| { |
| "add_bos_token": false, |
| "add_prefix_space": false, |
| "added_tokens_decoder": { |
| "248044": { |
| "content": "<|endoftext|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "248045": { |
| "content": "<|im_start|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "248046": { |
| "content": "<|im_end|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "248047": { |
| "content": "<|object_ref_start|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "248048": { |
| "content": "<|object_ref_end|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "248049": { |
| "content": "<|box_start|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "248050": { |
| "content": "<|box_end|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "248051": { |
| "content": "<|quad_start|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "248052": { |
| "content": "<|quad_end|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "248053": { |
| "content": "<|vision_start|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "248054": { |
| "content": "<|vision_end|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "248055": { |
| "content": "<|vision_pad|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "248056": { |
| "content": "<|image_pad|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "248057": { |
| "content": "<|video_pad|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "248058": { |
| "content": "<tool_call>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "248059": { |
| "content": "</tool_call>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "248060": { |
| "content": "<|fim_prefix|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "248061": { |
| "content": "<|fim_middle|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "248062": { |
| "content": "<|fim_suffix|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "248063": { |
| "content": "<|fim_pad|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "248064": { |
| "content": "<|repo_name|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "248065": { |
| "content": "<|file_sep|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "248066": { |
| "content": "<tool_response>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "248067": { |
| "content": "</tool_response>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "248068": { |
| "content": "<think>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "248069": { |
| "content": "</think>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "248070": { |
| "content": "<|audio_start|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "248071": { |
| "content": "<|audio_end|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "248072": { |
| "content": "<tts_pad>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "248073": { |
| "content": "<tts_text_bos>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "248074": { |
| "content": "<tts_text_eod>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "248075": { |
| "content": "<tts_text_bos_single>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "248076": { |
| "content": "<|audio_pad|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "248077": { |
| "content": "<IMG_CONTEXT>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "248078": { |
| "content": "<img>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "248079": { |
| "content": "</img>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "248080": { |
| "content": "<quad>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "248081": { |
| "content": "</quad>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "248082": { |
| "content": "<ref>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "248083": { |
| "content": "</ref>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "248084": { |
| "content": "<box>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "248085": { |
| "content": "</box>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "248086": { |
| "content": "<|action_start|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "248087": { |
| "content": "<|action_end|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "248088": { |
| "content": "<|interpreter|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "248089": { |
| "content": "<|plugin|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "248090": { |
| "content": "<video>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "248091": { |
| "content": "<|ts|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "248092": { |
| "content": "<|/ts|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "248093": { |
| "content": "<TS_CONTEXT>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "248094": { |
| "content": "<SMILES>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "248095": { |
| "content": "</SMILES>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "248096": { |
| "content": "<protein>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "248097": { |
| "content": "</protein>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "248098": { |
| "content": "<dna>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "248099": { |
| "content": "</dna>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "248100": { |
| "content": "<rna>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| }, |
| "248101": { |
| "content": "</rna>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": false |
| } |
| }, |
| "additional_special_tokens": [ |
| "<|im_start|>", |
| "<|im_end|>", |
| "<|object_ref_start|>", |
| "<|object_ref_end|>", |
| "<|box_start|>", |
| "<|box_end|>", |
| "<|quad_start|>", |
| "<|quad_end|>", |
| "<|vision_start|>", |
| "<|vision_end|>", |
| "<|vision_pad|>", |
| "<|image_pad|>", |
| "<|video_pad|>" |
| ], |
| "audio_bos_token": "<|audio_start|>", |
| "audio_eos_token": "<|audio_end|>", |
| "audio_token": "<|audio_pad|>", |
| "auto_map": { |
| "AutoTokenizer": [ |
| "tokenization_interns1.InternS1Tokenizer", |
| null |
| ] |
| }, |
| "bos_token": "<|im_start|>", |
| "clean_up_tokenization_spaces": false, |
| "eos_token": "<|im_end|>", |
| "errors": "replace", |
| "extra_special_tokens": { |
| "audio_bos_token": "<|audio_start|>", |
| "audio_eos_token": "<|audio_end|>", |
| "audio_token": "<|audio_pad|>", |
| "image_token": "<|image_pad|>", |
| "video_token": "<|video_pad|>", |
| "vision_bos_token": "<|vision_start|>", |
| "vision_eos_token": "<|vision_end|>" |
| }, |
| "image_token": "<|image_pad|>", |
| "model_max_length": 262144, |
| "offset_PROT": 249126, |
| "offset_SMILES": 248102, |
| "offset_XNA": 250150, |
| "pad_token": "<|endoftext|>", |
| "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+", |
| "special_tokens_pattern": "none", |
| "split_special_tokens": false, |
| "tokenizer_class": "InternS1Tokenizer", |
| "unk_token": null, |
| "video_token": "<|video_pad|>", |
| "vision_bos_token": "<|vision_start|>", |
| "vision_eos_token": "<|vision_end|>" |
| } |
|
|
