app.py

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
import gradio as gr

model_name = "NousResearch/Nous-Hermes-llama2-13b"
tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=True)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.float16,
    device_map="auto",
    trust_remote_code=True
)

generator = pipeline("text-generation", model=model, tokenizer=tokenizer)

def chat(prompt):
    output = generator(
        prompt,
        max_new_tokens=512,
        do_sample=True,
        temperature=0.8,
        top_k=60,
        top_p=0.95
    )
    return output[0]["generated_text"]

demo = gr.Interface(fn=chat, inputs="text", outputs="text")
demo.launch()