JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

Firefly: 大模型训练工具，支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型

User-friendly Desktop Client App for AI Models/LLMs (GPT, Claude, Gemini, Ollama...)

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

ChatGPT 中文调教指南。各种场景使用指南。学习怎么让它听你的话。

Real-time speech recognition and voice activity detection (VAD) using next-gen Kaldi with ncnn without Internet connection. Support iOS, Android, Linux, macOS, Windows, Raspberry Pi, VisionFive2, L…

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

Examples and guides for using the OpenAI API

🍲 好的，今天我们来做菜！OK, Let's Cook!

Making text a first-class citizen in TensorFlow.

中文生成式预训练模型

Automated Machine Learning on Kubernetes

打造超人思維

maximal update parametrization (µP)

📺 Discover the latest machine learning / AI courses on YouTube.

Optax is a gradient processing and optimization library for JAX.

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

Efficiently computes derivatives of NumPy code.

科技爱好者周刊，每周五发布

Making large AI models cheaper, faster and more accessible

[ICLR 2022] Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners

[ACL 2021] LM-BFF: Better Few-shot Fine-tuning of Language Models https://arxiv.org/abs/2012.15723

浏览过的精彩逆向文章汇总，值得一看

Jupyter notebooks for the Natural Language Processing with Transformers book

Implements an efficient softmax approximation as described in the paper "Efficient softmax approximation for GPUs" (http://arxiv.org/abs/1609.04309)