app.py

from transformers import AutoModelForCausalLM, AutoTokenizer
import gradio as gr

# Load the model and tokenizer
model_name = "silma-ai/SILMA-9B-Instruct-v1.0"
model_name = "rombodawg/Rombos-LLM-V2.5-Qwen-72b"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

def generate_response(prompt):
    inputs = tokenizer(prompt, return_tensors="pt")
    outputs = model.generate(**inputs, max_length=200, num_return_sequences=1)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

# Gradio Interface
interface = gr.Interface(
    fn=generate_response,
    inputs="text",
    outputs="text",
    title="SILMA-9B Instruct",
    description="Provide a prompt, and the model generates a response."
)

interface.launch()