app.py

import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "EssentialAI/rnj-1-instruct"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype="auto",
    device_map="auto"
)

def chat(prompt):
    inputs = tokenizer(prompt, return_tensors="pt")
    output = model.generate(
        **inputs,
        max_new_tokens=4096,  # long output
        temperature=0.2,
        do_sample=False
    )
    return tokenizer.decode(output[0], skip_special_tokens=True)

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