llama-tokenizer / tokenizer_config.json
ArthurZ's picture
ArthurZ HF staff
Upload tokenizer
0a9eb07
raw
history blame
903 Bytes
{
"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
},
"model_max_length": 2048,
"pad_token": null,
"sp_model_kwargs": {},
"special_tokens_map_file": "/home/arthur_huggingface_co/.cache/huggingface/hub/models--hf-internal-testing--llama-tokenizer/snapshots/25d5f79eeea5104810aee45f4ef599238f5ac21d/special_tokens_map.json",
"tokenizer_class": "LlamaTokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}