view article Article Apriel-1.6-15b-Thinker: Cost-efficient Frontier Multimodal Performance 17 days ago • 81
Trinity Collection Collection of Arcee AI models in the Trinity family • 8 items • Updated 14 days ago • 21
Derestricted Collection Models abliterated using Norm-Preserving Biprojected Abliteration • 6 items • Updated 16 days ago • 14
Pre-training Dataset Samples Collection A collection of pre-training datasets samples of sizes 10M, 100M and 1B tokens. Ideal for use in quick experimentation and ablations. • 19 items • Updated 1 day ago • 16
Jan-v2-VL Collection Jan-v2-VL: a family of VLM focused on reliable, many-step task execution. • 7 items • Updated 4 days ago • 38
Kimi Linear: An Expressive, Efficient Attention Architecture Paper • 2510.26692 • Published Oct 30 • 119
OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM Paper • 2510.15870 • Published Oct 17 • 89
Bee: A High-Quality Corpus and Full-Stack Suite to Unlock Advanced Fully Open MLLMs Paper • 2510.13795 • Published Oct 15 • 57
SINQ: Sinkhorn-Normalized Quantization for Calibration-Free Low-Precision LLM Weights Paper • 2509.22944 • Published Sep 26 • 79