Update app.py

app.py

@@ -1,70 +1,62 @@
 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="WWMachine/testmodel")
-
-    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,
-    type="messages",
-    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)",
-        ),
-    ],
-)
-
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
-
-
-if __name__ == "__main__":
-    demo.launch()
+from llama_cpp import Llama
+from huggingface_hub import hf_hub_download
+
+# --- Configuration ---
+# 1. Update with your model's repo ID and file name
+MODEL_REPO = "Your-HF-Username/your-model-repo"
+MODEL_FILE = "your-model-file-Q4_K_M.gguf"
+# Adjust context window and other params as needed
+CONTEXT_WINDOW = 4096 
+MAX_NEW_TOKENS = 512
+TEMPERATURE = 0.7 
+
+# --- Model Loading Function ---
+def load_llm():
+    """Downloads the GGUF model and initializes LlamaCPP."""
+    print("Downloading model...")
+    model_path = hf_hub_download(
+        repo_id=MODEL_REPO,
+        filename=MODEL_FILE
+    )
+    
+    # Initialize the LLM with the downloaded model path
+    # n_ctx is the context window size
+    # n_threads is set to 2 (free CPU core limit) for better parallelization
+    llm = Llama(
+        model_path=model_path,
+        n_ctx=CONTEXT_WINDOW,
+        n_threads=2,
+        verbose=False # Set to True for debugging
+    )
+    print("Model loaded successfully!")
+    return llm
+
+# Load the model only once when the Space starts
+llm = load_llm()
+
+# --- Inference Function ---
+def generate(prompt, history):
+    """Generates a response using the Llama model."""
+    # Use a basic prompt template (adjust for your model's specific format)
+    full_prompt = f"### Human: {prompt}\n### Assistant:"
+
+    output = llm(
+        prompt=full_prompt, 
+        max_tokens=MAX_NEW_TOKENS,
+        temperature=TEMPERATURE,
+        stop=["### Human:"], # Stop generation at the next user turn
+        echo=False
+    )
+    
+    # Extract the text from the response object
+    response_text = output['choices'][0]['text'].strip()
+    return response_text
+
+# --- Gradio Interface ---
+# Use the ChatInterface for a quick, functional chat UI
+gr.ChatInterface(
+    generate,
+    title=f"Chat with {MODEL_FILE}",
+    description="A GGUF LLM hosted on Hugging Face CPU Space using llama-cpp-python."
+).launch()