Update hf_model.py

hf_model.py

@@ -23,7 +23,17 @@ class HFModel:
     def generate_response(self, input_text, max_length=100, skip_special_tokens=True):
         try:
             inputs = self.tokenizer(input_text, return_tensors="pt").to(self.model.device)
-            outputs = self.model.generate(**inputs, max_length=max_length)
+            outputs = self.model.generate(
+                **inputs,
+                max_length=max_length,
+                pad_token_id=self.tokenizer.eos_token_id,  # Ensure proper padding
+                do_sample=True,  # Enable sampling for more diverse outputs
+                top_k=50,  # Limit sampling to top-k tokens
+                top_p=0.95,  # Use nucleus sampling
+                temperature=0.7,  # Control randomness
+            )
+            #inputs = self.tokenizer(input_text, return_tensors="pt").to(self.model.device)
+            #outputs = self.model.generate(**inputs, max_length=max_length)
             response = self.tokenizer.decode(outputs[0], skip_special_tokens=skip_special_tokens).strip()
             log_info(f"Generated Response: {response}")
             return response