Repository Index

Code and documentation to train Stanford's Alpaca models, and generate the data.

• deep-learning
• instruction-following
• language-model

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.

• attention-mechanism
• deep-learning
• gpt
• gpt-2

An open source implementation of CLIP.

• deep-learning
• pytorch
• computer-vision
• language-model

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

• gpt-2
• adaptation
• language-model
• gpt-3

A PyTorch-based Speech Toolkit

• speech-recognition
• speech-toolkit
• speaker-recognition
• speech-to-text