app.py

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

model_id = "chanystrange/mistral-agri-merged_143"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", load_in_4bit=True)
generator = pipeline("text-generation", model=model, tokenizer=tokenizer)

def chat(prompt):
    return generator(prompt, max_new_tokens=200)[0]["generated_text"]

demo = gr.Interface(fn=chat, inputs="text", outputs="text")
demo.launch()  # <-- enables REST API