app.py

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

model_id = "julien31/Soar-qwen-14b"

tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", trust_remote_code=True)
generator = pipeline("text-generation", model=model, tokenizer=tokenizer)

def chat(prompt):
    result = generator(prompt, max_new_tokens=256)[0]["generated_text"]
    return result

iface = gr.Interface(fn=chat, inputs="text", outputs="text", title="Soar Qwen 14B API")
iface.launch()