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

# Modeli yükleyin
model_name = "bkaplan/MRL1"

try:
    # Tokenizer ve modeli yükleme
    tokenizer = AutoTokenizer.from_pretrained(model_name)
    model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", torch_dtype=torch.float16)

    def respond(message, history, system_message, max_tokens, temperature, top_p):
        try:
            # Girdiyi hazırlama
            input_text = f"System: {system_message}\nUser: {message}\nAssistant:"
            
            # Tokenize etme
            inputs = tokenizer(input_text, return_tensors="pt").to(model.device)
            
            # Üretim parametreleri
            outputs = model.generate(
                **inputs, 
                max_length=max_tokens, 
                temperature=temperature, 
                top_p=top_p,
                num_return_sequences=1,
                do_sample=True
            )
            
            # Yanıtı çözme
            response = tokenizer.decode(outputs[0], skip_special_tokens=True)
            yield response
        
        except Exception as e:
            yield f"Hata oluştu: {str(e)}"

    # Gradio arayüzü
    demo = gr.ChatInterface(
        respond, 
        additional_inputs=[
            gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
            gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
            gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
            gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
        ]
    )

    if __name__ == "__main__":
        demo.launch(share=True)

except Exception as e:
    print(f"Model yüklenirken hata oluştue: {e}")