A native PyTorch Library for large model training

A small library to add extra functionality on top of streamlit's st.query_params API

This repository shares recipes on building Streamlit apps with various tools.

Guideline following Large Language Model for Information Extraction

Multipass orchestrates virtual Ubuntu instances

Separate static content from dynamic content in Streamlit

A minimal Streamlit app showing how to launch and stop a FastAPI process on demand

A python module to repair invalid JSON, commonly used to parse the output of LLMs

Late Interaction Models Training & Retrieval

Dataset Viber is your chill repo for data collection, annotation and vibe checks.

[ICCV 2023] ProPainter: Improving Propagation and Transformer for Video Inpainting

Retrieve, Read and LinK: Fast and Accurate Entity Linking and Relation Extraction on an Academic Budget (ACL 2024)

Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2

Augmenting character level Transformers with Causal Dilated Conv1D layers

The fastest way to create an HTML app

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

A modular graph-based Retrieval-Augmented Generation (RAG) system

FashionCLIP is a CLIP-like model fine-tuned for the fashion domain.

CoTracker is a model for tracking any point (pixel) on a video.

The n-gram Language Model

a Hassle-Free Python Experience

Korvus is a search SDK that unifies the entire RAG pipeline in a single database query. Built on top of Postgres with bindings for Python, JavaScript, Rust and C.

Desktop app for automatically translating comics - BDs, Manga, Manhwa, Fumetti and more in a variety of formats (Image, Pdf, Epub, cbr, cbz, etc) and in multiple languages.

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.