Commit Graph

  • 74e04a9169 Add "What's next" section (#432) Sebastian Raschka 2024-11-07 20:12:59 -06:00
  • f4ed263847 Add "What's next" section (#432) Sebastian Raschka 2024-11-07 20:12:59 -06:00
  • 5348565e0f add dropout scaling note rasbt 2024-11-06 05:52:47 -06:00
  • 1183fd7837 add dropout scaling note rasbt 2024-11-06 05:52:47 -06:00
  • 2fd07e2cfd potential little fixes appendix-D4 .ipynb (#427) casinca 2024-11-03 19:12:58 +01:00
  • 9ce0be333b potential little fixes appendix-D4 .ipynb (#427) casinca 2024-11-03 19:12:58 +01:00
  • 95f8a4084f Update CITATION.cff Sebastian Raschka 2024-11-01 21:32:17 -05:00
  • ba3137fa2c Update CITATION.cff Sebastian Raschka 2024-11-01 21:32:17 -05:00
  • 9d2fd4c22e Update CITATION.cff Sebastian Raschka 2024-11-01 21:29:22 -05:00
  • 734f36aac1 Update CITATION.cff Sebastian Raschka 2024-11-01 21:29:22 -05:00
  • 81e78d0ad8 Add citation file rasbt 2024-11-01 21:21:25 -05:00
  • 7553e87af0 Add citation file rasbt 2024-11-01 21:21:25 -05:00
  • 50500e94b5 Note about warm-up steps rasbt 2024-11-01 16:47:12 -05:00
  • f03f545a17 Note about warm-up steps rasbt 2024-11-01 16:47:12 -05:00
  • 7e6f8ce020 updated RoPE statement (#423) Daniel Kleine 2024-10-30 14:00:08 +01:00
  • 81eed9afe2 updated RoPE statement (#423) Daniel Kleine 2024-10-30 14:00:08 +01:00
  • 62e44b2415 Update README.md Sebastian Raschka 2024-10-29 20:20:48 -05:00
  • b5f2aa3500 Update README.md Sebastian Raschka 2024-10-29 20:20:48 -05:00
  • e85d154522 Fix argument name in LlamaTokenizer constructor (#421) ROHAN WINSOR 2024-10-30 04:31:36 +05:30
  • cd24a27161 Fix argument name in LlamaTokenizer constructor (#421) ROHAN WINSOR 2024-10-30 04:31:36 +05:30
  • 2b24a7ef30 minor fixes: Llama 3.2 standalone (#420) Daniel Kleine 2024-10-26 04:08:06 +02:00
  • e8c2f962e9 minor fixes: Llama 3.2 standalone (#420) Daniel Kleine 2024-10-26 04:08:06 +02:00
  • 75ede3e340 RoPE theta rescaling (#419) Sebastian Raschka 2024-10-25 15:27:23 -05:00
  • 1516de54a5 RoPE theta rescaling (#419) Sebastian Raschka 2024-10-25 15:27:23 -05:00
  • 0ed1e0d099 fixed typos (#414) Daniel Kleine 2024-10-25 01:23:53 +02:00
  • 5ff72c2850 fixed typos (#414) Daniel Kleine 2024-10-25 01:23:53 +02:00
  • 8b60460319 Updated Llama 2 to 3 paths (#413) Daniel Kleine 2024-10-24 14:40:08 +02:00
  • d38083c401 Updated Llama 2 to 3 paths (#413) Daniel Kleine 2024-10-24 14:40:08 +02:00
  • 632d7772b2 Update test-requirements-extra.txt Sebastian Raschka 2024-10-23 19:19:58 -05:00
  • e1dfd2cb7a Update test-requirements-extra.txt Sebastian Raschka 2024-10-23 19:19:58 -05:00
  • f8bdfe12e1 RoPE updates (#412) Sebastian Raschka 2024-10-23 18:07:49 -05:00
  • 7cd6a670ed RoPE updates (#412) Sebastian Raschka 2024-10-23 18:07:49 -05:00
  • 6dd3fbd79d Update tests.py Sebastian Raschka 2024-10-23 07:48:33 -05:00
  • 4f9c9fb703 Update tests.py Sebastian Raschka 2024-10-23 07:48:33 -05:00
  • cba4f89514 updates for PyTorch 2.5 (#408) Daniel Kleine 2024-10-23 03:23:31 +02:00
  • ef4018181e updates for PyTorch 2.5 (#408) Daniel Kleine 2024-10-23 03:23:31 +02:00
  • 9726ca6546 RoPE increase (#407) Sebastian Raschka 2024-10-21 19:58:38 -05:00
  • 534a704364 RoPE increase (#407) Sebastian Raschka 2024-10-21 19:58:38 -05:00
  • 208d8030c9 Set sampler in DDP example Sebastian Raschka 2024-10-21 09:26:01 -05:00
  • 75133605c5 Set sampler in DDP example Sebastian Raschka 2024-10-21 09:26:01 -05:00
  • 3c3dae0967 Add mean pooling experiment to classifier bonus experiments (#406) Sebastian Raschka 2024-10-20 11:04:18 -05:00
  • 38969864e6 Add mean pooling experiment to classifier bonus experiments (#406) Sebastian Raschka 2024-10-20 11:04:18 -05:00
  • c4bac22bff Test PyTorch 2.5 (#405) Sebastian Raschka 2024-10-20 10:23:31 -05:00
  • 467197bbf5 Test PyTorch 2.5 (#405) Sebastian Raschka 2024-10-20 10:23:31 -05:00
  • 42b703fc0b Note about SSL certificates (#404) Sebastian Raschka 2024-10-19 16:27:19 -05:00
  • 1f61aeb7c4 Note about SSL certificates (#404) Sebastian Raschka 2024-10-19 16:27:19 -05:00
  • 3567fb656d update mmap section rasbt 2024-10-14 14:27:19 -05:00
  • cd2753a36d update mmap section rasbt 2024-10-14 14:27:19 -05:00
  • 31fb74133a add mmap=True comparison rasbt 2024-10-14 11:09:55 -05:00
  • 08362fd290 add mmap=True comparison rasbt 2024-10-14 11:09:55 -05:00
  • 3d54af20f5 Memory efficient weight loading (#401) Sebastian Raschka 2024-10-14 10:30:25 -05:00
  • 05b04f2a5a Memory efficient weight loading (#401) Sebastian Raschka 2024-10-14 10:30:25 -05:00
  • 59a5c83726 remove redundant code line rasbt 2024-10-13 15:58:11 -05:00
  • a20ce1b817 remove redundant code line rasbt 2024-10-13 15:58:11 -05:00
  • 6a9bedc2ec Update bonus section formatting (#400) Sebastian Raschka 2024-10-12 10:26:08 -05:00
  • b6c4b2f9f1 Update bonus section formatting (#400) Sebastian Raschka 2024-10-12 10:26:08 -05:00
  • 35ecca0feb Update check-links.yml Sebastian Raschka 2024-10-11 12:20:49 -05:00
  • 233a3b0c8b Update check-links.yml Sebastian Raschka 2024-10-11 12:20:49 -05:00
  • 76d0807eab update card rasbt 2024-10-11 12:15:01 -05:00
  • 93d9dae95f update card rasbt 2024-10-11 12:15:01 -05:00
  • c36f623472 update reference numbers rasbt 2024-10-11 12:12:05 -05:00
  • 1f4fca9f8e update reference numbers rasbt 2024-10-11 12:12:05 -05:00
  • b66d846cf6 Add MFU formula as reference material (#395) Sebastian Raschka 2024-10-10 19:42:53 -05:00
  • 6d0f59a49c Add MFU formula as reference material (#395) Sebastian Raschka 2024-10-10 19:42:53 -05:00
  • 1715aaacbc Update check-links.yml Sebastian Raschka 2024-10-08 08:38:48 -05:00
  • 1a8d2929dd Update check-links.yml Sebastian Raschka 2024-10-08 08:38:48 -05:00
  • 37db3f0913 Add Llama 3.2 RoPE to CI (#391) Sebastian Raschka 2024-10-08 08:28:34 -05:00
  • ec18b6a8a3 Add Llama 3.2 RoPE to CI (#391) Sebastian Raschka 2024-10-08 08:28:34 -05:00
  • 06604f4b84 Introduce buffers to improve Llama 3.2 efficiency (#389) Sebastian Raschka 2024-10-06 12:49:04 -05:00
  • 1eb0b3810a Introduce buffers to improve Llama 3.2 efficiency (#389) Sebastian Raschka 2024-10-06 12:49:04 -05:00
  • 4f9775d91c fixed Llama 2 to 3.2 NBs (#388) Daniel Kleine 2024-10-06 16:56:55 +02:00
  • a0c0c765a8 fixed Llama 2 to 3.2 NBs (#388) Daniel Kleine 2024-10-06 16:56:55 +02:00
  • 81053ccadd Add a note about weight tying in Llama 3.2 (#386) Sebastian Raschka 2024-10-05 09:20:54 -05:00
  • 0972ded530 Add a note about weight tying in Llama 3.2 (#386) Sebastian Raschka 2024-10-05 09:20:54 -05:00
  • 58c3bb3d9d Llama 3 (#384) Sebastian Raschka 2024-10-05 07:52:15 -05:00
  • 8a448a4410 Llama 3 (#384) Sebastian Raschka 2024-10-05 07:52:15 -05:00
  • 8d6b25785d Llama 3.2 requirements file Sebastian Raschka 2024-10-05 07:32:43 -05:00
  • 8553644440 Llama 3.2 requirements file Sebastian Raschka 2024-10-05 07:32:43 -05:00
  • 6f86c78763 Implement Llama 3.2 (#383) Sebastian Raschka 2024-10-05 07:30:47 -05:00
  • b44096acef Implement Llama 3.2 (#383) Sebastian Raschka 2024-10-05 07:30:47 -05:00
  • d313f61c86 Cos-sin fix in Llama 2 bonus notebook (#381) Sebastian Raschka 2024-10-03 20:45:40 -05:00
  • a5405c255d Cos-sin fix in Llama 2 bonus notebook (#381) Sebastian Raschka 2024-10-03 20:45:40 -05:00
  • feb0647c79 Improve rope settings for llama3 (#380) Sebastian Raschka 2024-10-03 08:29:54 -05:00
  • b993c2b25b Improve rope settings for llama3 (#380) Sebastian Raschka 2024-10-03 08:29:54 -05:00
  • 2ae4ad15ba add section numbers rasbt 2024-09-30 08:42:22 -05:00
  • 278a50a348 add section numbers rasbt 2024-09-30 08:42:22 -05:00
  • 505e9a5fa5 Improve DDP on Windows (#376) Sebastian Raschka 2024-09-29 16:53:48 -05:00
  • 4caafddb93 Improve DDP on Windows (#376) Sebastian Raschka 2024-09-29 16:53:48 -05:00
  • 58d0ce83a4 llama note rasbt 2024-09-26 07:41:11 -05:00
  • bfa4215774 llama note rasbt 2024-09-26 07:41:11 -05:00
  • 68505fab64 Fix truncation issue in classify_review function (#373) Sebastian Raschka 2024-09-25 19:54:36 -05:00
  • 7ef5129e18 Fix truncation issue in classify_review function (#373) Sebastian Raschka 2024-09-25 19:54:36 -05:00
  • b8497c1bf5 Add llama2 unit tests (#372) Sebastian Raschka 2024-09-25 19:40:36 -05:00
  • b56d0b2942 Add llama2 unit tests (#372) Sebastian Raschka 2024-09-25 19:40:36 -05:00
  • a23fca84d5 improve formatting rasbt 2024-09-24 18:49:17 -05:00
  • a6d8e93da3 improve formatting rasbt 2024-09-24 18:49:17 -05:00
  • 4541177063 ch05/07 gpt_to_llama text improvements (#369) Daniel Kleine 2024-09-25 01:45:49 +02:00
  • ff31b345b0 ch05/07 gpt_to_llama text improvements (#369) Daniel Kleine 2024-09-25 01:45:49 +02:00
  • 941629d2c7 add json import rasbt 2024-09-23 09:12:31 -05:00
  • d144bd5b7a add json import rasbt 2024-09-23 09:12:31 -05:00