llama-falc / tokenizer_config.json
gpnd's picture
Fine-tuning FALC avec MLX-LM LoRA sur Llama 3.2 3B-Instruct
415bb41 verified
raw
history blame contribute delete
295 Bytes
{
"backend": "tokenizers",
"bos_token": "<|begin_of_text|>",
"clean_up_tokenization_spaces": true,
"eos_token": "<|eot_id|>",
"is_local": true,
"model_input_names": [
"input_ids",
"attention_mask"
],
"model_max_length": 131072,
"tokenizer_class": "TokenizersBackend"
}