app.py

import streamlit as st
import torch
from transformers import pipeline

pipe = pipeline("text-generation", model="TheBloke/LLaMA2-13B-Estopia-GPTQ", disable_exllama=True)

text = st.text_area("Ask your question !")

if text:
    # We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
    messages = [
        {
            "role": "system",
            "content": "You are a friendly chatbot who always responds in the style of a pirate",
        },
        {"role": "user", "content": text},
    ]
    prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    out = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
    st.json(out[0]["generated_text"])