🔄 In a Training Loop

Joel Wang

joelhenwang

·

joelhenwang

AI & ML interests

None yet

Recent Activity

upvoted a paper 2 days ago

When Losses Align: Gradient-Based Composite Loss Weighting for Efficient Pretraining

upvoted a paper 3 days ago

RoPE-Aware Bit Allocation for KV-Cache Quantization

upvoted an article 4 days ago

Kog Laneformer 2B: The Latency-First Model Behind Kog Inference Engine

View all activity

Organizations

models 3

joelhenwang/OdinNext-138M-Instruct

Text Generation • 0.1B • Updated 20 days ago • 108 • 5

joelhenwang/OdinNext-138M-Base

Text Generation • 0.1B • Updated 20 days ago • 149 • 2

joelhenwang/OdinNext-138M-Early-Checkpoint

Text Generation • 0.2B • Updated May 28 • 7

datasets 1

joelhenwang/comt

Preview • Updated Feb 27 • 47