app.py

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

model_id = "heyIamUmair/llama3-3b-merged-legal"

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

pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)

def chat(query):
    output = pipe(query, max_new_tokens=200, do_sample=True, temperature=0.7)
    return output[0]["generated_text"]

gr.ChatInterface(fn=chat, title="🧑‍⚖️ Pakistan Law Chatbot (LLama 3.2)", theme="default").launch()