Upload tokenizer
Browse files- tokenizer.json +2 -2
- tokenizer_config.json +7 -0
tokenizer.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
+
size 11422654
|
tokenizer_config.json
CHANGED
|
@@ -231,9 +231,16 @@
|
|
| 231 |
"eos_token": "<|im_end|>",
|
| 232 |
"errors": "replace",
|
| 233 |
"extra_special_tokens": {},
|
|
|
|
| 234 |
"model_max_length": 131072,
|
|
|
|
| 235 |
"pad_token": "<|endoftext|>",
|
|
|
|
|
|
|
| 236 |
"split_special_tokens": false,
|
|
|
|
| 237 |
"tokenizer_class": "Qwen2Tokenizer",
|
|
|
|
|
|
|
| 238 |
"unk_token": null
|
| 239 |
}
|
|
|
|
| 231 |
"eos_token": "<|im_end|>",
|
| 232 |
"errors": "replace",
|
| 233 |
"extra_special_tokens": {},
|
| 234 |
+
"max_length": 512,
|
| 235 |
"model_max_length": 131072,
|
| 236 |
+
"pad_to_multiple_of": null,
|
| 237 |
"pad_token": "<|endoftext|>",
|
| 238 |
+
"pad_token_type_id": 0,
|
| 239 |
+
"padding_side": "right",
|
| 240 |
"split_special_tokens": false,
|
| 241 |
+
"stride": 0,
|
| 242 |
"tokenizer_class": "Qwen2Tokenizer",
|
| 243 |
+
"truncation_side": "right",
|
| 244 |
+
"truncation_strategy": "longest_first",
|
| 245 |
"unk_token": null
|
| 246 |
}
|