Buckets:
| { | |
| "backend": "tokenizers", | |
| "clean_up_tokenization_spaces": false, | |
| "do_lower_case": false, | |
| "eos_token": "<|endoftext|>", | |
| "extra_special_tokens": [ | |
| "<|endoftext|>", | |
| "[MASK]", | |
| "[gMASK]", | |
| "[sMASK]", | |
| "<sop>", | |
| "<eop>", | |
| "<|system|>", | |
| "<|user|>", | |
| "<|assistant|>", | |
| "<|observation|>", | |
| "<|begin_of_image|>", | |
| "<|end_of_image|>", | |
| "<|begin_of_video|>", | |
| "<|end_of_video|>", | |
| "<|begin_of_audio|>", | |
| "<|end_of_audio|>", | |
| "<|begin_of_transcription|>", | |
| "<|end_of_transcription|>" | |
| ], | |
| "is_local": true, | |
| "local_files_only": false, | |
| "model_max_length": 1048576, | |
| "model_specific_special_tokens": {}, | |
| "pad_token": "<|endoftext|>", | |
| "padding_side": "left", | |
| "remove_space": false, | |
| "tokenizer_class": "TokenizersBackend" | |
| } | |
Xet Storage Details
- Size:
- 790 Bytes
- Xet hash:
- 28a3988c35b4702ceafae4e5370fa27b02d5a8336f54b660b2691d9974d7d947
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.