acean's repositories
BELLE
BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）
clash
A rule based proxy in Go.
ColossalAI
Making large AI models cheaper, faster and more accessible
corundum
Open source FPGA-based NIC and platform for in-network compute
CPM-Bee
百亿参数的中英文双语基座大模型
DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
Dolly-2.0-Series
Resources for running, fine-tuning, and inferencing Dolly 2.0
Dromedary
Dromedary: towards helpful, ethical and reliable LLMs.
EasyLM
Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.
fairscale
PyTorch extensions for high performance and large scale training.
FATE
An Industrial Grade Federated Learning Framework
ICL_PaperList
Paper List for In-context Learning 🌷
langchain-ChatGLM
langchain-ChatGLM, local knowledge based ChatGLM with langchain ｜ 基于本地知识的 ChatGLM 问答
LAVIS
LAVIS - A One-stop Library for Language-Vision Intelligence
Linly
Chinese-LLaMA 、Chinese-Falcon 基础模型；ChatFlow中文对话模型；中文OpenLLaMA模型；NLP预训练/指令微调数据集
LLaVA
Large Language-and-Vision Assistant built towards multimodal GPT-4 level capabilities.
LLM-Blender
[ACL2023] We introduce LLM-Blender, an innovative ensembling framework to attain consistently superior performance by leveraging the diverse strengths of multiple open-source LLMs. LLM-Blender cut the weaknesses through ranking and integrate the strengths through fusing generation to enhance the capability of LLMs.
llm-foundry
LLM training code for MosaicML foundation models
Luotuo-Chinese-LLM
骆驼(Luotuo): Open Sourced Chinese Language Models. Developed by 陈启源 @ 华中师范大学 & 李鲁鲁 @ 商汤科技 & 冷子昂 @ 商汤科技
mlflow
Open source platform for the machine learning lifecycle
MOSS
An open-source tool-augmented conversational language model from Fudan University
OlaGPT
Official implementation for "OlaGPT: Empowering LLMs With Human-like Problem-Solving Abilities" (keep updating)
OpenAGI
OpenAGI: When LLM Meets Domain Experts
TencentPretrain
Tencent Pre-training framework in PyTorch & Pre-trained Model Zoo
TigerBot
TigerBot: A multi-language multi-task LLM
tokenizers
💥 Fast State-of-the-Art Tokenizers optimized for Research and Production