Flock is a workflow-based low-code platform for rapidly building chatbots, RAG, and coordinating multi-agent teams.（Flock 是一个基于workflow工作流的低代码平台，用于快速构建聊天机器人、RAG、Agent和Muti-Agent应用。）

Minimalistic large language model 3D-parallelism training

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

Open sourece medical books in LaTeX. LaTeX写的中文开源医学书籍

[ECCV 2024] Tokenize Anything via Prompting

Codebase for Merging Language Models (ICML 2024)

Large World Model -- Modeling Text and Video with Millions Context

Tools for merging pretrained large language models.

VMamba: Visual State Space Models，code is based on mamba

[NeurlPS D&B 2024] Generative AI for Math: MathPile

[ECCV 2024] Official code implementation of Vary: Scaling Up the Vision Vocabulary of Large Vision Language Models.

An in-context conditioning version of MUSE with pre-trained checkpoints.

Official Pytorch Implementation of Synthesizing Coherent Story with Auto-Regressive Latent Diffusion Models

Mamba SSM architecture

Apache NiFi

A series of large language models trained from scratch by developers @01-ai

Toolkit for creating, sharing and using natural language prompts.

Apache Ignite Python Thin Client

[ICLR'24 spotlight] Chinese and English Multimodal Large Model Series (Chat and Paint) | 基于CPM基础模型的中英双语多模态大模型系列

🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

Langflow is a low-code app builder for RAG and multi-agent AI applications. It’s Python-based and agnostic to any model, API, or database.

DAMO-ConvAI: The official repository which contains the codebase for Alibaba DAMO Conversational AI.

text2vec, text to vector. 文本向量表征工具，把文本转化为向量矩阵，实现了Word2Vec、RankBM25、Sentence-BERT、CoSENT等文本表征、文本相似度计算模型，开箱即用。

Extends of Apache Ignite， add feathers：Mongodb protocol，Gremlin protocol, vector search，fulltext search，graph compute

Modification of Lucidrains' RETRO (retrieval-enhanced transformer) implementation to work with BERT/BM25-indexed retrieval on the Wikitext-103 dataset.

A framework for few-shot evaluation of language models.