Google releases Gemma 2 language model with improved performance, inference efficiency, and security

Odaily News Google announced the release of the Gemma 2 large language model for researchers and developers around the world. According to reports, Gemma 2 has two parameter sizes, 9 billion (9B) and 27 billion (27B). Compared with the first generation, it has higher performance, higher inference efficiency, and built-in significant security improvements. Google said that the performance of Gemma 2 27B is more competitive than similar products that are twice as large; the performance of 9B is also at the leading level of similar products, better than Llama 3 8B and other open models. (Jiemian News)