Upload tokenizer
Browse files- tokenizer_config.json +4 -0
tokenizer_config.json
CHANGED
|
@@ -339,11 +339,15 @@
|
|
| 339 |
"clean_up_tokenization_spaces": false,
|
| 340 |
"eos_token": "<|endoftext|>",
|
| 341 |
"legacy": false,
|
|
|
|
| 342 |
"model_max_length": 4096,
|
| 343 |
"pad_token": "<unk>",
|
| 344 |
"padding_side": "right",
|
| 345 |
"sp_model_kwargs": {},
|
|
|
|
| 346 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
|
|
|
| 347 |
"unk_token": "<unk>",
|
| 348 |
"use_default_system_prompt": false
|
| 349 |
}
|
|
|
|
| 339 |
"clean_up_tokenization_spaces": false,
|
| 340 |
"eos_token": "<|endoftext|>",
|
| 341 |
"legacy": false,
|
| 342 |
+
"max_length": 2048,
|
| 343 |
"model_max_length": 4096,
|
| 344 |
"pad_token": "<unk>",
|
| 345 |
"padding_side": "right",
|
| 346 |
"sp_model_kwargs": {},
|
| 347 |
+
"stride": 0,
|
| 348 |
"tokenizer_class": "LlamaTokenizer",
|
| 349 |
+
"truncation_side": "right",
|
| 350 |
+
"truncation_strategy": "longest_first",
|
| 351 |
"unk_token": "<unk>",
|
| 352 |
"use_default_system_prompt": false
|
| 353 |
}
|