Update backend/query_llm.py

backend/query_llm.py

@@ -70,15 +70,57 @@ def generate_hf(prompt: str, history: str, temperature: float = 0.9, max_new_tok
 
     temperature = max(float(temperature), 1e-2)  # Ensure temperature isn't too low
     top_p = float(top_p)
-
-    generate_kwargs = {
-        'temperature': temperature,
-        'max_new_tokens': max_new_tokens,
-        'top_p': top_p,
-        'repetition_penalty': repetition_penalty,
-        'do_sample': True,
-        'seed': 42,
-        }
+    generate_kwargs=[
+    gr.Textbox(
+        label="System Prompt",
+        max_lines=1,
+        interactive=True,
+    ),
+    gr.Slider(
+        label="Temperature",
+        value=0.9,
+        minimum=0.0,
+        maximum=1.0,
+        step=0.05,
+        interactive=True,
+        info="Higher values produce more diverse outputs",
+    ),
+    gr.Slider(
+        label="Max new tokens",
+        value=256,
+        minimum=0,
+        maximum=4048,
+        step=64,
+        interactive=True,
+        info="The maximum numbers of new tokens",
+    ),
+    gr.Slider(
+        label="Top-p (nucleus sampling)",
+        value=0.90,
+        minimum=0.0,
+        maximum=1,
+        step=0.05,
+        interactive=True,
+        info="Higher values sample more low-probability tokens",
+    ),
+    gr.Slider(
+        label="Repetition penalty",
+        value=1.2,
+        minimum=1.0,
+        maximum=2.0,
+        step=0.05,
+        interactive=True,
+        info="Penalize repeated tokens",
+    )
+    ]
+    # generate_kwargs = {
+    #     'temperature': temperature,
+    #     'max_new_tokens': max_new_tokens,
+    #     'top_p': top_p,
+    #     'repetition_penalty': repetition_penalty,
+    #     'do_sample': True,
+    #     'seed': 42,
+    #     }
     
     formatted_prompt = format_prompt(prompt, "hf")