🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org

A Next-Generation Training Engine Built for Ultra-Large MoE Models

EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

List of papers about Proteins Design using Deep Learning

LongRoPE is a novel method that can extends the context window of pre-trained LLMs to an impressive 2048k tokens.

Minimal keyword extraction with BERT

Retrieval and Retrieval-augmented LLMs

EasyTPP: Towards Open Benchmarking Temporal Point Processes

本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）

Example models using DeepSpeed

《动手学大模型Dive into LLMs》系列编程实践教程

Trax — Deep Learning with Clear Code and Speed

The paper list of the 86-page SCIS cover paper "The Rise and Potential of Large Language Model Based Agents: A Survey" by Zhiheng Xi et al.

强化学习中文教程（蘑菇书🍄），在线阅读地址：https://datawhalechina.github.io/easy-rl/

课程视频、PPT和源代码：侯捷C++系列；台大郭彦甫MATLAB

A simple, easy-to-hack GraphRAG implementation

stay tuned.

LLM training in simple, raw C/CUDA

Learning notes (In Chinese) of TED speeches, English magazines (e.g., The Economist) and YouTube videos

主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题

Open-Sora: Democratizing Efficient Video Production for All

数字人资料整理

This is an implementation of the paper: Searching for Best Practices in Retrieval-Augmented Generation (EMNLP2024)

personal chatgpt

UP-TO-DATE LLM Watermark paper. 🔥🔥🔥

VirtualWife是一个虚拟数字人项目，支持B站直播，支持openai、ollama

[ACL 2024 main] Aligning Large Language Models with Human Preferences through Representation Engineering (https://aclanthology.org/2024.acl-long.572/)

VLDB 2024 paper repo. RoarGraph: A Projected Bipartite Graph for Efficient Cross-Modal Approximate Nearest Neighbor Search

Grok open release

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