Fix literary summaries: exclude plays/epics, use human summaries from BookSum

Fix literary summaries: use only BookSum data (not Gutenberg excerpts)

Fix regression: restore balanced training settings, add technical manual filter

Major improvements: real titles, anti-overfitting, better demo UX

Add English language filter to all data downloads

Updated Training run, fixed dataset langauge issue

Improve discovery dataset quality

Fix type hints in demo_gradio.py for Pylance

Trigger rebuild

Use HF Datasets for discovery demo

Fix catalog.json path resolution for HF Space

Redesign Gradio demo as book/paper discovery tool

Fix Gradio demo metrics display and visualization script MLflow URI

Fixed compiling issue, added legnth penalty, and atttempting freezing encoder layers 0-5 to lower parameters and preserve T5's langauge understanding.

Remove custom theme - use Gradio default for compatibility

Minor fixes to Gradio and visualization scripts

Improve emotion task architecture and fix visualizations

Clean up codebase and fix training bugs

Fix Gradio demo: whole-book summaries, emotion sorting, styling

Add demo data for HF Space (books + news samples)

Redesign Gradio demo with book/news browsing, update .gitignore

Update Gradio demo, inference factory, and evaluation results

Update Gradio demo, inference factory, and evaluation results

Update LexiMind: improved training, model architecture, and evaluation

Expand datasets: GoEmotions (28 emotions), Yahoo Answers (10 topics), BookSum

Demo: Update Gradio UI with metrics, visualizations, and clean tabs

Fix Pylance type errors, add inductor compilation support

Full training run, code cleanup, mypy/ruff fixes

Clean up demo_gradio.py with consistent commenting style

Simplify Gradio demo to fix schema bug

Fix: Remove DownloadButton to avoid Gradio schema bug

Fix: Remove Gallery to avoid Gradio schema bug

Fix Gradio schema bug: replace Dataframe with Markdown tables

Fix Gradio HF Space compatibility

Training run: dev config 1 epoch results

feat: Add FLAN-T5 compatibility with relative position bias

Refactor: Fix B905 zip() strictness and resolve mypy error in evaluate.py

Style: Apply ruff formatting

Style: Fix linting errors and organize imports (ruff & mypy)

Refactor: Consolidate dependencies, improve testing, and add CI/CD

fix: correct rouge metrics column name and precision

download checkpoint from hub at runtime

Added pretrained BART wights for the encoder/decoder while keeping custom architectiure and task heads

Summarization fix through pipeline

Summarization fix

Summarization fix

Refactor: Fix tokenization, pathing, and track visuals with LFS

Fixing Display Issues for Metrics

Fixed Some Display Issues

Fixed Some Display Issues