tya-m1-multilingual / tokenizer_config.json
rita-cohere's picture
Add full M1 hf_export/bf16 weights + bakeoff script.py + wheels
b6140ac verified
Raw
History Blame Contribute Delete
5.71 kB
{
"add_bos_token": true,
"add_eos_token": false,
"add_prefix_space": false,
"clean_up_tokenization_spaces": false,
"legacy": true,
"spaces_between_special_tokens": false,
"use_default_system_prompt": false,
"bos_token": "<BOS_TOKEN>",
"eos_token": "<EOS_TOKEN>",
"pad_token": "<PAD>",
"unk_token": "<UNK>",
"tokenizer_class": "CohereTokenizerFast",
"model_max_length": 1000000000000000019884624838656,
"sp_model_kwargs": {},
"added_tokens_decoder": {
"0": {
"content": "<PAD>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<MASK_TOKEN>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<BOS_TOKEN>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<EOS_TOKEN>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "<UNK>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"5": {
"content": "<|START_OF_TURN_TOKEN|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"6": {
"content": "<|END_OF_TURN_TOKEN|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"7": {
"content": "<|USER_TOKEN|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"8": {
"content": "<|CHATBOT_TOKEN|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"9": {
"content": "<|SYSTEM_TOKEN|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"10": {
"content": "<|NEW_FILE|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"11": {
"content": "<|BEGINNING_OF_PREFIX_FIM_TOKEN|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"12": {
"content": "<|BEGINNING_OF_MIDDLE_FIM_TOKEN|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"13": {
"content": "<|BEGINNING_OF_SUFFIX_FIM_TOKEN|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"14": {
"content": "<|END_OF_MIDDLE_FIM_TOKEN|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"261000": {
"content": "<|START_RESPONSE|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"261001": {
"content": "<|END_RESPONSE|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"261002": {
"content": "<|START_ACTION|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"261003": {
"content": "<|END_ACTION|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"261004": {
"content": "<|START_TOOL_RESULT|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"261005": {
"content": "<|END_TOOL_RESULT|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"261006": {
"content": "<|START_THINKING|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"261007": {
"content": "<|END_THINKING|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
}
}