Mike Lasby's picture

Mike Lasby

mklasby

·

mklasby

AI & ML interests

Efficient ML, sparse neural networks, quantization

Recent Activity

upvoted an article 1 day ago

A Review on the Evolvement of Load Balancing Strategy in MoE LLMs: Pitfalls and Lessons

updated a dataset about 1 month ago

mklasby/self-distill-qwen-qwen3-30b-a3b-theblackcat102-evol-codealpaca-v1

published a dataset about 1 month ago

mklasby/self-distill-qwen-qwen3-30b-a3b-theblackcat102-evol-codealpaca-v1

View all activity

Organizations

None yet

upvoted an article 1 day ago

Article

A Review on the Evolvement of Load Balancing Strategy in MoE LLMs: Pitfalls and Lessons

Feb 4, 2025

•

32

upvoted a collection 6 months ago

Cerebras REAP

Sparse MoE models compressed using REAP (Router-weighted Expert Activation Pruning) method • 30 items • Updated Feb 25 • 135

upvoted a collection 11 months ago

GLM-4-0414

GLM-4-0414 series model • 6 items • Updated Mar 2 • 135

upvoted a collection over 1 year ago

Sparse Foundational Llama 2 Models

Sparse pre-trained and fine-tuned Llama models made by Neural Magic + Cerebras • 27 items • Updated Apr 16, 2025 • 10

upvoted a paper over 2 years ago

QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models

Paper • 2310.16795 • Published Oct 25, 2023 • 27