![[Long Review] CLAS: Deep context: end-to-end contextual speech recognition](/media/video/2022/04/long-review-clas-deep-context-end-to-end-contextual-speech-recognition/preview.jpg)
![[Long Review] Hurdles to Progress in Long Form Question Answering](/media/video/2022/04/long-review-hurdles-to-progress-in-long-form-question-answering/preview.jpg)
![[Long Review] Finetuned Language Models Are Zero-Shot Learners](/media/video/2022/03/long-review-finetuned-language-models-are-zero-shot-learners/preview.jpg)
Tutorials
[长评] 经过微调的语言模型是零样本学习器
在 InstructGPT 将指令微调变成家喻户晓的术语之前，Google 的 FLAN 论文主张，通过对自然语言指令进行适度的多任务微调，可以将一个普通的 LM 变成一个出人意料的 c
![[Long Review] 'GShard': Scaling Giant Models with Conditional Computation and Automatic Sharding](/media/video/2022/02/long-review-gshard-scaling-giant-models-with-conditional-computation-and-automatic/preview.jpg)
Tutorials
[长评] 'GShard'：使用条件计算和自动分片扩展巨大模型
将 Transformer 扩展到数千亿参数以上会很快变成哲学问题：你是激活整个网络来处理每个 token，还是将每个 token 路由给真正需要看到它的专家？