Sources
Loading...
Additional media
Loading...
DeepNewz, mobile.
People-sourced. AI-powered. Unbiased News.
GoogleDeepMind has announced the release of Gemma v1.1 IT models, addressing community feedback and introducing new RL algorithms. The models aim to improve instruction following, factuality, reasoning, and coding capabilities. The updated models include Gemma 1.1 Instruct 2B and 7B, with enhancements in multi-turn interactions and fixing previous issues.
SCREENSHOT to CODE https://t.co/zhnGvbsQII more to come... #SoftwareBuidlingSoftware #KeepOnCompounding https://t.co/NFwX2jweZG
CodeGemma is here! And it’s good. 🔨 Loving the 2B small model for code completion on device! https://t.co/8ytBZgFsot
CodeGemma 2B, 7B & 7B-it 💎 > pretty strong model, beats codellama 13B. > supports fill-in-the-middle (code completion), code generation and chat. > compatible with torch.compile() > optimised for speed, about ~1.5x faster than models in the similar category. > 2B model supports… https://t.co/dQtclciN5l