Infatoshi/DeepSeek-V4.1-Flash-1017-MXFP4-uncensored Text Generation • 763B • Updated 14 days ago • 1.35k • 52
view article Article The Chinese GLM-5 Model Now Ranks #2 in Arabic Language Performance silma-ai • Feb 16 • 5
Cerebras REAP Collection Sparse MoE models compressed using REAP (Router-weighted Expert Activation Pruning) method • 30 items • Updated Feb 25 • 154