akashmjn

segment-anything

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

PaddleOCR

Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)

FastChat

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

faiss

A library for efficient similarity search and clustering of dense vectors.

llama3

The official Meta Llama 3 GitHub site

LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

mlx

MLX: An array framework for Apple silicon

redis-py

Redis Python client

surya

OCR, layout analysis, reading order, line detection in 90+ languages

trl

Train transformer language models with reinforcement learning.

minbpe

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

promptbase

All things prompt engineering

sglang

SGLang is a fast serving framework for large language models and vision language models.

alignment-handbook

Robust recipes to align language models with human and AI preferences

gpu.cpp

A lightweight library for portable low-level GPU computation using WebGPU.

deepdoctection

A Repo For Document AI

lightllm

LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.

webdataset

A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.

whisper_streaming

Whisper realtime streaming for long speech-to-text transcription and translation

S-LoRA

S-LoRA: Serving Thousands of Concurrent LoRA Adapters

HALOs

A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).

gritlm

Generative Representational Instruction Tuning

tevatron

Tevatron - A flexible toolkit for neural retrieval research and development.

unitable

UniTable: Towards a Unified Table Foundation Model

ml-sigma-reparam

tamil-llama

A New Tamil Large Language Model (LLM) Based on Llama 2

stopes

A library for preparing data for machine translation research (monolingual preprocessing, bitext mining, etc.) built by the FAIR NLLB team.

chug

Minimal sharded dataset loaders, decoders, and utils for multi-modal document, image, and text datasets.

vidore-benchmark

Vision Document Retrieval (ViDoRe): Benchmark. Evaluation code for the ColPali paper.

openhathi_instruct

This repository contains the code for dataset curation and finetuning of instruct variant of the Bilingual OpenHathi model. The resulting model is meant to follow instructions and chat in Hindi and Hinglish.