Update app.py

app.py

@@ -1,54 +1,47 @@
 import gradio as gr
-from unsloth import FastLanguageModel
-from transformers import TextStreamer
+from huggingface_hub import InferenceClient
 
-# Load the model
-model_path = "Grandediw/lora_model"  # Replace with the actual model path
-model = FastLanguageModel.for_inference(model_path)
-tokenizer = model.tokenizer  # Use the tokenizer from the model
+# Initialize the InferenceClient
+client = InferenceClient(model="Grandediw/lora_model")
 
-# Define the response function
 def respond(
     message,
     history: list[tuple[str, str]],
+    system_message,
     max_tokens,
     temperature,
     top_p,
 ):
-    # Build chat history
-    messages = [{"role": "user", "content": message}]
-    for user_msg, assistant_msg in history:
-        messages.append({"role": "user", "content": user_msg})
-        messages.append({"role": "assistant", "content": assistant_msg})
+    context = system_message + "\n"
+    for user_message, assistant_message in history:
+        context += f"User: {user_message}\nAssistant: {assistant_message}\n"
+    context += f"User: {message}\nAssistant:"
 
-    # Prepare inputs
-    inputs = tokenizer.apply_chat_template(
-        messages,
-        tokenize=True,
-        add_generation_prompt=True,
-        return_tensors="pt",
-    ).to("cuda")
-
-    # Stream response
-    response = ""
-    streamer = TextStreamer(tokenizer, skip_prompt=True)
-    model.generate(
-        input_ids=inputs,
-        streamer=streamer,
-        max_new_tokens=max_tokens,
-        use_cache=True,
-        temperature=temperature,
-        min_p=top_p,
-    )
-    return response
+    try:
+        response = client.text_generation(
+            context,
+            max_new_tokens=max_tokens,
+            temperature=temperature,
+            top_p=top_p,
+        )
+        yield response
+    except Exception as e:
+        yield f"Error: {e}"
 
 # Build the Gradio ChatInterface
 demo = gr.ChatInterface(
-    fn=respond,
+    respond,
     additional_inputs=[
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max Tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=1.5, step=0.1, label="Temperature"),
-        gr.Slider(minimum=0.1, maximum=1.0, value=0.9, step=0.05, label="Top-p"),
+        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
+        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
+        gr.Slider(
+            minimum=0.1,
+            maximum=1.0,
+            value=0.95,
+            step=0.05,
+            label="Top-p (nucleus sampling)",
+        ),
     ],
 )