LayerSkip - a facebook Collection

facebook 's Collections

Web-SSL

blt

Perception Encoder

DRAMA

Sparsh

Seamless Communication

MAGNeT

XLSR

XLS-R

Robust Wav2Vec 2.0

HuBERT

Fairseq S^2 TTS

Dinov2

MusicGen Stereo

Sapiens

OPT

FAIR's LayerSkip Llama models

LayerSkip

updated Nov 21, 2024

Models continually pretrained using LayerSkip - https://arxiv.org/abs/2404.16710

LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding

Paper • 2404.16710 • Published Apr 25, 2024 • 80
facebook/layerskip-llama2-7B

Text Generation • Updated Oct 19, 2024 • 4.21k • 14
facebook/layerskip-llama2-13B

Text Generation • Updated Oct 19, 2024 • 2.23k • 5
facebook/layerskip-llama2-70B

Text Generation • Updated Nov 3, 2024 • 628 • 4
facebook/layerskip-codellama-7B

Text Generation • Updated Oct 19, 2024 • 7 • 6
facebook/layerskip-codellama-34B

Text Generation • Updated Oct 19, 2024 • 566 • 4
facebook/layerskip-llama3-8B

Text Generation • Updated Oct 19, 2024 • 2.12k • 20
facebook/layerskip-llama3.2-1B

Text Generation • Updated Oct 26, 2024 • 4.99k • 21