Create generation_config.json

generation_config.json

@@ -0,0 +1,57 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128004
+  ],
+  "pad_token_id": null,
+  "transformers_version": "4.45.0",
+  
+  "do_sample": true,
+  "temperature": 0.7,
+  "top_p": 0.9,
+  "top_k": 50,
+  "repetition_penalty": 1.1,
+  "no_repeat_ngram_size": 3,
+  "encoder_no_repeat_ngram_size": 0,
+  
+  "max_length": 8192,
+  "max_new_tokens": null,
+  "min_length": 0,
+  "min_new_tokens": null,
+  
+  "early_stopping": false,
+  "length_penalty": 1.0,
+  "num_beams": 1,
+  "num_beam_groups": 1,
+  "diversity_penalty": 0.0,
+  
+  "num_return_sequences": 1,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "output_scores": false,
+  "return_dict_in_generate": false,
+  
+  "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": true,
+  "exponential_decay_length_penalty": null,
+  "suppress_tokens": null,
+  "begin_suppress_tokens": null,
+  
+  "guidance_scale": null,
+  "low_memory": null,
+  
+  "typical_p": null,
+  "epsilon_cutoff": 0.0,
+  "eta_cutoff": 0.0,
+  
+  "use_cache": true,
+  "static_cache": false,
+  "cache_implementation": null
+}