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

model_name = "TheBloke/SOLAR-10.7B-Instruct-v1.0-AWQ"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", torch_dtype=torch.float16)
chat = pipeline("text-generation", model=model, tokenizer=tokenizer, device_map="auto")

# AlpDroid prompt
prompt_url = "https://raw.githubusercontent.com/ALPERALL/AlpDroid/main/prompt.txt"
system_prompt = requests.get(prompt_url).text

def alp_droid_chat(user_input):
    full = f"{system_prompt}\n\nKullanıcı: {user_input}\nAlpDroid:"
    res = chat(full, max_new_tokens=256, do_sample=True, temperature=0.7, top_p=0.9)[0]["generated_text"]
    return res.split("AlpDroid:")[-1].strip()

app = gr.Interface(alp_droid_chat,
                   inputs=gr.Textbox(lines=4, placeholder="Sorunu yaz..."),
                   outputs="text",
                   title="AlpDroid (SOLAR‑10.7B)",
                   description="TheBloke'un instruct modeliyle çalışan AlpDroid.")
app.launch()