Stars
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
中文Mixtral混合专家大模型（Chinese Mixtral MoE LLMs）
中文LLaMA-2 & Alpaca-2大模型二期项目 + 64K超长上下文模型 (Chinese LLaMA-2 & Alpaca-2 LLMs with 64K long context models)
用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库；24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.
The code of paper ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge Graphs. Zhanqiu Zhang, Jie Wang, Jiajun Chen, Shuiwang Ji, Feng Wu. NeurIPS 2021.
MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.
Awesome-LLM: a curated list of Large Language Model
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
校招、秋招、春招、实习好项目！带你从零实现一个高性能的深度学习推理库，支持大模型 llama2 、Unet、Yolov5、Resnet等模型的推理。Implement a high-performance deep learning inference library step by step
Must-read papers on knowledge graph reasoning
🔨 🍇 💻 🚀 GraphScope: A One-Stop Large-Scale Graph Computing System from Alibaba | 一站式图计算系统
CLI for building apps using Cloud Native Buildpacks
Terraform Provider for VMware vSphere
A tiny KV storage based on skiplist written in C++ language| 使用C++开发，基于跳表实现的轻量级键值数据库🔥🔥 🚀
互联网仍有记忆！那些曾经在校招过程中毁过口头offer、意向书、三方的公司！纵然人微言轻，也想尽绵薄之力！
ioCoro is an async-IO service framework based on cpp20Coroutine
TiDB is built for agentic workloads that grow unpredictably, with ACID guarantees and native support for transactions, analytics, and vector search. No data silos. No noisy neighbors. No infrastruc…
Context-Sensitive Lexicon Features for Neural Sentiment Analysis