TGTGInsighttelegram intelligenceLIVE / telegram public index
TGINSIGHT POST
Post #957
@LinghaoCh
Parallel Experiments
Post content
Post content
https://huggingface.co/blog/smollm3 Hugging Face 发布 SmolLM3，一个 3B 小模型。他们非常慷慨地提供了完整的技术细节，从 model architecture 和 data mixture 到 pre/mid/post training 的多个 recipe 🫡