Update README.md

README.md

@@ -350,11 +350,13 @@ inputs = inputs.to("cuda")
 # Generation configs
 generation_config =  model.generation_config
 generation_config.do_sample   = True
-generation_config.temperature = 0.2
+generation_config.temperature = 1.0
 generation_config.top_k       = 1
-generation_config.top_p       = 0.001
+generation_config.top_p       = 0.9
+generation_config.min_p       = 0.1
+generation_config.best_of     = 5
 generation_config.max_new_tokens     = 2048
-generation_config.repetition_penalty = 1.1
+generation_config.repetition_penalty = 1.06
 
 # Inference
 generated_ids = model.generate(**inputs, generation_config=generation_config)