Trained with Unsloth
Browse filesUpload model trained with Unsloth 2x faster
- tokenizer_config.json +4 -0
tokenizer_config.json
CHANGED
|
@@ -74,11 +74,15 @@
|
|
| 74 |
"eos_token": "</s>",
|
| 75 |
"extra_ids": 0,
|
| 76 |
"mask_token": "<MASK|LLM-jp>",
|
|
|
|
| 77 |
"model_max_length": 4096,
|
| 78 |
"pad_token": "<PAD|LLM-jp>",
|
| 79 |
"padding_side": "left",
|
| 80 |
"sep_token": "<SEP|LLM-jp>",
|
| 81 |
"sp_model_kwargs": {},
|
|
|
|
| 82 |
"tokenizer_class": "PreTrainedTokenizerFast",
|
|
|
|
|
|
|
| 83 |
"unk_token": "<unk>"
|
| 84 |
}
|
|
|
|
| 74 |
"eos_token": "</s>",
|
| 75 |
"extra_ids": 0,
|
| 76 |
"mask_token": "<MASK|LLM-jp>",
|
| 77 |
+
"max_length": 4096,
|
| 78 |
"model_max_length": 4096,
|
| 79 |
"pad_token": "<PAD|LLM-jp>",
|
| 80 |
"padding_side": "left",
|
| 81 |
"sep_token": "<SEP|LLM-jp>",
|
| 82 |
"sp_model_kwargs": {},
|
| 83 |
+
"stride": 0,
|
| 84 |
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 85 |
+
"truncation_side": "right",
|
| 86 |
+
"truncation_strategy": "longest_first",
|
| 87 |
"unk_token": "<unk>"
|
| 88 |
}
|