lmsreborn

fiddler

Fast Inference of MoE Models with CPU-GPU Orchestration

cleanlab

The standard data-centric AI package for data quality and machine learning with messy, real-world data and labels.

trl

Train transformer language models with reinforcement learning.

concurrent-btrees

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

zero_nlp

中文nlp解决方案(大模型、数据、模型、训练、推理)

open-parse

Improved file parsing for LLM’s

CUDA-Learn-Notes

🎉CUDA 笔记 / 大模型手撕CUDA / C++笔记，更新随缘: flash_attn、sgemm、sgemv、warp reduce、block reduce、dot product、elementwise、softmax、layernorm、rmsnorm、hist etc.

BERT-NER-Pytorch

Chinese NER(Named Entity Recognition) using BERT(Softmax, CRF, Span)

git-cliff

A highly customizable Changelog Generator that follows Conventional Commit specifications ⛰️

makeMoE

From scratch implementation of a sparse mixture of experts language model inspired by Andrej Karpathy's makemore :)

supersonic

SuperSonic is the next-generation BI platform that integrates Chat BI (powered by LLM) and Headless BI (powered by semantic layer) paradigms.

surya

OCR, layout analysis, and line detection in 90+ languages

SWE-agent

SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.29% of bugs in the SWE-bench evaluation set and takes just 1.5 minutes to run.

duckdb-polr

iresearch

IResearch is a cross-platform, high-performance search analytics library written entirely in C++ with the focus on a pluggability of different ranking/similarity models

RAG-Retrieval

Unify Efficient Fine-tuning of RAG Retrieval, including Embedding, ColBERT,Cross Encoder

deepdoctection

A Repo For Document AI

ragflow

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

one-transformer

a tutorial for training a PyTorch transformer from scratch

CPlusPlusThings

C++那些事

LLaMA-Factory

Unify Efficient Fine-Tuning of 100+ LLMs

stella

text embedding

ChainForge

An open-source visual programming environment for battle-testing prompts to LLMs.

llm-books

利用LLM构建应用实践笔记

Linly

Chinese-LLaMA 1&2、Chinese-Falcon 基础模型；ChatFlow中文对话模型；中文OpenLLaMA模型；NLP预训练/指令微调数据集

Real-ESRGAN

Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.

DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Open-Sora

Open-Sora: Democratizing Efficient Video Production for All

quantum

Powerful multi-threaded coroutine dispatcher and parallel execution engine