Reflection 发布 501B 开源权重模型 Beam
Beam: Reflection's 501B open-weight model
Reflection 发布 Beam，一个 5010 亿总参数、230 亿激活参数的稀疏 MoE 开源权重模型，面向编程、推理和 agentic 工作负载。该模型在 23.8 万亿 token 上预训练，并在 10.5K 张 NVIDIA GB300 GPU 上用 4 周完成超过 1 亿次 rollout 的高算力 RL 训练。目前仅开放早期访问注册，未公布权重和技术细节。
> Beam is a sparse Mixture-of-Experts model with 501 billion total parameters, 23 billion active, built for coding, reasoning, and agentic workloads.
> Beam’s capabilities come from major investments in both pretraining and reinforcement learning (RL). We pretrained the model on 23.8 trillion diverse, curated, high-quality tokens from the web and proprietary licensed datasets, matching or outperforming available similar-sized open base models. In parallel, we developed the algorithms, training environments, and infrastructure needed to sustain high-compute RL at exceptional scale. Our high-compute RL run generated over 100 million rollouts on 10.5K NVIDIA GB300 GPUs over 4 weeks of training.
Early access, no weights no tech details, just a sign up here for info
来源：Hacker News · 首页 · news.ycombinator.com