app.py

import gradio as gr
from transformers import AutoTokenizer, AutoModelForCausalLM

MODEL_ID = "INTERX/Qwen2.5-GenX-7B"

tokenizer = AutoTokenizer.from_pretrained(MODEL_ID, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(MODEL_ID, device_map="auto", torch_dtype="auto", trust_remote_code=True)

def chat(user_input):
    messages = [{"role": "user", "content": user_input}]
    inputs = tokenizer.apply_chat_template(
        messages,
        tokenize=True,
        add_generation_prompt=True,
        return_tensors="pt"
    ).to(model.device)

    output = model.generate(inputs, max_new_tokens=512)
    response = tokenizer.decode(output[0], skip_special_tokens=True)
    return response

gr.Interface(fn=chat, inputs="text", outputs="text", title="Chat con Qwen2.5-GenX-7B").launch()