Bantam-285m / tokenizer_config.json
Theoistic's picture
Upload folder using huggingface_hub
bc9042e verified
{
"added_tokens_decoder": {
"0": {
"content": "<|UNK|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<|PAD|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<|BOS|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<|EOS|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "<|SYSTEM_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"5": {
"content": "<|SYSTEM_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"6": {
"content": "<|USER_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"7": {
"content": "<|USER_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"8": {
"content": "<|AGENT_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"9": {
"content": "<|AGENT_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"10": {
"content": "<|THINK_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"11": {
"content": "<|THINK_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"12": {
"content": "<|COMPUTE_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"13": {
"content": "<|COMPUTE_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"14": {
"content": "<|IMAGE_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"15": {
"content": "<|IMAGE_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"16": {
"content": "<|AUDIO_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"17": {
"content": "<|AUDIO_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"18": {
"content": "<|VISION_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"19": {
"content": "<|VISION_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"20": {
"content": "<|OBJECT_REF_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21": {
"content": "<|OBJECT_REF_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"22": {
"content": "<|BOX_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"23": {
"content": "<|BOX_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"24": {
"content": "<|QUAD_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"25": {
"content": "<|QUAD_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"26": {
"content": "<|VISION_PAD|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"27": {
"content": "<|IMAGE_PAD|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"28": {
"content": "<|VIDEO_PAD|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"29": {
"content": "<|AUDIO_TOKEN_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"30": {
"content": "<|AUDIO_TOKEN_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"31": {
"content": "<|JSON_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32": {
"content": "<|JSON_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"33": {
"content": "<|TOOL_CALL_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"34": {
"content": "<|TOOL_CALL_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"35": {
"content": "<|TOOL_RESPONSE_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"36": {
"content": "<|TOOL_RESPONSE_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"37": {
"content": "<|OBJECTIVES_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"38": {
"content": "<|OBJECTIVES_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"39": {
"content": "<|TASKS_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"40": {
"content": "<|TASKS_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"41": {
"content": "<|ASSUMPTIONS_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"42": {
"content": "<|ASSUMPTIONS_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"43": {
"content": "<|CONSTRAINTS_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"44": {
"content": "<|CONSTRAINTS_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"45": {
"content": "<|CONTEXT_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"46": {
"content": "<|CONTEXT_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"47": {
"content": "<|CITATIONS_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"48": {
"content": "<|CITATIONS_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"49": {
"content": "<|PROVENANCE_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"50": {
"content": "<|PROVENANCE_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"51": {
"content": "<|REASON_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"52": {
"content": "<|REASON_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"53": {
"content": "<|VERIFY_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"54": {
"content": "<|VERIFY_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"55": {
"content": "<|ANSWER_DRAFT_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"56": {
"content": "<|ANSWER_DRAFT_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"57": {
"content": "<|SUMMARY_BULLETS_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"58": {
"content": "<|SUMMARY_BULLETS_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"59": {
"content": "<|ANSWER_FINAL_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"60": {
"content": "<|ANSWER_FINAL_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"61": {
"content": "<|REDACT_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"62": {
"content": "<|REDACT_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"63": {
"content": "<|EXT1_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64": {
"content": "<|EXT1_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65": {
"content": "<|EXT2_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"66": {
"content": "<|EXT2_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"67": {
"content": "<|EXT3_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"68": {
"content": "<|EXT3_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"69": {
"content": "<|EXT4_START|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"70": {
"content": "<|EXT4_END|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<|SYSTEM_START|>",
"<|SYSTEM_END|>",
"<|USER_START|>",
"<|USER_END|>",
"<|AGENT_START|>",
"<|AGENT_END|>",
"<|THINK_START|>",
"<|THINK_END|>",
"<|COMPUTE_START|>",
"<|COMPUTE_END|>",
"<|IMAGE_START|>",
"<|IMAGE_END|>",
"<|AUDIO_START|>",
"<|AUDIO_END|>",
"<|VISION_START|>",
"<|VISION_END|>",
"<|OBJECT_REF_START|>",
"<|OBJECT_REF_END|>",
"<|BOX_START|>",
"<|BOX_END|>",
"<|QUAD_START|>",
"<|QUAD_END|>",
"<|VISION_PAD|>",
"<|IMAGE_PAD|>",
"<|VIDEO_PAD|>",
"<|AUDIO_TOKEN_START|>",
"<|AUDIO_TOKEN_END|>",
"<|JSON_START|>",
"<|JSON_END|>",
"<|TOOL_CALL_START|>",
"<|TOOL_CALL_END|>",
"<|TOOL_RESPONSE_START|>",
"<|TOOL_RESPONSE_END|>",
"<|OBJECTIVES_START|>",
"<|OBJECTIVES_END|>",
"<|TASKS_START|>",
"<|TASKS_END|>",
"<|ASSUMPTIONS_START|>",
"<|ASSUMPTIONS_END|>",
"<|CONSTRAINTS_START|>",
"<|CONSTRAINTS_END|>",
"<|CONTEXT_START|>",
"<|CONTEXT_END|>",
"<|CITATIONS_START|>",
"<|CITATIONS_END|>",
"<|PROVENANCE_START|>",
"<|PROVENANCE_END|>",
"<|REASON_START|>",
"<|REASON_END|>",
"<|VERIFY_START|>",
"<|VERIFY_END|>",
"<|ANSWER_DRAFT_START|>",
"<|ANSWER_DRAFT_END|>",
"<|SUMMARY_BULLETS_START|>",
"<|SUMMARY_BULLETS_END|>",
"<|ANSWER_FINAL_START|>",
"<|ANSWER_FINAL_END|>",
"<|REDACT_START|>",
"<|REDACT_END|>",
"<|EXT1_START|>",
"<|EXT1_END|>",
"<|EXT2_START|>",
"<|EXT2_END|>",
"<|EXT3_START|>",
"<|EXT3_END|>",
"<|EXT4_START|>",
"<|EXT4_END|>"
],
"bos_token": "<|BOS|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|EOS|>",
"extra_special_tokens": {},
"model_max_length": 16384,
"pad_token": "<|PAD|>",
"tokenizer_class": "PreTrainedTokenizerFast",
"unk_token": "<|UNK|>"
}