LLM.py

import gradio as gr
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("IlyaGusev/saiga_gemma2_10b")
model = AutoModelForCausalLM.from_pretrained("IlyaGusev/saiga_gemma2_10b")

def generate_text(prompt):
    input_ids = tokenizer.encode(prompt, return_tensors="pt")
    output = model.generate(input_ids, max_length=50)
    return tokenizer.decode(output[0], skip_special_tokens=True)

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