app.py

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

model_name = "TheBloke/MythoMax-L2-13B-GGUF"  # change this for OpenHermes

# Use token from environment
hf_token = os.environ.get("HF_TOKEN")

tokenizer = AutoTokenizer.from_pretrained(model_name, token=hf_token)
model = AutoModelForCausalLM.from_pretrained(model_name, token=hf_token, torch_dtype=torch.float16)

def chat(prompt):
    inputs = tokenizer(prompt, return_tensors="pt")
    outputs = model.generate(**inputs, max_new_tokens=200)
    reply = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return reply

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