A tool that facilitates easy, efficient and high-quality fine-tuning of Cohere's models

Unify Efficient Fine-tuning of RAG Retrieval, including Embedding, ColBERT, ReRanker.

Zero shot pdf OCR with gpt-4o-mini

Minimalistic http servert template in go

[side-project] 과금 정보 수집 & 처리 시스템 - 다람쥐 금고

A Python implementation of Clean Architecture, inspired by Uncle Bob's book

Lite & Super-fast re-ranking for your search & retrieval pipelines. Supports SoTA Listwise and Pairwise reranking based on LLMs and cross-encoders and more. Created by Prithivi Da, open for PRs & C…

Code for explaining and evaluating late chunking (chunked pooling)

Entropy Based Sampling and Parallel CoT Decoding

Lightweight selfhosted Firefox Send alternative without public upload. AWS S3 supported.

Model components of the Llama Stack APIs

🇰🇷파이토치에서 제공하는 튜토리얼의 한국어 번역을 위한 저장소입니다. (Translate PyTorch tutorials in Korean🇰🇷)

Infinity is a high-throughput, low-latency REST API for serving text-embeddings, reranking models and clip

🐳Dockerfile for 🎨ComfyUI. | 容器镜像与启动脚本

gpt_server是一个用于生产级部署LLMs或Embedding的开源框架。

Training code for Sparse Autoencoders on Embedding models

RankLLM is a Python toolkit for reproducible information retrieval research using rerankers, with a focus on listwise reranking.

Prometheus exporter for custom eBPF metrics

FastAPI Best Practices and Conventions we used at our startup

한글 텍스트 임베딩 모델 리더보드

A compact LLM pretrained in 9 days by using high quality data

Efficient Triton Kernels for LLM Training

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

A family of compressed models obtained via pruning and knowledge distillation

Fast, streaming indexing and query library for AI (RAG) applications, written in Rust

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

FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.

A blazing fast inference solution for text embeddings models