Upload tokenizer
Browse files- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +5 -3
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
tokenizer_config.json
CHANGED
|
@@ -28,11 +28,13 @@
|
|
| 28 |
}
|
| 29 |
},
|
| 30 |
"bos_token": "<s>",
|
| 31 |
-
"clean_up_tokenization_spaces":
|
| 32 |
"eos_token": "</s>",
|
| 33 |
-
"legacy":
|
| 34 |
-
"model_max_length":
|
| 35 |
"pad_token": "<unk>",
|
|
|
|
|
|
|
| 36 |
"tokenizer_class": "LlamaTokenizer",
|
| 37 |
"unk_token": "<unk>",
|
| 38 |
"use_default_system_prompt": false
|
|
|
|
| 28 |
}
|
| 29 |
},
|
| 30 |
"bos_token": "<s>",
|
| 31 |
+
"clean_up_tokenization_spaces": false,
|
| 32 |
"eos_token": "</s>",
|
| 33 |
+
"legacy": false,
|
| 34 |
+
"model_max_length": 2048,
|
| 35 |
"pad_token": "<unk>",
|
| 36 |
+
"padding_side": "right",
|
| 37 |
+
"sp_model_kwargs": {},
|
| 38 |
"tokenizer_class": "LlamaTokenizer",
|
| 39 |
"unk_token": "<unk>",
|
| 40 |
"use_default_system_prompt": false
|