ggml-org/llama.cpp

Support for Sparse MoE models like Camelidae and Sparsetral

Open

#5365 aperta il 6 feb 2024

Vedi su GitHub
 (6 commenti) (35 reazioni) (0 assegnatari)C++ (18.202 fork)batch import
enhancementgood first issue

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

Guida contributor