
| 11 |
-
"content": "<s>",
|
| 12 |
-
"lstrip": false,
|
| 13 |
-
"normalized": true,
|
| 14 |
-
"rstrip": false,
|
| 15 |
-
"single_word": false
|
| 16 |
-
},
|
| 17 |
-
"eos_token": {
|
| 18 |
-
"__type": "AddedToken",
|
| 19 |
-
"content": "</s>",
|
| 20 |
-
"lstrip": false,
|
| 21 |
-
"normalized": true,
|
| 22 |
-
"rstrip": false,
|
| 23 |
-
"single_word": false
|
| 24 |
-
},
|
| 25 |
-
"unk_token": {
|
| 26 |
-
"__type": "AddedToken",
|
| 27 |
-
"content": "<unk>",
|
| 28 |
-
"lstrip": false,
|
| 29 |
-
"normalized": true,
|
| 30 |
-
"rstrip": false,
|
| 31 |
-
"single_word": false
|
| 32 |
-
},
|
| 33 |
-
"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 %}"
|
| 34 |
-
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"model_max_length": 4096,
|
| 5 |
+
"pad_token": null,
|
| 6 |
+
"sp_model_kwargs": {},
|
| 7 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 8 |
+
"clean_up_tokenization_spaces": false,
|
| 9 |
+
"bos_token": {
|
| 10 |
+
"__type": "AddedToken",
|
| 11 |
+
"content": "<s>",
|
| 12 |
+
"lstrip": false,
|
| 13 |
+
"normalized": true,
|
| 14 |
+
"rstrip": false,
|
| 15 |
+
"single_word": false
|
| 16 |
+
},
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"__type": "AddedToken",
|
| 19 |
+
"content": "</s>",
|
| 20 |
+
"lstrip": false,
|
| 21 |
+
"normalized": true,
|
| 22 |
+
"rstrip": false,
|
| 23 |
+
"single_word": false
|
| 24 |
+
},
|
| 25 |
+
"unk_token": {
|
| 26 |
+
"__type": "AddedToken",
|
| 27 |
+
"content": "<unk>",
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"normalized": true,
|
| 30 |
+
"rstrip": false,
|
| 31 |
+
"single_word": false
|
| 32 |
+
},
|
| 33 |
+
"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 %}"
|
| 34 |
+
}
|