init

.gitignore

@@ -0,0 +1,2 @@
+/venv
+/.idea

README.md

@@ -1,14 +1,15 @@
 ---
-title: PAIL UVA
+title: PAIL-UVA (Unique Virtual Assistant)
 emoji: 💬
 colorFrom: yellow
 colorTo: purple
 sdk: gradio
 sdk_version: 5.0.1
 app_file: app.py
-pinned: false
+pinned: true
 license: llama3.1
 short_description: Our flagship LLM. Based on Llama 3.1 8B IQ4_XS
 ---
 
-An example chatbot using [Gradio](https://gradio.app), [`huggingface_hub`](https://huggingface.co/docs/huggingface_hub/v0.22.2/en/index), and the [Hugging Face Inference API](https://huggingface.co/docs/api-inference/index).
+### Demo
+PAIL-UVA (Personalized AI Labs - Unique Virtual Assistant) is an efficient and responsive virtual assistant powered by the Llama 3.1 8B model with IQ4_XS quantization. It is optimized for low-resource environments while maintaining high performance for conversational tasks and provides information about Personalized AI Labs.

app.py

@@ -1,64 +1,29 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from llama_cpp import Llama
 
-"""
-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)",
-        ),
-    ],
+llm = Llama.from_pretrained(
+	repo_id="bartowski/Meta-Llama-3.1-8B-Instruct-GGUF",
+	filename="Meta-Llama-3.1-8B-Instruct-IQ4_XS.gguf",
 )
 
-
-if __name__ == "__main__":
-    demo.launch()
+def predict(message, history):
+	messages = [{"role": "system", "content": "You are a helpful assistant. Keep your responses short and to the point."}]
+	for user_message, bot_message in history:
+		if user_message:
+			messages.append({"role": "user", "content": user_message})
+		if bot_message:
+			messages.append({"role": "assistant", "content": bot_message})
+	messages.append({"role": "user", "content": message})
+
+	response = ""
+	for chunk in llm.create_chat_completion(
+			stream=True,
+			messages=messages,
+	):
+		part = chunk["choices"][0]["delta"].get("content", None)
+		if part:
+			response += part
+		yield response
+
+
+demo = gr.ChatInterface(predict).launch()

requirements.txt

@@ -1 +1,3 @@
-huggingface_hub==0.25.2
+huggingface_hub==0.25.2
+gradio
+llama-cpp-python