view article Article Harness, Scaffold, and the AI Agent Terms Worth Getting Right sergiopaniego, ariG23498 • 4 days ago • 73
Zagreus 0.4B Collection The Zagreus-0.4B collection contains four bilingual English + Romance language foundational SLMs (~400M parameters) trained from scratch • 4 items • Updated Mar 4 • 7
Numina-Lean-Agent: An Open and General Agentic Reasoning System for Formal Mathematics Paper • 2601.14027 • Published Jan 20 • 14
Qwen-3.6-unsloth-mlx Collection AWQ-style pre-scaling using Unsloth's imatrix calibration data, then 3-6-bit affine quantization with the Unsloth mixed-precision recipe via MLX • 18 items • Updated 13 days ago • 19
view article Article DeepSeek-V4: a million-token context that agents can actually use burtenshaw • Apr 24 • 47
DeltaTok Collection DeltaTok tokenizer, DeltaWorld predictor, and evaluation heads. https://github.com/amazon-far/deltatok • 7 items • Updated Apr 8 • 8
view article Article Training and Finetuning Multimodal Embedding & Reranker Models with Sentence Transformers tomaarsen • Apr 16 • 71
VidEoMT: Your ViT is Secretly Also a Video Segmentation Model Paper • 2602.17807 • Published Feb 19 • 7
view article Article How I contributed a new model to the Transformers library using Codex nielsr • Mar 30 • 52
MolmoWeb Collection This is the collection of MolmoWeb artifacts, including model checkpoints and data. • 8 items • Updated Apr 13 • 25
OpenResearcher Collection OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis • 8 items • Updated Mar 24 • 18
view article Article Nemotron 3 Nano 4B: A Compact Hybrid Model for Efficient Local AI nvidia • Mar 17 • 65