Update app.py

app.py

@@ -24,19 +24,20 @@ model = PeftModel.from_pretrained(model, LORA_PATH)
 model.eval()
 
 
-def chat(prompt, max_new_tokens=256, temperature=0.7):
+def chat(prompt):
     inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
 
     with torch.no_grad():
         output = model.generate(
             **inputs,
-            max_new_tokens=max_new_tokens,
-            temperature=temperature,
-            do_sample=True,
+            max_new_tokens=256,
+            do_sample=False,
             eos_token_id=tokenizer.eos_token_id
         )
 
-    return tokenizer.decode(output[0], skip_special_tokens=True)
+    generated = output[0][inputs["input_ids"].shape[-1]:]
+    return tokenizer.decode(generated, skip_special_tokens=True)
+
 
 
 # Gradio UI