generation_config.json

{
  "_from_model_config": false,
  "assistant_confidence_threshold": 0.4,
  "assistant_lookbehind": 10,
  "decoder_start_token_id": 0,
  "diversity_penalty": 0.0,
  "do_sample": true,
  "early_stopping": false,
  "encoder_no_repeat_ngram_size": 0,
  "encoder_repetition_penalty": 1.0,
  "eos_token_id": 1,
  "epsilon_cutoff": 0.0,
  "eta_cutoff": 0.0,
  "length_penalty": 1.0,
  "max_length": 20,
  "max_new_tokens": 64,
  "min_length": 0,
  "no_repeat_ngram_size": 2,
  "num_assistant_tokens": 20,
  "num_assistant_tokens_schedule": "constant",
  "num_beam_groups": 1,
  "num_beams": 8,
  "num_return_sequences": 5,
  "output_scores": false,
  "pad_token_id": 0,
  "remove_invalid_values": false,
  "repetition_penalty": 1.0,
  "return_dict_in_generate": false,
  "target_lookbehind": 10,
  "temperature": 0.8,
  "top_k": 50,
  "top_p": 0.95,
  "transformers_version": "5.0.0",
  "typical_p": 1.0,
  "use_cache": true
}