generation_config.json

{
  "attn_implementation": "flash_attention_2",
  "bos_token_id": 151643,
  "do_sample": true,
  "eos_token_id": [
    151645,
    151643
  ],
  "max_length": 128000,
  "pad_token_id": 151643,
  "repetition_penalty": 1.05,
  "temperature": 1e-06,
  "transformers_version": "4.54.0"
}