Bantam-Tokenizer-128k / tokenizer_config.json
Theoistic's picture
Upload folder using huggingface_hub
7b8408b verified
{
"add_prefix_space": false,
"added_tokens_decoder": {
"128000": {
"content": "<|UNK|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128001": {
"content": "<|PAD|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128002": {
"content": "<|BOS|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128003": {
"content": "<|EOS|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128004": {
"content": "<|SYSTEM_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128005": {
"content": "<|SYSTEM_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128006": {
"content": "<|USER_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128007": {
"content": "<|USER_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128008": {
"content": "<|AGENT_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128009": {
"content": "<|AGENT_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128010": {
"content": "<|THINK_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128011": {
"content": "<|THINK_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128012": {
"content": "<|COMPUTE_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128013": {
"content": "<|COMPUTE_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128014": {
"content": "<|IMAGE_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128015": {
"content": "<|IMAGE_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128016": {
"content": "<|AUDIO_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128017": {
"content": "<|AUDIO_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128018": {
"content": "<|VISION_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128019": {
"content": "<|VISION_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128020": {
"content": "<|OBJECT_REF_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128021": {
"content": "<|OBJECT_REF_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128022": {
"content": "<|BOX_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128023": {
"content": "<|BOX_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128024": {
"content": "<|QUAD_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128025": {
"content": "<|QUAD_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128026": {
"content": "<|VISION_PAD|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128027": {
"content": "<|IMAGE_PAD|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128028": {
"content": "<|VIDEO_PAD|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128029": {
"content": "<|AUDIO_TOKEN_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128030": {
"content": "<|AUDIO_TOKEN_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128031": {
"content": "<|JSON_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128032": {
"content": "<|JSON_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128033": {
"content": "<|TOOL_CALL_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128034": {
"content": "<|TOOL_CALL_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128035": {
"content": "<|TOOL_RESPONSE_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128036": {
"content": "<|TOOL_RESPONSE_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128037": {
"content": "<|OBJECTIVES_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128038": {
"content": "<|OBJECTIVES_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128039": {
"content": "<|TASKS_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128040": {
"content": "<|TASKS_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128041": {
"content": "<|ASSUMPTIONS_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128042": {
"content": "<|ASSUMPTIONS_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128043": {
"content": "<|CONSTRAINTS_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128044": {
"content": "<|CONSTRAINTS_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128045": {
"content": "<|CONTEXT_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128046": {
"content": "<|CONTEXT_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128047": {
"content": "<|CITATIONS_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128048": {
"content": "<|CITATIONS_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128049": {
"content": "<|PROVENANCE_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128050": {
"content": "<|PROVENANCE_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128051": {
"content": "<|REASON_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128052": {
"content": "<|REASON_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128053": {
"content": "<|VERIFY_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128054": {
"content": "<|VERIFY_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128055": {
"content": "<|ANSWER_DRAFT_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128056": {
"content": "<|ANSWER_DRAFT_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128057": {
"content": "<|SUMMARY_BULLETS_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128058": {
"content": "<|SUMMARY_BULLETS_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128059": {
"content": "<|ANSWER_FINAL_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128060": {
"content": "<|ANSWER_FINAL_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128061": {
"content": "<|REDACT_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128062": {
"content": "<|REDACT_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128063": {
"content": "<|EXT1_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128064": {
"content": "<|EXT1_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128065": {
"content": "<|EXT2_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128066": {
"content": "<|EXT2_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128067": {
"content": "<|EXT3_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128068": {
"content": "<|EXT3_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128069": {
"content": "<|EXT4_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128070": {
"content": "<|EXT4_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|BOS|>",
"eos_token": "<|EOS|>",
"pad_token": "<|PAD|>",
"unk_token": "<|UNK|>",
"extra_special_tokens": {},
"tokenizer_class": "GPT2Tokenizer",
"model_max_length": 1000000000000000000000000000000,
"clean_up_tokenization_spaces": false
}