Commit
•
22b03da
1
Parent(s):
d20cab0
Upload tokenizer
Browse files- tokenizer.json +0 -0
- tokenizer_config.json +2 -2
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -33,11 +33,11 @@
|
|
| 33 |
"bos_token": "<s>",
|
| 34 |
"clean_up_tokenization_spaces": false,
|
| 35 |
"eos_token": "</s>",
|
| 36 |
-
"legacy":
|
| 37 |
"model_max_length": 1000000000000000019884624838656,
|
| 38 |
"pad_token": "</s>",
|
|
|
|
| 39 |
"sp_model_kwargs": {},
|
| 40 |
-
"spaces_between_special_tokens": false,
|
| 41 |
"tokenizer_class": "LlamaTokenizer",
|
| 42 |
"unk_token": "<unk>",
|
| 43 |
"use_default_system_prompt": true
|
|
|
|
| 33 |
"bos_token": "<s>",
|
| 34 |
"clean_up_tokenization_spaces": false,
|
| 35 |
"eos_token": "</s>",
|
| 36 |
+
"legacy": false,
|
| 37 |
"model_max_length": 1000000000000000019884624838656,
|
| 38 |
"pad_token": "</s>",
|
| 39 |
+
"padding_side": "right",
|
| 40 |
"sp_model_kwargs": {},
|
|
|
|
| 41 |
"tokenizer_class": "LlamaTokenizer",
|
| 42 |
"unk_token": "<unk>",
|
| 43 |
"use_default_system_prompt": true
|