app.py

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

model_id = "ilsp/Meltemi-7B-Instruct-v1"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    load_in_4bit=True,
    torch_dtype=torch.float16
)

def chat(user_input):
    messages = [
        {"role": "system", "content": "Είσαι το Μελτέμι, ένα γλωσσικό μοντέλο για την ελληνική γλώσσα."},
        {"role": "user", "content": user_input}
    ]
    prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
    outputs = model.generate(**inputs, max_new_tokens=256)
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return response

gr.Interface(fn=chat, inputs="text", outputs="text", title="Meltemi Chatbot 🇬🇷").launch()