LEK-GPT-OSS-20B / tokenizer_config.json
lthn's picture
LEK-GPT-OSS-20B v2: 600 iter LoRA on 2,299 examples (up from 160)
06261ac verified
raw
history blame contribute delete
351 Bytes
{
"backend": "tokenizers",
"bos_token": "<|startoftext|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|return|>",
"is_local": true,
"model_input_names": [
"input_ids",
"attention_mask"
],
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<|endoftext|>",
"tokenizer_class": "TokenizersBackend"
}