app.py

import json
import pandas as pd
import requests
from multiprocessing import Pool
from functools import partial
import streamlit as st


GITHUB_CODE = "https://huggingface.co/datasets/lvwerra/github-code"
INCODER_IMG = (
    "https://huggingface.co/datasets/loubnabnl/repo-images/raw/main/incoder.png"
)


@st.cache()
def load_examples():
    with open("utils/examples.json", "r") as f:
        examples = json.load(f)
    return examples


def generate_code(model_name, gen_prompt, max_new_tokens, temperature, seed):
    url = (
        f"https://hf.space/embed/loubnabnl/{model_name.lower()}-subspace/+/api/predict/"
    )
    r = requests.post(
        url=url, json={"data": [gen_prompt, max_new_tokens, temperature, seed]}
    )
    generated_text = r.json()["data"][0]
    return generated_text


st.set_page_config(page_icon=":laptop:", layout="wide")

st.sidebar.header("Models")
models = ["CodeParrot", "InCoder"]
selected_models = st.sidebar.multiselect(
    "Select code generation models to compare", models, default=["CodeParrot"]
)

st.sidebar.header("Tasks")
tasks = [
    " ",
    "Pretraining datasets",
    "Model architecture",
    "Model evaluation",
    "Code generation",
]
selected_task = st.sidebar.selectbox("Select a task", tasks)


if selected_task == " ":
    st.title("Code Generation Models")
    with open("utils/intro.txt", "r") as f:
        intro = f.read()
    st.markdown(intro)