app.py

import streamlit as st
from datasets import load_dataset
from transformer_ranker import TransformerRanker, prepare_popular_models

st.title("Choose Your Transformer")

# 1) Select multiple models from HuggingFace model hub
model_options = ['prajjwal1/bert-tiny', 'google/electra-small-discriminator', 'microsoft/deberta-v3-small',
                 'bert-base-uncased', 'bert-base-cased', 'distilbert-base-uncased', 'roberta-base']  # List of models
selected_models = st.multiselect("Select Models", model_options, default=model_options[:1])

# 2) Select dataset names (from text classification or token classification subcategory)
dataset_options = ['trec', 'conll2003']  # Example datasets; you can expand this list
selected_dataset = st.selectbox("Select Dataset", dataset_options)

# 3) Select the parameter for dataset downsampling
downsample_values = [0.05, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0]
downsample_ratio = st.select_slider("Dataset Downsample Ratio", options=downsample_values, value=0.2)

# 4) Select the parameter for "layer selection" with layermean as the default
layer_options = ['lastlayer', 'layermean', 'bestlayer']
selected_layer = st.selectbox("Layer Selection", layer_options, index=1)

# Add real-time logging in the future
log_expander = st.expander("Expand to view log")
log_placeholder = log_expander.empty()  # Placeholder for log updates

# Button to run the ranking process
if st.button("Run Model Ranking"):
    with st.spinner("Running the transformer-ranker..."):

        # Step 1: Load the selected dataset
        dataset = load_dataset(selected_dataset)

        # Step 2: Prepare the selected models
        language_models = prepare_popular_models('base') if selected_models == [] else selected_models

        # Step 3: Initialize the ranker
        ranker = TransformerRanker(dataset, dataset_downsample=downsample_ratio)

        # Placeholder for log updates
        log_placeholder.text("Real-time logging will be added here...")

        # Run the ranker
        results = ranker.run(language_models, batch_size=64)

        # Display the final results
        st.write(results)

    st.success("Ranking is Done!")