2 6 16

Shaij PRO

appoose

AI & ML interests

None yet

Organizations

Posts 2

Post

2056

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

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

Post

1786

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.

mobiuslabsgmbh/Llama-3.1-8b-instruct_4bitgs64_hqq_calib

spaces 1

No application file

🐠

MobiusSearch

models 1

appoose/aana-soccer-no-pretraining-weight-balanced-2_2.0_720-combined-finetuned

Updated May 30

datasets

None public yet