loubnabnl's picture
loubnabnl HF staff
High-level review (#2)
1e77c56
raw
history blame
4.35 kB
import json
import pandas as pd
import requests
import threading
import streamlit as st
MODELS = ["CodeParrot", "InCoder", "CodeGen", "PolyCoder"]
GENERATION_MODELS = ["CodeParrot", "InCoder", "CodeGen"]
@st.cache()
def load_examples():
with open("utils/examples.json", "r") as f:
examples = json.load(f)
return examples
def read_markdown(path):
with open(path, "r") as f:
output = f.read()
st.markdown(output, unsafe_allow_html=True)
def generate_code(
generations, model_name, gen_prompt, max_new_tokens, temperature, seed
):
# call space using its API endpoint
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]
generations.append(generated_text)
def generate_code_threads(
generations, models, gen_prompt, max_new_tokens, temperature, seed
):
threads = []
for model_name in models:
# create the thread
threads.append(
threading.Thread(
target=generate_code,
args=(
generations,
model_name,
gen_prompt,
max_new_tokens,
temperature,
seed,
),
)
)
threads[-1].start()
for t in threads:
t.join()
st.set_page_config(page_icon=":laptop:", layout="wide")
with open("utils/table_contents.md", "r") as f:
contents = f.read()
st.sidebar.markdown(contents)
# Introduction
st.title("Code generation with 🤗")
read_markdown("utils/intro.md")
# Code datasets
st.subheader("1 - Code datasets")
read_markdown("datasets/intro.md")
read_markdown("datasets/github_code.md")
col1, col2 = st.columns([1, 2])
with col1:
selected_model = st.selectbox("", MODELS, key=1)
read_markdown(f"datasets/{selected_model.lower()}.md")
# Model architecture
st.subheader("2 - Model architecture")
read_markdown("architectures/intro.md")
col1, col2 = st.columns([1, 2])
with col1:
selected_model = st.selectbox("", MODELS, key=2)
read_markdown(f"architectures/{selected_model.lower()}.md")
# Model evaluation
st.subheader("3 - Code models evaluation")
read_markdown("evaluation/intro.md")
read_markdown("evaluation/demo_humaneval.md")
# Code generation
st.subheader("4 - Code generation ✨")
read_markdown("generation/intro.md")
col1, col2, col3 = st.columns([7, 1, 6])
with col1:
st.markdown("**Models**")
selected_models = st.multiselect(
"Select code generation models to compare:",
GENERATION_MODELS,
default=["CodeParrot"],
key=3,
)
st.markdown(" ")
st.markdown("**Examples**")
examples = load_examples()
example_names = [example["name"] for example in examples]
name2id = dict([(name, i) for i, name in enumerate(example_names)])
selected_example = st.selectbox(
"Select one of the following examples or implement yours:", example_names
)
example_text = examples[name2id[selected_example]]["value"]
default_length = examples[name2id[selected_example]]["length"]
with col3:
st.markdown("**Generation settings**")
temperature = st.slider(
"Temperature:", value=0.2, min_value=0.0, step=0.1, max_value=2.0
)
max_new_tokens = st.slider(
"Number of tokens to generate:",
value=default_length,
min_value=8,
step=4,
max_value=256,
)
seed = st.slider("Random seed:", value=42, min_value=0, step=1, max_value=1000)
gen_prompt = st.text_area(
"Generate code with prompt:",
value=example_text,
height=200,
).strip()
if st.button("Generate code!"):
with st.spinner("Generating code..."):
# use threading
generations = []
generate_code_threads(
generations,
selected_models,
gen_prompt=gen_prompt,
max_new_tokens=max_new_tokens,
temperature=temperature,
seed=seed,
)
for i in range(len(generations)):
st.markdown(f"**{selected_models[i]}**")
st.code(generations[i])
# Resources
st.subheader("Resources")
read_markdown("utils/resources.txt")