Lists (2)
Stars
Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for LLMs
DISC-FinLLM，中文金融大语言模型（LLM），旨在为用户提供金融场景下专业、智能、全面的金融咨询服务。DISC-FinLLM, a Chinese financial large language model (LLM) designed to provide users with professional, intelligent, and comprehensive financ…
how to optimize some algorithm in cuda.
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）
OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.
A performance library for machine learning applications.
Skywork series models are pre-trained on 3.2TB of high-quality multilingual (mainly Chinese and English) and code data. We have open-sourced the model, training data, evaluation data, evaluation me…
基于pytorch_bert的中文多标签分类
Development repository for the Triton language and compiler
Llama中文社区，Llama3在线体验和微调模型已开放，实时汇总最新Llama3学习资料，已将所有代码更新适配Llama3，构建最好的中文Llama大模型，完全开源可商用
北京航空航天大学大数据高精尖中心自然语言处理研究团队对信息抽取领域的调研。包括实体识别，关系抽取，属性抽取等子任务，每类子任务分别对学术界和工业界进行调研。
TigerBot: A multi-language multi-task LLM
FlagAI (Fast LArge-scale General AI models) is a fast, easy-to-use and extensible toolkit for large-scale model.
A CPU+GPU Profiling library that provides access to timeline traces and hardware performance counters.
中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)
AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术
Several simple examples for popular neural network toolkits calling custom CUDA operators.
An open-source tool-augmented conversational language model from Fudan University
Making large AI models cheaper, faster and more accessible
《Machine Learning Systems: Design and Implementation》- Chinese Version
Apache DolphinScheduler is the modern data orchestration platform. Agile to create high performance workflow with low-code
Visualizations for machine learning datasets
你管这破玩意叫操作系统源码 — 像小说一样品读 Linux 0.11 核心代码