init commit infer

app.py

@@ -1,64 +1,62 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-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("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    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,
-    ):
-        token = message.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
-"""
-demo = 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)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+from llama_cpp import Llama
+from huggingface_hub import hf_hub_download
+
+# Model identifier from Hugging Face
+model_repo = "ID2223-Lab/llama_lora_merged_GGUF"  # Hugging Face model ID
+
+# Download the GGUF file from Hugging Face
+model_path = hf_hub_download(repo_id=model_repo, filename="FineTune_Llama.gguf")
+
+# Load the GGUF model using llama-cpp-python
+print("Loading model...")
+llm = Llama(model_path=model_path, n_ctx=2048, n_threads=8)  # Adjust threads as needed
+print("Model loaded!")
+# Function for inference
+def chat_with_model(user_input, chat_history):
+    """
+    Process user input and generate a response from the model.
+    :param user_input: User's input string
+    :param chat_history: List of [user_message, ai_response] pairs
+    :return: Updated chat history
+    """
+    # Construct the prompt from chat history
+    prompt = ""
+    for user, ai in chat_history:
+        prompt += f"User: {user}\nAI: {ai}\n"
+    prompt += f"User: {user_input}\nAI:"  # Add the latest user input
+
+    # Generate response from the model
+    raw_response = llm(prompt)["choices"][0]["text"].strip()
+
+    # Clean the response (remove extra tags, if any)
+    response = raw_response.split("User:")[0].strip()
+
+    # Update chat history with the new turn
+    chat_history.append((user_input, response))
+    return chat_history, chat_history
+
+
+# Gradio UI
+with gr.Blocks() as demo:
+    gr.Markdown("# 🦙 LLaMA Chatbot with Base Model and LoRA Adapter")
+    chatbot = gr.Chatbot(label="Chat with the Model")
+
+    with gr.Row():
+        with gr.Column(scale=4):
+            user_input = gr.Textbox(label="Your Message", placeholder="Type a message...")
+        with gr.Column(scale=1):
+            submit_btn = gr.Button("Send")
+
+    chat_history = gr.State([])
+
+    # Link components
+    submit_btn.click(
+        chat_with_model,
+        inputs=[user_input, chat_history],
+        outputs=[chatbot, chat_history],
+        show_progress=True,
+    )
+
+# Launch the Gradio app
+demo.launch()

requirements.txt

@@ -1 +1,4 @@
-huggingface_hub==0.25.2
+huggingface_hub==0.25.2
+gradio 
+llama-cpp-python
+