Update app.py

app.py

@@ -1,6 +1,23 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
+from threading import Thread
 
+# Model configuration
+model_id = "Qwen/Qwen3-Coder-Next"
+
+# Load Tokenizer
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+
+# Load Model in 4-bit to save VRAM
+# Note: Requires a high-end GPU (A100 80GB recommended)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    torch_dtype="auto",
+    device_map="auto",
+    load_in_4bit=True, 
+    trust_remote_code=True
+)
 
 def respond(
     message,
@@ -9,61 +26,51 @@ def respond(
     max_tokens,
     temperature,
     top_p,
-    hf_token: gr.OAuthToken,
 ):
-    """
-    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(token=hf_token.token, model="Qwen/Qwen3-Coder-Next")
-
+    # Format the prompt using the chat template
     messages = [{"role": "system", "content": system_message}]
-
-    messages.extend(history)
-
+    for msg in history:
+        messages.append(msg)
     messages.append({"role": "user", "content": message})
 
-    response = ""
+    input_ids = tokenizer.apply_chat_template(
+        messages, 
+        add_generation_prompt=True, 
+        return_tensors="pt"
+    ).to(model.device)
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
+    # Setup Streaming
+    streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)
+    
+    generate_kwargs = dict(
+        input_ids=input_ids,
+        streamer=streamer,
+        max_new_tokens=max_tokens,
+        do_sample=True,
         temperature=temperature,
         top_p=top_p,
-    ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = choices[0].delta.content
+        pad_token_id=tokenizer.eos_token_id,
+    )
 
-        response += token
-        yield response
+    # Run generation in a separate thread
+    thread = Thread(target=model.generate, kwargs=generate_kwargs)
+    thread.start()
 
+    response = ""
+    for new_text in streamer:
+        response += new_text
+        yield response
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# Gradio Interface
 chatbot = gr.ChatInterface(
     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.Textbox(value="You are a helpful coding assistant.", label="System message"),
+        gr.Slider(minimum=1, maximum=4096, value=2048, step=1, label="Max new tokens"),
+        gr.Slider(minimum=0.1, maximum=2.0, 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"),
     ],
 )
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
-
-
 if __name__ == "__main__":
-    demo.launch()
+    chatbot.launch()