app.py

import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("AmanMussa/llama2-kazakh-7b")
model = AutoModelForCausalLM.from_pretrained("AmanMussa/llama2-kazakh-7b")

def generate(text):
    inputs = tokenizer(text, return_tensors="pt")
    outputs = model.generate(**inputs, max_new_tokens=100)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

demo = gr.Interface(fn=generate, inputs="text", outputs="text", title="Llama2-Kazakh-7B Chatbot")
demo.launch()