Update app.py

app.py

@@ -1,64 +1,56 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("Grandediw/lora_model")
+from unsloth import FastLanguageModel
+from transformers import TextStreamer
 
+# 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
 
+# Define the response function
 def respond(
     message,
     history: list[tuple[str, str]],
-    system_message,
     max_tokens,
     temperature,
     top_p,
 ):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
+    # 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})
+
+    # Prepare inputs
+    inputs = tokenizer.apply_chat_template(
+        messages,
+        tokenize=True,
+        add_generation_prompt=True,
+        return_tensors="pt",
+    ).to("cuda")
 
+    # Stream response
     response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
+    streamer = TextStreamer(tokenizer, skip_prompt=True)
+    model.generate(
+        input_ids=inputs,
+        streamer=streamer,
+        max_new_tokens=max_tokens,
+        use_cache=True,
         temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
+        min_p=top_p,
+    )
+    return response
 
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# Build the Gradio ChatInterface
 demo = gr.ChatInterface(
-    respond,
+    fn=respond,
     additional_inputs=[
-        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)",
-        ),
+        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"),
     ],
 )
 
-
 if __name__ == "__main__":
     demo.launch()