Update app.py

app.py

@@ -2,12 +2,13 @@ import gradio as gr
 from llama_cpp import Llama
 from huggingface_hub import hf_hub_download
 
-# Load model
+# Download the GGUF model
 model_path = hf_hub_download(
     repo_id="ciphermosaic/qwen-alpaca-gguf",
-    filename="Qwen2.5-0.5B-Instruct.Q4_K_M.gguf"
+    filename="qwen-alpaca-q4_k_m.gguf"
 )
 
+# Load the model
 llm = Llama(
     model_path=model_path,
     n_ctx=2048,
@@ -15,27 +16,37 @@ llm = Llama(
     verbose=False,
 )
 
+# Chat function
 def chat(message, history):
     messages = []
 
-    for user_msg, assistant_msg in history:
-        messages.append({"role": "user", "content": user_msg})
-        messages.append({"role": "assistant", "content": assistant_msg})
+    # Add previous conversation
+    if history:
+        messages.extend(history)
 
-    messages.append({"role": "user", "content": message})
+    # Add current user message
+    messages.append({
+        "role": "user",
+        "content": message
+    })
 
+    # Generate response
     response = llm.create_chat_completion(
-        messages=messages
+        messages=messages,
+        temperature=0.7,
+        max_tokens=256,
     )
 
     reply = response["choices"][0]["message"]["content"]
 
     return reply
 
+# Gradio interface
 demo = gr.ChatInterface(
     fn=chat,
+    type="messages",
     title="🤖 Qwen Alpaca Chatbot",
-    description="A fine-tuned Qwen 0.5B GGUF model running with llama.cpp"
+    description="A fine-tuned Qwen 0.5B GGUF model running with llama.cpp",
 )
 
 demo.launch()