Compressed LMs

AI & ML interests

None defined yet.

Recent Activity

xzyao authored a paper about 1 month ago

Apertus 1.5: From Open Text Models to Open Multimodal Reasoners

xzyao authored a paper about 1 month ago

Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter

xzyao authored a paper about 1 year ago

Apertus: Democratizing Open and Compliant LLMs for Global Language Environments

View all activity

models 48

espressor/google.gemma-2b-it_W8A8_int8

Text Generation • 3B • Updated Dec 12, 2024 • 18

espressor/google.gemma-2b-it_W4A16

Text Generation • 3B • Updated Dec 12, 2024 • 11

espressor/google.gemma-2b-it_W8A8_FP8

Text Generation • 3B • Updated Dec 12, 2024 • 17

espressor/google.gemma-7b-it_W8A8_FP8

Text Generation • 9B • Updated Dec 12, 2024 • 18

espressor/google.gemma-2-9b-it_W8A8_FP8

Text Generation • 10B • Updated Dec 12, 2024 • 14

espressor/google.gemma-2-2b-it_W8A8_int8

Text Generation • 3B • Updated Dec 12, 2024 • 28

espressor/google.gemma-2-2b-it_W4A16

Text Generation • 3B • Updated Dec 12, 2024 • 8

espressor/google.gemma-2-2b-it_W8A8_FP8

Text Generation • 3B • Updated Dec 12, 2024 • 13

espressor/meta-llama.Llama-2-70b-chat-hf_W8A8_FP8

Text Generation • 69B • Updated Nov 28, 2024 • 25

espressor/meta-llama.Meta-Llama-3-70B-Instruct_W8A8_FP8

Text Generation • 71B • Updated Nov 28, 2024 • 21

datasets 1

espressor/calibration

Viewer • Updated Mar 26, 2024 • 188k • 39