Sources
Loading...
Additional media
Loading...
DeepNewz, mobile.
People-sourced. AI-powered. Unbiased News.
Google releases Gemma 2: https://t.co/NUWMgjirNP
Gemma 2 is out with 9b and 27b! A few things I really liked in tech report: On pretraining: - GQA (finally lol) - interleaving global attn w local (but 4k vs. 8k? it feels like it should support longer and was kneecapped...) - 16x expansion ratio (very wide!) (1/n) https://t.co/3NEjzBoAg3
Gemma 2 released in 9B and 27B variants with faster inference and improved capabilities. i need to try this out and check if it tops llama3 actually or not https://t.co/QRJC0j8OZk https://t.co/QryiKVz7uX
Google has launched Gemma 2, a new AI model available in 9 billion and 27 billion parameter sizes. Gemma 2 is optimized for speed, offers great performance, and supports up to 8K context. It is released for researchers and developers globally, providing higher performance and efficiency compared to the first generation.