cs247_codellama7b_refinement_4ep / tokenizer_config.json
mohsenfayyaz's picture
Upload weights
2dd03ad
{
"add_bos_token": true,
"add_eos_token": false,
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32000": {
"content": "▁<PRE>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32001": {
"content": "▁<MID>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32002": {
"content": "▁<SUF>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32003": {
"content": "▁<EOT>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32004": {
"content": "<pad>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"▁<PRE>",
"▁<MID>",
"▁<SUF>",
"▁<EOT>"
],
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"eot_token": "▁<EOT>",
"fill_token": "<FILL_ME>",
"legacy": null,
"middle_token": "▁<MID>",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<pad>",
"prefix_token": "▁<PRE>",
"sp_model_kwargs": {},
"suffix_first": false,
"suffix_token": "▁<SUF>",
"tokenizer_class": "CodeLlamaTokenizer",
"tokenizer_file": "/home/mohsenfayyaz/.cache/huggingface/hub/models--codellama--CodeLlama-7b-Python-hf/snapshots/953594314d3f482e2cfc1cf1778a10f994e6896d/tokenizer.json",
"unk_token": "<unk>",
"use_default_system_prompt": false
}