Commit Graph

  • a3a62c509a
    Improve MHA einsum (#781) main Jestine Paul 2025-08-23 04:12:26 +08:00
  • 670f7a4dd0
    - added (missing) Gemma3 bullet point in parent folder's readme.md (#788) casinca 2025-08-22 22:03:47 +02:00
  • 4a84cfccf9
    Minor cosmetic fixes in Gemma 3 nbs (#780) Sebastian Raschka 2025-08-19 21:08:29 -05:00
  • f571b5e493
    Add Gemma3 KV cache variant (#776) Sebastian Raschka 2025-08-19 12:37:49 -05:00
  • 8c1f9ccf54
    Improve MHA einsum (#775) Sebastian Raschka 2025-08-19 10:38:15 -05:00
  • 80d4732456
    add HF equivalency tests for standalone nbs (#774) Sebastian Raschka 2025-08-18 18:58:46 -05:00
  • a6b883c9f9
    Gemma 3 270M From Scratch (#771) Sebastian Raschka 2025-08-17 08:23:05 -05:00
  • 8fd29ed079
    Gemma 3 270M from scratch gemma-3 rasbt 2025-08-16 19:49:38 -05:00
  • e9c1c1da38
    Fix qk_norm comment (#769) Sebastian Raschka 2025-08-15 08:38:48 -05:00
  • 27fa95d24b Fix qk_norm comment (#769) Sebastian Raschka 2025-08-15 08:38:48 -05:00
  • b14325e56d
    Qwen3 and Llama3 equivalency teests with HF transformers (#768) Sebastian Raschka 2025-08-14 18:36:07 -05:00
  • 07c3122b5c Qwen3 and Llama3 equivalency teests with HF transformers (#768) Sebastian Raschka 2025-08-14 18:36:07 -05:00
  • 06aa6d470a
    Fix eos token usage in Qwen3 tokenizer fix-qwen3-tokeniizer-eos rasbt 2025-08-05 13:42:18 -05:00
  • 2e3205f747 MoE Nb readability improvements (#761) Sebastian Raschka 2025-08-01 19:58:18 -05:00
  • 5febcf8a1b
    MoE Nb readability improvements (#761) Sebastian Raschka 2025-08-01 19:58:18 -05:00
  • 71ef67be46 Qwen3 Coder Flash & MoE from Scratch (#760) Sebastian Raschka 2025-08-01 19:13:17 -05:00
  • f92b40e4ab
    Qwen3 Coder Flash & MoE from Scratch (#760) Sebastian Raschka 2025-08-01 19:13:17 -05:00
  • d6213a398a [Minor] Qwen3 typo & optim (#758) casinca 2025-07-29 00:29:44 +02:00
  • 145322ded8
    [Minor] Qwen3 typo & optim (#758) casinca 2025-07-29 00:29:44 +02:00
  • 4aa398c79d
    Comment typo: head_dim -> head_dim // 2 head-dim rasbt 2025-07-23 08:16:30 -05:00
  • 19c065b342 Interleaved Q and K for RoPE in Llama 2 (#750) Sebastian Raschka 2025-07-23 08:02:02 -05:00
  • b12dbf6c68
    Interleaved Q and K for RoPE in Llama 2 (#750) Sebastian Raschka 2025-07-23 08:02:02 -05:00
  • b74ab9611e Minor typo: pply -> Apply (#749) Sebastian Raschka 2025-07-22 08:19:25 -05:00
  • 13f049f6a4
    Minor typo: pply -> Apply (#749) Sebastian Raschka 2025-07-22 08:19:25 -05:00
  • 068751c053 Update Python dependency in pyproject.toml (#748) Sebastian Raschka 2025-07-22 08:03:57 -05:00
  • c6472f1af1
    Update Python dependency in pyproject.toml (#748) Sebastian Raschka 2025-07-22 08:03:57 -05:00
  • 38591b0049 get rid of redundant memory profiler import (#744) Sebastian Raschka 2025-07-16 07:36:51 -05:00
  • 3233ddc475
    get rid of redundant memory profiler import (#744) Sebastian Raschka 2025-07-16 07:36:51 -05:00
  • db3659241d Add link to official video course (#741) Sebastian Raschka 2025-07-13 10:35:12 -05:00
  • 7e9ce325de
    Add link to official video course (#741) Sebastian Raschka 2025-07-13 10:35:12 -05:00
  • 3d43a27ca9 Fix issue: 731 by resolving semantic error (#738) Matthew Hernandez 2025-07-10 14:30:15 -07:00
  • 6f12edb0cc
    Fix issue: 731 by resolving semantic error (#738) Matthew Hernandez 2025-07-10 14:30:15 -07:00
  • 1552023bd4
    Fix issue 724: unused args (#726) weezymatt-bugfix/semantic-error Matthew Hernandez 2025-07-08 04:37:39 -07:00
  • 5188a41267
    Batched KV Cache Inference for Qwen3 (#735) Sebastian Raschka 2025-07-10 08:09:35 -05:00
  • 6515889431
    Qwen3 tokenizer sanity checks (#730) Sebastian Raschka 2025-07-09 13:52:35 -05:00
  • 14fa50dfc8
    Add more sophisticated Qwen3 tokenizer (#729) Sebastian Raschka 2025-07-09 13:16:26 -05:00
  • f596aab0cb
    Simplify KV cache usage (#728) Sebastian Raschka 2025-07-08 12:56:55 -05:00
  • 4c2745509f
    Update Qwen3 tokenizer test (#727) Sebastian Raschka 2025-07-08 06:59:46 -05:00
  • 420081ae06
    fix merge conflict rasbt 2025-07-10 12:52:10 -05:00
  • a200698698 Batched KV Cache Inference for Qwen3 (#735) Sebastian Raschka 2025-07-10 08:09:35 -05:00
  • a354555049
    Batched KV Cache Inference for Qwen3 (#735) Sebastian Raschka 2025-07-10 08:09:35 -05:00
  • ede5cac208 Fix issue: 731 by resolving the semantic error 85853890+weezymatt@users.noreply.github.com 2025-07-09 21:24:27 -06:00
  • a96370df4a Fix issue: 731 by resolving the semantic error 85853890+weezymatt@users.noreply.github.com 2025-07-09 21:09:35 -06:00
  • 7dc1dcbe27 Qwen3 tokenizer sanity checks (#730) Sebastian Raschka 2025-07-09 13:52:35 -05:00
  • b8c8237251
    Qwen3 tokenizer sanity checks (#730) Sebastian Raschka 2025-07-09 13:52:35 -05:00
  • d23b1f07b8 Add more sophisticated Qwen3 tokenizer (#729) Sebastian Raschka 2025-07-09 13:16:26 -05:00
  • 21c41721cc
    Add more sophisticated Qwen3 tokenizer (#729) Sebastian Raschka 2025-07-09 13:16:26 -05:00
  • 90c824506c Simplify KV cache usage (#728) Sebastian Raschka 2025-07-08 12:56:55 -05:00
  • 3c9dc4807b
    Simplify KV cache usage (#728) Sebastian Raschka 2025-07-08 12:56:55 -05:00
  • b5bd8d2de2 Update Qwen3 tokenizer test (#727) Sebastian Raschka 2025-07-08 06:59:46 -05:00
  • 9cf64170ed
    Update Qwen3 tokenizer test (#727) Sebastian Raschka 2025-07-08 06:59:46 -05:00
  • 80c1bb2cf4 Fix issue 724: unused args (#726) Matthew Hernandez 2025-07-08 04:37:39 -07:00
  • 83c76891fc
    Fix issue 724: unused args (#726) Matthew Hernandez 2025-07-08 04:37:39 -07:00
  • ce24cd428a Update README.md Sebastian Raschka 2025-07-06 17:58:33 -05:00
  • c8c6e7814a
    Update README.md Sebastian Raschka 2025-07-06 17:58:33 -05:00
  • ab57562066 Add prerequisite section (#723) Sebastian Raschka 2025-07-06 12:45:42 -05:00
  • 6103acbedb
    Add prerequisite section (#723) Sebastian Raschka 2025-07-06 12:45:42 -05:00
  • 95a77a747a Fix pip uv typo in installation instructions (#722) Sebastian Raschka 2025-07-03 15:18:48 -05:00
  • c62fc7cad1
    Fix pip uv typo in installation instructions (#722) Sebastian Raschka 2025-07-03 15:18:48 -05:00
  • 30645a6d64 Handle other Qwen3 tokenizer settings (#716) Sebastian Raschka 2025-06-30 17:49:51 -05:00
  • 0405b0c8e7
    Handle other Qwen3 tokenizer settings (#716) Sebastian Raschka 2025-06-30 17:49:51 -05:00
  • 6a4d0a1022 Fix d_out code comment in bonus materials (#715) Sebastian Raschka 2025-06-28 10:07:16 -05:00
  • 4e61dc4224
    Fix d_out code comment in bonus materials (#715) Sebastian Raschka 2025-06-28 10:07:16 -05:00
  • dc2f8e95d4 Support different Qwen3 sizes in pkg (#714) Sebastian Raschka 2025-06-28 08:00:23 -05:00
  • c4ec55edac
    Support different Qwen3 sizes in pkg (#714) Sebastian Raschka 2025-06-28 08:00:23 -05:00
  • 8c8ff24118 Use test mode arg in ch07 (#713) Sebastian Raschka 2025-06-27 19:28:56 -05:00
  • ddbaf0d83e
    Use test mode arg in ch07 (#713) Sebastian Raschka 2025-06-27 19:28:56 -05:00
  • 9c666a4d94 Remove unused params for hparam script (#710) Sebastian Raschka 2025-06-25 12:50:32 -05:00
  • 8b3e4b24b0
    Remove unused params for hparam script (#710) Sebastian Raschka 2025-06-25 12:50:32 -05:00
  • 81be5fab0b Add Qwen3 1.7, 4B, 8B, and 32B support to from-scratch nb (#709) Sebastian Raschka 2025-06-25 08:53:09 -05:00
  • 190c66b3b0
    Add Qwen3 1.7, 4B, 8B, and 32B support to from-scratch nb (#709) Sebastian Raschka 2025-06-25 08:53:09 -05:00
  • 1bce95d70c Link the other KV cache sections (#708) Sebastian Raschka 2025-06-24 16:52:29 -05:00
  • 2f53bf5fe5
    Link the other KV cache sections (#708) Sebastian Raschka 2025-06-24 16:52:29 -05:00
  • cd03d5008a Add link to free exercise PDF (#706) Sebastian Raschka 2025-06-24 08:24:02 -05:00
  • 47a750014d
    Add link to free exercise PDF (#706) Sebastian Raschka 2025-06-24 08:24:02 -05:00
  • 28b5d4e8a6 Update Llama 3 table for consistency with Qwen3 Sebastian Raschka 2025-06-23 18:33:04 -05:00
  • 3bdf18a599
    Update Llama 3 table for consistency with Qwen3 Sebastian Raschka 2025-06-23 18:33:04 -05:00
  • 58b30e2f7b Improve KV cache code for torch.compile (#705) Sebastian Raschka 2025-06-23 18:08:49 -05:00
  • 81eda38d3b
    Improve KV cache code for torch.compile (#705) Sebastian Raschka 2025-06-23 18:08:49 -05:00
  • ad16b1fbee Fix bug in masking when kv cache is used. (#697) Martin Ma 2025-06-23 11:12:56 -07:00
  • 6522be94be
    Fix bug in masking when kv cache is used. (#697) Martin Ma 2025-06-23 11:12:56 -07:00
  • e9ffdbace4 CPU compile performance for Qwen3 models (#704) Sebastian Raschka 2025-06-23 11:06:10 -05:00
  • 37b26c2e04
    CPU compile performance for Qwen3 models (#704) Sebastian Raschka 2025-06-23 11:06:10 -05:00
  • d7c7393af7 Ch06 classifier function asserts (#703) Sebastian Raschka 2025-06-23 08:21:55 -05:00
  • 4014bdd520
    Ch06 classifier function asserts (#703) Sebastian Raschka 2025-06-23 08:21:55 -05:00
  • f051a5fe6b Update README.md (#702) Shamik 2025-06-23 17:51:51 +05:30
  • f5bc863752
    Update README.md (#702) Shamik 2025-06-23 17:51:51 +05:30
  • f3fadd6c0a Fix issue #684: Minor docstring edit (#699) Matthew Hernandez 2025-06-23 05:18:28 -07:00
  • 5c66f74fbe
    Fix issue #684: Minor docstring edit (#699) Matthew Hernandez 2025-06-23 05:18:28 -07:00
  • 713a6e24c9
    add tests fix_masking_kv_cache rasbt 2025-06-22 17:48:23 -05:00
  • 984cca3f64 Fix code comment: embed_dim -> d_out (#698) Sebastian Raschka 2025-06-22 16:36:39 -05:00
  • d37ddb668a
    Fix code comment: embed_dim -> d_out (#698) Sebastian Raschka 2025-06-22 16:36:39 -05:00
  • ffc5e4e5d6 Fix bug in masking when kv cache is used. martinzwm 2025-06-22 14:06:00 -07:00
  • a5ea296259 Use more recent sentencepiece tokenizer API (#696) Sebastian Raschka 2025-06-22 13:52:30 -05:00
  • 01be5a42e4
    Use more recent sentencepiece tokenizer API (#696) Sebastian Raschka 2025-06-22 13:52:30 -05:00
  • 2351a1f282 Fix some wording issues in the notes (#695) Sebastian Raschka 2025-06-22 13:46:16 -05:00
  • bcfdbd7008
    Fix some wording issues in the notes (#695) Sebastian Raschka 2025-06-22 13:46:16 -05:00
  • cfdf22330b Fix: Typo in appendix_d.py comments. (#682) Sajjad Baloch 2025-06-22 10:15:12 -07:00
  • 661a6e84ee
    Fix: Typo in appendix_d.py comments. (#682) Sajjad Baloch 2025-06-22 10:15:12 -07:00
  • c4b19d7eb6 fix issue #664 - inverted token and pos emb layers (#665) casinca 2025-06-22 19:15:01 +02:00