generation_config.json

{
  "max_length": 20,
  "max_new_tokens": 160,
  "min_length": 0,
  "min_new_tokens": null,
  "early_stopping": true,
  "max_time": null,
  "stop_strings": null,
  "do_sample": false,
  "num_beams": 4,
  "use_cache": true,
  "cache_implementation": null,
  "cache_config": null,
  "return_legacy_cache": null,
  "prefill_chunk_size": null,
  "temperature": 1.0,
  "top_k": 50,
  "top_p": 1.0,
  "min_p": null,
  "typical_p": 1.0,
  "epsilon_cutoff": 0.0,
  "eta_cutoff": 0.0,
  "repetition_penalty": 1.0,
  "encoder_repetition_penalty": 1.0,
  "length_penalty": 1.0,
  "no_repeat_ngram_size": 0,
  "bad_words_ids": null,
  "renormalize_logits": false,
  "forced_bos_token_id": 250037,
  "forced_eos_token_id": null,
  "remove_invalid_values": false,
  "exponential_decay_length_penalty": null,
  "suppress_tokens": null,
  "begin_suppress_tokens": null,
  "sequence_bias": null,
  "token_healing": false,
  "guidance_scale": null,
  "watermarking_config": null,
  "num_return_sequences": 1,
  "output_attentions": false,
  "output_hidden_states": false,
  "output_scores": false,
  "output_logits": null,
  "return_dict_in_generate": false,
  "pad_token_id": null,
  "bos_token_id": null,
  "eos_token_id": null,
  "encoder_no_repeat_ngram_size": 0,
  "decoder_start_token_id": 250037,
  "is_assistant": false,
  "num_assistant_tokens": 20,
  "num_assistant_tokens_schedule": "constant",
  "assistant_confidence_threshold": 0.4,
  "prompt_lookup_num_tokens": null,
  "max_matching_ngram_size": null,
  "assistant_early_exit": null,
  "assistant_lookbehind": 10,
  "target_lookbehind": 10,
  "disable_compile": false,
  "low_memory": null,
  "penalty_alpha": null,
  "dola_layers": null,
  "diversity_penalty": 0.0,
  "num_beam_groups": 1,
  "constraints": null,
  "force_words_ids": null,
  "_from_model_config": false,
  "transformers_version": "4.57.1"
}