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.
Apache License 2.0
12.32k
stars
838
forks
source link
Add to guidance https://github.com/microsoft/guidance/tree/main/guidance/llms/transformers #123
Guidance is a high-level wrapper library that embeds prompt parameters through natural languages, and guidance combines a versatile of techniques that are able to spit out exact output schema to make LLM respond meets expected format
Guidance is a high-level wrapper library that embeds prompt parameters through natural languages, and guidance combines a versatile of techniques that are able to spit out exact output schema to make LLM respond meets expected format