20 Feb 2025
5m
技术揭秘 05」立地成佛，DeepSeek R1是如何“顿悟”出推理能力的？ ｜ChatGPT｜MLA多头潜在注意力｜MOE混合专家｜MTP多Token预测｜推理模型R1｜大模型LLM｜OpenAI
Wild AI Product Dog
Open in Podwise to generate AI notes
Sign in to process this episode and unlock summaries, transcripts, highlights and translations.
Shownotes are not generated by Podwise.