Unified Latents (UL): How to train your latents Paper • 2602.17270 • Published 22 days ago • 57
Running on CPU Upgrade Featured 3.04k The Smol Training Playbook 📚 3.04k The secrets to building world-class LLMs
google/embeddinggemma-300m Sentence Similarity • 0.3B • Updated Sep 25, 2025 • 2.01M • • 1.51k
Multilingual CLIP Collection Models that can be used for multilingual Smart Search in Immich. See https://immich.app/docs/features/searching/#clip-models for more info. • 6 items • Updated Mar 31, 2025 • 19
Encoders vs Decoders: the Ettin Suite Collection A collection of SOTA, open-data, paired encoder-only and decoder only models ranging from 17M params to 1B. See the paper at https://arxiv.org/abs/250 • 30 items • Updated 11 days ago • 26
NeuralOS: Towards Simulating Operating Systems via Neural Generative Models Paper • 2507.08800 • Published Jul 11, 2025 • 81
MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention Paper • 2506.13585 • Published Jun 16, 2025 • 273