cerebras/Kimi-Linear-REAP-35B-A3B-Instruct Text Generation • 35B • Updated about 1 month ago • 6.35k • 51
view post Post 3895 Starts erasing! 🎉 🎉 🎉 This is made with a one-step SD1.5 LBM [1] eraser !Data is open. Data pipeline is open. Training code is open. On our LBM fork : https://github.com/finegrain-ai/LBM[1] LBM: Latent Bridge Matching for Fast Image-to-Image Translation (2503.07535) See translation 1 reply · 👍 11 11 🔥 3 3 👀 1 1 + Reply
Cerebras REAP Collection Sparse MoE models compressed using REAP (Router-weighted Expert Activation Pruning) method • 17 items • Updated 19 days ago • 50