tiny-random-CohereForCausalLM / tokenizer_config.json
hf-transformers-bot's picture
Upload tiny models for CohereForCausalLM
a71c4a2
raw
history blame
2.2 kB
{
"add_bos_token": true,
"add_eos_token": false,
"add_prefix_space": false,
"added_tokens_decoder": {
"0": {
"content": "<PAD>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<UNK>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<CLS>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<SEP>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "<MASK_TOKEN>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"5": {
"content": "<BOS_TOKEN>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"6": {
"content": "<EOS_TOKEN>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"7": {
"content": "<EOP_TOKEN>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"8": {
"content": "<|END_OF_TURN_TOKEN|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"auto_map": {
"AutoTokenizer": [
null,
"CohereForAI/c4ai-command-r-v01--tokenization_cohere_fast.CohereTokenizerFast"
]
},
"bos_token": "<BOS_TOKEN>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|END_OF_TURN_TOKEN|>",
"legacy": true,
"merges_file": null,
"model_max_length": 512,
"pad_token": "<PAD>",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "CohereTokenizer",
"unk_token": null,
"use_default_system_prompt": false,
"vocab_file": null
}