Stars
Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…
雅意信息抽取大模型：在百万级人工构造的高质量信息抽取数据上进行指令微调，由中科闻歌算法团队研发。 (Repo for YAYI Unified Information Extraction Model)
Accessible large language models via k-bit quantization for PyTorch.
[ACL 2024] An Easy-to-use Instruction Processing Framework for LLMs.
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
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)
Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)
BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）
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
An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.
The official GitHub page for the survey paper "A Survey of Large Language Models".
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)
Ongoing research training transformer language models at scale, including: BERT & GPT-2
A framework for few-shot evaluation of autoregressive language models.
Toolkit for creating, sharing and using natural language prompts.
Human ChatGPT Comparison Corpus (HC3), Detectors, and more! 🔥
Open source annotation tool for machine learning practitioners.
A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
Pretrain, finetune ANY AI model of ANY size on multiple GPUs, TPUs with zero code changes.
Semi-supervised Learning for Sentiment Analysis