精选理由
IBM开源了Granite 4.2系列模型，内置代理能力，规模大，功能强大，值得一看。
IBM推出Granite 4.2系列语言模型，包括3B、8B和30B三种规模，基于约1500亿个token训练，支持512,000个token的上下文窗口。大型模型采用'代理强化学习'训练，可自主学习工具使用和代码执行。所有模型均以Apache 2.0许可证开源。
原文 · Decoder
IBM drops open-weight Granite 4.2 family with built-in agentic capabilities under Apache 2.0
IBM is releasing its Granite 4.2 language models in 3B, 8B, and 30B sizes, trained on about 15 trillion tokens with a context window of up to 512,000 tokens. The larger models use "agentic RL" training to learn tool use and code execution on their own. All models are available under the Apache 2.0 license. The article IBM drops open-weight Granite 4.2 family with built-in agentic capabilities under Apache 2.0 appeared first on The Decoder .