Vladimir's picture

2 3 1

Vladimir

galqiwi

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 2 days ago

HALO: Hadamard-Assisted Lossless Optimization for Efficient Low-Precision LLM Training and Fine-Tuning

upvoted a paper 2 days ago

QuEST: Stable Training of LLMs with 1-Bit Weights and Activations

updated a model about 2 months ago

galqiwi/llama-3.2-3b-aqlm-pv-2x8-f32-int8-and-nf4-emb

View all activity

Organizations

galqiwi's activity

upvoted 2 papers 2 days ago

HALO: Hadamard-Assisted Lossless Optimization for Efficient Low-Precision LLM Training and Fine-Tuning

Paper • 2501.02625 • Published Jan 5 • 16

QuEST: Stable Training of LLMs with 1-Bit Weights and Activations

Paper • 2502.05003 • Published 5 days ago • 38

upvoted a collection 5 months ago

AQLM+PV

Official AQLM quantizations for "PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression": https://arxiv.org/abs/2405.14852 • 25 items • Updated Dec 18, 2024 • 20