NVIDIA AI· @NVIDIAAI · X·· 10 小时前精选AI 评分80
AI 导读
ReflectionAI 发布首个开源权重模型 Beam，采用 Apache 2.0 许可，并与 40 多家合作伙伴共同推进。该模型为 501B MoE，在 NVIDIA GB300 NVL72 上训练，在 Blackwell Ultra 上开箱即达 70K tokens/sec/GPU。发布内容包括权重、tokenizer 与参考实现，BF16、FP8、NVFP4 权重及 DFlash2 drafter，以及训练所用的开源 harness Mirror CLI，权重和模型卡已上线 Hugging Face。
推荐理由
ReflectionAI 首个开源权重模型 Beam 的发布信息，含 501B MoE 规模与 GB300 NVL72 训练、Blackwell Ultra 上 70K tokens/sec/GPU 的部署数据。
正文
Welcome Beam!
Congrats to @ReflectionAI on launching their first open-weight model.
The 501B MoE model was trained on NVIDIA GB300 NVL72 and delivers over 70K tokens/sec/GPU on Blackwell Ultra out of the box on day 0.
🤗 Beam 1.0 NVFP4 checkpoint on @huggingface: https://huggingface.co/reflection/Beam-1.0-501B-A23B-NVFP4
Beam is now available across platforms, with open weights under the Apache 2.0 license - in collaboration with an ecosystem of 40+ partners. We're releasing: - Weights, tokenizer, and reference implementation - BF16, FP8 and NVFP4 weights and a DFlash2 drafter - The open source harness we built and trained Beam on: Mirror CLI Weights and model card on Hugging Face: https://huggingface.co/reflection在 X 查看被引用的帖子
来源：NVIDIA AI · x.com