Google Gemma 2 Series adds 2 billion parameter models
lwh7654321
发表于 2024-8-1 14:21:34
3505
0
0
On July 31st local time, Google announced the addition of a new small model, Gemma 2B (with 2 billion parameters), to the Gemma 2 series. In the LMSYS Chatbot Arena, Gemma 2B scored higher than GPT-3.5-Turbo. The security content classifier model ShieldGemma and the model interpretability tool Gemma Scope, which were launched together with Gemma 2B. Gemma 2 is an open-source model from Google. In June of this year, Google released the Gemma 2 series, including Gemma 2 27B and 9B.
CandyLake.com 系信息发布平台,仅提供信息存储空间服务。
声明:该文观点仅代表作者本人,本文不代表CandyLake.com立场,且不构成建议,请谨慎对待。
声明:该文观点仅代表作者本人,本文不代表CandyLake.com立场,且不构成建议,请谨慎对待。
猜你喜欢
- Meta releases new AI model: capable of self checking and reviewing the work of other AI models
- Huaqiangbei Merchant: iPhone 16 All Models Breakthrough
- Apple iPhone 16 Series Sales Drop 1% YoY in Four Weeks of First Release in the US
- Xiaopeng Motors announces launch of chip upgrade crowdfunding for different car models: successful, immediately developed, failed, original refund
- The delivery volume of Jike 7X model exceeds 20000
- The delivery volume of Jike 7X model exceeds 25000 units
- Minsheng Securities releases overseas gold stock observation report: Eagle Mining is a model of successful mergers and acquisitions; Multiple exploration projects with great growth potential
- Google launches a reasoning model similar to OpenAI o1
- Qifu Technology's financial AI big model achievements have officially landed
- Ideal car Li Xiang: Big models will fundamentally change humanity