Create app.py

app.py

@@ -0,0 +1,35 @@
+import gradio as gr
+from llama_cpp import Llama
+from huggingface_hub import hf_hub_download
+
+# Download the model from Hugging Face
+MODEL_REPO = "krishna195/new_model"  # Replace with your repo ID
+MODEL_FILE = "unsloth.Q4_K_M.gguf"  # Replace with your file name
+
+model_path = hf_hub_download(
+    repo_id=MODEL_REPO,
+    filename=MODEL_FILE,
+    cache_dir="./models"  # Cache directory for storing the model
+)
+
+# Load the LLaMA model
+llm = Llama(model_path=model_path)
+
+# Function for chatbot interaction
+def chat_with_llama(user_input, history):
+    response = llm.create_chat_completion(
+        messages=[{"role": "user", "content": user_input}]
+    )
+    return response["choices"][0]["message"]["content"]  # Extract response text
+
+# Gradio UI
+chatbot_ui = gr.ChatInterface(
+    fn=chat_with_llama,
+    title="LLaMA Chatbot",
+    description="Chat with a fine-tuned LLaMA model hosted on Hugging Face.",
+    theme="compact"
+)
+
+# Launch Gradio app
+if __name__ == "__main__":
+    chatbot_ui.launch()