generation_config.json

{
  "_from_model_config": true,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "max_length": 32768,
  "max_new_tokens": 512,
  "min_length": 0,
  "min_new_tokens": null,
  "early_stopping": false,
  "max_time": null,
  "do_sample": true,
  "num_beams": 1,
  "num_beam_groups": 1,
  "penalty_alpha": null,
  "use_cache": true,
  "temperature": 0.7,
  "top_k": 50,
  "top_p": 0.95,
  "typical_p": 1.0,
  "epsilon_cutoff": 0.0,
  "eta_cutoff": 0.0,
  "diversity_penalty": 0.0,
  "repetition_penalty": 1.15,
  "encoder_repetition_penalty": 1.0,
  "length_penalty": 1.0,
  "no_repeat_ngram_size": 0,
  "bad_words_ids": null,
  "force_words_ids": null,
  "renormalize_logits": false,
  "constraints": null,
  "forced_bos_token_id": null,
  "forced_eos_token_id": null,
  "remove_invalid_values": false,
  "exponential_decay_length_penalty": null,
  "suppress_tokens": null,
  "begin_suppress_tokens": null,
  "forced_decoder_ids": null,
  "sequence_bias": null,
  "guidance_scale": null,
  "low_memory": null,
  "num_return_sequences": 1,
  "output_attentions": false,
  "output_hidden_states": false,
  "output_scores": false,
  "return_dict_in_generate": false,
  "pad_token_id": null,
  "decoder_start_token_id": null,
  "transformers_version": "4.34.0",
  "task_specific_params": {
    "industrial_cost_calculation": {
      "temperature": 0.7,
      "top_p": 0.95,
      "repetition_penalty": 1.15,
      "max_new_tokens": 512,
      "do_sample": true
    },
    "document_analysis": {
      "temperature": 0.3,
      "top_p": 0.9,
      "repetition_penalty": 1.1,
      "max_new_tokens": 1024,
      "do_sample": true
    },
    "report_generation": {
      "temperature": 0.5,
      "top_p": 0.9,
      "repetition_penalty": 1.2,
      "max_new_tokens": 2048,
      "do_sample": true
    }
  }
}