Chat with Meta's LLaMA models at home made easy

Updated 3 years ago

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.

Updated 3 years ago

Inference on CPU code for LLaMA models

Updated 3 years ago