Cohere Labs releases Tiny Aya L2-Thinker for in-language reasoning across 60 languages
The 3.35B open-weight research model is trained to keep reasoning in the user’s language, combining English…
Read storyDAILY EDITION
6 source-linked reports.
Follow Open Model Weights on Google See more of our open-weight AI reporting in Google Search.
The 3.35B open-weight research model is trained to keep reasoning in the user’s language, combining English…
Read storyThe 740M-parameter Apache-2.0 model maps text, code, images, video and audio into one embedding space, with…
Read storyHugging Face’s October 6 release adds Google’s multimodal EmbeddingGemma 2 architecture, makes token-dispatch…
Read storyThe October 5 serving release adds a GPU-resident weight-cache daemon, experimental initialized-engine…
Read storyThe official Index-Translate GGUF repository packages llama.cpp conversions from Q2_K through F16 for the…
Read storyCoreAI’s pipeline turns observed agent failures into executable training tasks, uses a stronger teacher to…
Read story