add generation_config

README.md

@@ -139,6 +139,13 @@ prompt = generate_prompt(
 inputs = tokenizer(prompt, return_tensors="pt", padding=True, truncation=True, max_length=2048)
 input_ids = inputs["input_ids"].to(model.device)
 
+generation_config = GenerationConfig(
+    temperature=0.2,
+    top_p=0.75,
+    top_k=40,
+    num_beams=4,
+)
+
 with torch.no_grad():
     gen_outputs = model.generate(
         input_ids=input_ids,