Support for Sparse MoE models like Camelidae and Sparsetral
#5365 aperta il 6 feb 2024
Metriche repository
- Star
- (110.169 star)
- Metriche merge PR
- (Merge medio 6g 8h) (389 PR mergiate in 30 g)
Descrizione
A new technique for broadening the capabilities of LLMs without massively increasing resource requirements has recently emerged. Instead of shuffling tokens in between expert models like a standard MoE, it shuffles them between expert LoRAs. This gives much of the benefit of a MoE, but with very low memory and compute requirements above what is needed by the base model. Please consider adding support for inferencing and quantizing these sparse MoEs, as they are a very promising branch of LLMs that can be not only inferenced but fully trained on attainable consumer hardware.
Camelidae on HF: https://huggingface.co/hywu
Sparsetral on HF:https://huggingface.co/serpdotai/sparsetral-16x7B-v2