Update app.py

app.py

@@ -1,69 +1,49 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-
-def respond(
-    message,
-    history: list[dict[str, str]],
-    system_message,
-    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="openai/gpt-oss-20b")
-
-    messages = [{"role": "system", "content": system_message}]
-
-    messages.extend(history)
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-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)",
-        ),
-    ],
+from llama_cpp import Llama
+
+# Load the model
+# Note: Ensure you have a Q4_K_M file in your repo, or change the filename below to match your exact upload (e.g., "*.gguf")
+llm = Llama.from_pretrained(
+    repo_id="WithinUsAI/IBM-Grok4-Ultra.Fast.Coder-1B-GGUF",
+    filename="*Q4_K_M*", 
+    n_ctx=8192,
+    n_threads=4,
+    verbose=False,
 )
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
-
-
-if __name__ == "__main__":
-    demo.launch()
+def chat(message, history):
+    # Standard ChatML format, highly effective for modern coding models
+    prompt = "<|im_start|>system\nYou are an ultra-fast, expert coding assistant. You write clean, efficient, and well-documented code.<|im_end|>\n"
+    
+    for user_msg, assistant_msg in history:
+        prompt += f"<|im_start|>user\n{user_msg}<|im_end|>\n"
+        prompt += f"<|im_start|>assistant\n{assistant_msg}<|im_end|>\n"
+        
+    prompt += f"<|im_start|>user\n{message}<|im_end|>\n<|im_start|>assistant\n"
+
+    output = llm(
+        prompt,
+        max_tokens=1024,
+        stop=["<|im_end|>", "<|im_start|>"],
+        temperature=0.6, # Slightly lower temperature for more precise code generation
+        top_p=0.95,
+        repeat_penalty=1.1,
+        echo=False,
+    )
+    return output["choices"][0]["text"].strip()
+
+# Wrap the ChatInterface in gr.Blocks to safely apply the blue theme
+with gr.Blocks(theme=gr.themes.Default(primary_hue="blue")) as demo:
+    gr.ChatInterface(
+        fn=chat,
+        title="💻 IBM-Grok4 Ultra Fast Coder — 1B",
+        description="Lightning-fast 1B coding assistant by **WithIn Us AI**. Built for speed, efficiency, and accurate code generation.",
+        examples=[
+            "Write a Python web scraper using BeautifulSoup.",
+            "Create a simple React component for a login form.",
+            "Explain the difference between TCP and UDP.",
+            "Debug this code: def add(a,b) return a+b",
+        ],
+    )
+
+demo.launch()