/external/2024/2024-03-14-fsdp-qlora-deep-dive 2024-03-14T00:00:00+00:00 /external/2024/2024-12-19-finally-replacement-for-bert 2024-12-19T00:00:00+00:00 /external/2025/2025-02-10-masked-language-models-zero-shot 2025-02-10T00:00:00+00:00 /external/2025/2025-11-14-openmidnight 2025-11-14T00:00:00+00:00 /external/2025/2025-12-22-medmarks_01 2025-12-22T00:00:00+00:00 /2021/07/19/benchmarking-pytorch-native-mish.html 2021-07-19T00:00:00+00:00 /2021/10/01/inference-with-fastai.html 2021-10-01T00:00:00+00:00 /2021/12/08/testing-amazon-sagemaker-studio-lab.html 2021-12-08T00:00:00+00:00 /2022/03/11/detecting-cloud-cover-via-satellite.html 2022-03-11T00:00:00+00:00 /2022/06/06/introducing-fastxtend.html 2022-06-06T00:00:00+00:00 /2022/06/14/debugging-pytorch-performance-decrease.html 2022-06-14T00:00:00+00:00 /2022/07/14/tinkering-with-attention-pooling.html 2022-07-14T00:00:00+00:00 /2022/08/07/remixed-art-history-with-stable-diffusion.html 2022-08-07T00:00:00+00:00 /2022/08/31/training-atari-agents-faster.html 2022-08-31T00:00:00+00:00 /2023/01/20/replicating-growing-cosine-unit.html 2023-01-20T00:00:00+00:00 /2023/05/10/quickly-finetune-transformers.html 2023-05-10T00:00:00+00:00 /2023/07/01/attention-mechanism.html 2023-07-01T00:00:00+00:00 /2023/07/28/rest-of-the-transformer.html 2023-07-28T00:00:00+00:00 /2023/08/16/flash-attention-compile.html 2023-08-16T00:00:00+00:00 /about.html / /papers.html /projects.html /all/all.html /all/page/2/all.html /all/page/3/all.html /all/page/4/all.html /posts/posts.html /posts/page/2/posts.html /posts/page/3/posts.html