Text Generation
Transformers
Safetensors
Czech
mpt
custom_code
text-generation-inference
Inference Endpoints
csmpt7b / tokenizer_config.json
mfajcik's picture
Update tokenizer_config.json
17f6699 verified
raw
history blame
771 Bytes
{
"added_tokens_decoder": {
"0": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64000": {
"content": "[UNK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64001": {
"content": "[EOS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"clean_up_tokenization_spaces": true,
"eos_token": "[EOS]",
"model_max_length": 2048,
"pad_token": "[EOS]",
"tokenizer_class": "PreTrainedTokenizerFast",
"unk_token": "[UNK]",
"use_token_type_ids": false
}