# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Abonia/Llama-2-7b-chat-finetune")
model = AutoModelForCausalLM.from_pretrained("Abonia/Llama-2-7b-chat-finetune")

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Abonia/Llama-2-7b-chat-finetune")


import gradio as gr

gr.load("models/Abonia/Llama-2-7b-chat-finetune").launch()