Upload tokenizer
Browse files- .gitattributes +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -2073,6 +2073,7 @@
|
|
| 2073 |
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 2074 |
"clean_up_tokenization_spaces": true,
|
| 2075 |
"eos_token": "<|im_end|>",
|
|
|
|
| 2076 |
"model_input_names": [
|
| 2077 |
"input_ids",
|
| 2078 |
"attention_mask"
|
|
|
|
| 2073 |
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 2074 |
"clean_up_tokenization_spaces": true,
|
| 2075 |
"eos_token": "<|im_end|>",
|
| 2076 |
+
"extra_special_tokens": {},
|
| 2077 |
"model_input_names": [
|
| 2078 |
"input_ids",
|
| 2079 |
"attention_mask"
|