Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
Repository Index
47,133 repositories indexed
1–14 of 14 · Most stars
Code and documentation to train Stanford's Alpaca models, and generate the data.
🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.
An open source implementation of CLIP.
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
Hierarchical Reasoning Model Official Release
An open-source, tool-augmented conversational language model from Fudan University
A PyTorch-based Speech Toolkit
🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
Plug and Play Language Model implementation. Allows to steer topic and attributes of GPT-2 models.
Tasks Assessing Protein Embeddings (TAPE), a set of five biologically relevant semi-supervised learning tasks spread across different domains of protein biology.
零基础入门大模型（LLM）的基础教程：从零手写 GPT-2，一行行看懂大模型是怎么工作的 | Build GPT-2 from scratch in PyTorch, step by step