donghucey

donghucey's Stars

• pprp/Pruner-Zero

  Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for LLMs

  Language:Python675

• nyunAI/PruneGPT

  Language:Python502

• Duxiaoman-DI/XuanYuan

  轩辕：度小满中文金融对话大模型

  Language:Python1k88

• FudanDISC/DISC-FinLLM

  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 financial consulting services in financial scenarios.

  Language:Python56267

• xiaomabenten/system_architect

  💯2024年 系统架构设计师（软考高级）备考资源库+配套免费刷题软件。

  1.9k646

• BBuf/how-to-optim-algorithm-in-cuda

  how to optimize some algorithm in cuda.

  Language:Cuda1.4k118

• liguodongiot/llm-action

  本项目旨在分享大模型相关技术原理以及实战经验。

  Language:HTML9.1k889

• open-compass/opencompass

  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.

  Language:Python3.7k401

• kakaobrain/trident

  A performance library for machine learning applications.

  Language:Python17811

• liguodongiot/llm-resource

  LLM全栈优质资源汇总

  Language:Shell31129

• SkyworkAI/Skywork

  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 methods, etc. 天工系列模型在3.2TB高质量多语言和代码数据上进行预训练。我们开源了模型参数，训练数据，评估数据，评估方法。

  Language:Python1.2k111

• taishan1994/pytorch_bert_multi_classification

  基于pytorch_bert的中文多标签分类

  Language:Python7914

• taishan1994/pytorch_bert_event_extraction

  基于pytorch+bert的中文事件抽取

  Language:Python643

• triton-lang/triton

  Development repository for the Triton language and compiler

  Language:C++12.7k1.5k

• LlamaFamily/Llama-Chinese

  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

  Language:Python13.6k1.2k

• BDBC-KG-NLP/IE-Survey

  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。

  45369

• TigerResearch/TigerBot

  TigerBot: A multi-language multi-task LLM

  Language:Python2.2k194

• FlagAI-Open/FlagAI

  FlagAI (Fast LArge-scale General AI models) is a fast, easy-to-use and extensible toolkit for large-scale model.

  Language:Python3.8k415

• pytorch/kineto

  A CPU+GPU Profiling library that provides access to timeline traces and hardware performance counters.

  Language:HTML692164

• ymcui/Chinese-LLaMA-Alpaca

  中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)

  Language:Python18.2k1.9k

• chenzomi12/AISystem

  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

  Language:Jupyter Notebook10.4k1.5k

• godweiyang/NN-CUDA-Example

  Several simple examples for popular neural network toolkits calling custom CUDA operators.

  Language:Python1.3k183

• Light-City/CPlusPlusThings

  C++那些事

  Language:C++38.8k8.5k

• OpenMOSS/MOSS

  An open-source tool-augmented conversational language model from Fudan University

  Language:Python11.9k1.1k

• hpcaitech/ColossalAI

  Making large AI models cheaper, faster and more accessible

  Language:Python38.6k4.3k

• openmlsys/openmlsys-zh

  《Machine Learning Systems: Design and Implementation》- Chinese Version

  Language:TeX4k430

• apache/dolphinscheduler

  Apache DolphinScheduler is the modern data orchestration platform. Agile to create high performance workflow with low-code

  Language:Java12.7k4.6k

• PAIR-code/facets

  Visualizations for machine learning datasets

  Language:Jupyter Notebook7.3k887

• dibingfa/flash-linux0.11-talk

  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

  Language:HTML19.9k2.7k

• seaswalker/spring-analysis

  Spring源码阅读

  Language:Java13.5k4.2k