CodeLlama-7b-hf / tokenizer_config.json
tanaymehta's picture
Add Fill-in-Middle specific tokens
26de81c verified
{
"add_bos_token": true,
"add_eos_token": false,
"bos_token": {
"__type": "AddedToken",
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"clean_up_tokenization_spaces": false,
"eos_token": {
"__type": "AddedToken",
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"legacy": null,
"model_max_length": 1000000000000000019884624838656,
"pad_token": null,
"sp_model_kwargs": {},
"tokenizer_class": "CodeLlamaTokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"fim_prefix": "▁<PRE>",
"fim_middle": "▁<MID>",
"fim_suffix": "▁<SUF>"
}