Upload tokenizer
Browse files- .gitattributes +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +0 -4
.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
|
@@ -35,12 +35,8 @@
|
|
| 35 |
"clean_up_tokenization_spaces": false,
|
| 36 |
"eos_token": "<|endoftext|>",
|
| 37 |
"errors": "replace",
|
| 38 |
-
"max_length": 2986,
|
| 39 |
"model_max_length": 32768,
|
| 40 |
-
"pad_to_multiple_of": null,
|
| 41 |
"pad_token": "<|im_start|>",
|
| 42 |
-
"pad_token_type_id": 0,
|
| 43 |
-
"padding_side": "left",
|
| 44 |
"split_special_tokens": false,
|
| 45 |
"tokenizer_class": "Qwen2Tokenizer",
|
| 46 |
"unk_token": null
|
|
|
|
| 35 |
"clean_up_tokenization_spaces": false,
|
| 36 |
"eos_token": "<|endoftext|>",
|
| 37 |
"errors": "replace",
|
|
|
|
| 38 |
"model_max_length": 32768,
|
|
|
|
| 39 |
"pad_token": "<|im_start|>",
|
|
|
|
|
|
|
| 40 |
"split_special_tokens": false,
|
| 41 |
"tokenizer_class": "Qwen2Tokenizer",
|
| 42 |
"unk_token": null
|