deepseek-llm-7b-base / tokenizer_config.json
msr2000's picture
Update tokenizer_config.json
c6ccb0e
raw
history blame
792 Bytes
{
"add_bos_token": true,
"add_eos_token": false,
"bos_token": {
"__type": "AddedToken",
"content": "<|begin▁of▁sentence|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"clean_up_tokenization_spaces": false,
"eos_token": {
"__type": "AddedToken",
"content": "<|end▁of▁sentence|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"legacy": true,
"model_max_length": 4096,
"pad_token": {
"__type": "AddedToken",
"content": "<|end▁of▁sentence|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"sp_model_kwargs": {},
"unk_token": null,
"tokenizer_class": "LlamaTokenizerFast"
}