Upload tokenizer
Browse files- tokenizer.json +0 -0
- tokenizer_config.json +18 -0
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": null,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<|start|>",
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"cls_token": "<|cls|>",
|
| 7 |
+
"eos_token": "<|end|>",
|
| 8 |
+
"extra_special_tokens": [],
|
| 9 |
+
"is_local": true,
|
| 10 |
+
"mask_token": "<|mask|>",
|
| 11 |
+
"model_max_length": 1024,
|
| 12 |
+
"model_type": "modernbert",
|
| 13 |
+
"pad_token": "<|pad|>",
|
| 14 |
+
"sep_token": "<|sep|>",
|
| 15 |
+
"tokenizer_class": "TokenizersBackend",
|
| 16 |
+
"unk_token": "<|unk|>",
|
| 17 |
+
"vocab_size": 32767
|
| 18 |
+
}
|