AI 精选动态
智能评分 60
Poolside 开源 Laguna M.1 模型权重
AI 推荐理由
这是首个采用 Apache 2.0 开源权重的 256K 上下文模型，值得关注其实际性能和生态影响。核心解读
Poolside 宣布开源其最强模型 Laguna M.1 的权重，支持 256K 上下文长度，采用 Apache 2.0 许可，base 和 post-trained 检查点已在 Hugging Face 上发布。
全文
AK (@_akhaliq) 转发了 clem 🤗 (@ClementDelangue) 的帖子：
"Open weights are now our default" https://huggingface.co/collections/poolside/laguna-m1
> **引用原帖 Poolside (@poolsideai):**
> Today we’re releasing the weights for Laguna M.1,
> our most capable model to date, with a 256K context length.
> Both base and post-trained checkpoints are now available on Hugging Face under Apache 2.0. https://t.co/gMWuYo8zN1
> https://x.com/poolsideai/status/2067623353230217448