import os
import gradio as gr
from huggingface_hub import login
from transformers import AutoTokenizer, AutoModelForCausalLM


login(os.environ["HF_TOKEN"])
model_id = "jimy26/Sherlock_Model"

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

def chat(prompt):
    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
    outputs = model.generate(**inputs, max_new_tokens=150, temperature=0.7, top_p=0.9)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

gr.Interface(
    fn=chat,
    inputs=gr.Textbox(lines=3, placeholder="Ask Sherlock Holmes something..."),
    outputs="text",
    title="🕵️ Chat with Sherlock Holmes",
    description="A character-based chatbot fine-tuned to act like Sherlock Holmes."
).launch()