Mobius Labs GmbH

company

https://www.mobiuslabs.com/

mobiusml

AI & ML interests

Computer Vision, LLMs, Multimodal Models, Model Compression

mobicham

updated a model 3 months ago

mobiuslabsgmbh/CLIP-ViT-H-14-laion2B-2bit_g16_s128-HQQ

Image Classification • Updated Aug 22 • 34 • 5

mobicham

updated a collection 3 months ago

Aana Episodic Finetunes

4 items • Updated Aug 2

appoose

posted an update over 1 year ago

Post

2114

Releasing HQQ Llama-3.1-70b 4-bit quantized version! Check it out at https://huggingface.co/mobiuslabsgmbh/Llama-3.1-70b-instruct_4bitgs64_hqq.

Achieves 99% of the base model performance across various benchmarks! Details in the model card.

appoose

posted an update over 1 year ago

Post

1801

Excited to announce the release of our high-quality Llama-3.1 8B 4-bit HQQ/calibrated quantized model! Achieving an impressive 99.3% relative performance to FP16, it also delivers the fastest inference speed for transformers.

https://huggingface.co/mobiuslabsgmbh/Llama-3.1-8b-instruct_4bitgs64_hqq_calib

1 reply

·

Jilt

updated a dataset over 1 year ago

mobiuslabsgmbh/youtube-commons-asr-eval

Viewer • Updated May 2, 2024 • 94 • 38 • 5

appoose

updated a Space over 1 year ago

README

Multimodal AI for the world's scale

mobicham

updated 5 models over 1 year ago

mobiuslabsgmbh/Llama-2-7b-chat-hf_2bitgs8_hqq

Text Generation • Updated Feb 5 • 60 • 36

mobiuslabsgmbh/aanaphi2-v0.1

Text Generation • 3B • Updated Mar 4, 2024 • 78 • 28

mobiuslabsgmbh/Mixtral-8x7B-Instruct-v0.1-hf-attn-4bit-moe-3bit-metaoffload-HQQ

Text Generation • Updated Feb 5 • 31 • 13

mobiuslabsgmbh/Mixtral-8x7B-Instruct-v0.1-hf-attn-4bit-moe-2bitgs8-metaoffload-HQQ

Text Generation • Updated Feb 5 • 27 • 19

mobiuslabsgmbh/Mixtral-8x7B-Instruct-v0.1-hf-attn-4bit-moe-2bit-metaoffload-HQQ

Text Generation • Updated Feb 5 • 30 • 16

mobicham

updated 6 models almost 2 years ago

mobiuslabsgmbh/Mixtral-8x7B-v0.1-hf-2bit_g16_s128-HQQ

Text Generation • Updated Feb 5 • 66 • 4

mobiuslabsgmbh/Mixtral-8x7B-v0.1-hf-attn-4bit-moe-2bit-HQQ

Text Generation • Updated Feb 5 • 29 • 7

mobiuslabsgmbh/Mixtral-8x7B-Instruct-v0.1-hf-2bit_g16_s128-HQQ

Text Generation • Updated Feb 5 • 61 • 9

mobiuslabsgmbh/Mixtral-8x7B-Instruct-v0.1-hf-attn-4bit-moe-2bit-HQQ

Text Generation • Updated Feb 5 • 34 • 38

mobiuslabsgmbh/Mixtral-8x7B-Instruct-v0.1-hf-4bit_g64-HQQ

Text Generation • Updated Feb 5 • 33 • 9

mobiuslabsgmbh/Mixtral-8x7B-v0.1-hf-4bit_g64-HQQ

Text Generation • Updated Feb 5 • 30 • 1