rasbt
|
8fd29ed079
|
Gemma 3 270M from scratch
|
2025-08-16 19:49:38 -05:00 |
|
Sebastian Raschka
|
27fa95d24b
|
Fix qk_norm comment (#769)
|
2025-08-15 08:38:48 -05:00 |
|
Sebastian Raschka
|
07c3122b5c
|
Qwen3 and Llama3 equivalency teests with HF transformers (#768)
* Qwen3 and Llama3 equivalency teests with HF transformers
* update
|
2025-08-14 18:36:07 -05:00 |
|
Sebastian Raschka
|
2e3205f747
|
MoE Nb readability improvements (#761)
|
2025-08-01 19:58:18 -05:00 |
|
Sebastian Raschka
|
71ef67be46
|
Qwen3 Coder Flash & MoE from Scratch (#760)
* Qwen3 Coder Flash & MoE from Scratch
* update
* refinements
* updates
* update
* update
* update
|
2025-08-01 19:13:17 -05:00 |
|
casinca
|
d6213a398a
|
[Minor] Qwen3 typo & optim (#758)
* typo
* remove weight dict after loading
|
2025-07-28 17:29:44 -05:00 |
|
Sebastian Raschka
|
19c065b342
|
Interleaved Q and K for RoPE in Llama 2 (#750)
|
2025-07-23 08:02:02 -05:00 |
|
Sebastian Raschka
|
b74ab9611e
|
Minor typo: pply -> Apply (#749)
|
2025-07-22 08:19:25 -05:00 |
|
Sebastian Raschka
|
068751c053
|
Update Python dependency in pyproject.toml (#748)
|
2025-07-22 08:03:57 -05:00 |
|
Sebastian Raschka
|
38591b0049
|
get rid of redundant memory profiler import (#744)
|
2025-07-16 07:36:51 -05:00 |
|
Sebastian Raschka
|
db3659241d
|
Add link to official video course (#741)
|
2025-07-13 10:35:12 -05:00 |
|
Matthew Hernandez
|
3d43a27ca9
|
Fix issue: 731 by resolving semantic error (#738)
* fix issue 731
* update test path
---------
Co-authored-by: rasbt <mail@sebastianraschka.com>
|
2025-07-10 16:30:15 -05:00 |
|
Sebastian Raschka
|
a200698698
|
Batched KV Cache Inference for Qwen3 (#735)
|
2025-07-10 08:09:35 -05:00 |
|
Sebastian Raschka
|
7dc1dcbe27
|
Qwen3 tokenizer sanity checks (#730)
|
2025-07-09 13:52:35 -05:00 |
|
Sebastian Raschka
|
d23b1f07b8
|
Add more sophisticated Qwen3 tokenizer (#729)
|
2025-07-09 13:16:26 -05:00 |
|
Sebastian Raschka
|
90c824506c
|
Simplify KV cache usage (#728)
* Simplify KV cache usage
* Swap mark text with ghostwriter
|
2025-07-08 12:56:55 -05:00 |
|
Sebastian Raschka
|
b5bd8d2de2
|
Update Qwen3 tokenizer test (#727)
* Update Qwen3 tokenizer test
* add tokenizers to dev dependencies
* add tokenizers to dev dependencies
|
2025-07-08 06:59:46 -05:00 |
|
Matthew Hernandez
|
80c1bb2cf4
|
Fix issue 724: unused args (#726)
* Fix issue 724: unused args
* Update 02_opt_multi_gpu_ddp.py
|
2025-07-08 06:37:39 -05:00 |
|
Sebastian Raschka
|
ce24cd428a
|
Update README.md
|
2025-07-06 17:58:33 -05:00 |
|
Sebastian Raschka
|
ab57562066
|
Add prerequisite section (#723)
|
2025-07-06 12:45:42 -05:00 |
|
Sebastian Raschka
|
95a77a747a
|
Fix pip uv typo in installation instructions (#722)
|
2025-07-03 15:18:48 -05:00 |
|
Sebastian Raschka
|
30645a6d64
|
Handle other Qwen3 tokenizer settings (#716)
|
2025-06-30 17:49:51 -05:00 |
|
Sebastian Raschka
|
6a4d0a1022
|
Fix d_out code comment in bonus materials (#715)
|
2025-06-28 10:07:16 -05:00 |
|
Sebastian Raschka
|
dc2f8e95d4
|
Support different Qwen3 sizes in pkg (#714)
|
2025-06-28 08:00:23 -05:00 |
|
Sebastian Raschka
|
8c8ff24118
|
Use test mode arg in ch07 (#713)
|
2025-06-27 19:28:56 -05:00 |
|
Sebastian Raschka
|
9c666a4d94
|
Remove unused params for hparam script (#710)
|
2025-06-25 12:50:32 -05:00 |
|
Sebastian Raschka
|
81be5fab0b
|
Add Qwen3 1.7, 4B, 8B, and 32B support to from-scratch nb (#709)
|
2025-06-25 08:53:09 -05:00 |
|
Sebastian Raschka
|
1bce95d70c
|
Link the other KV cache sections (#708)
|
2025-06-24 16:52:29 -05:00 |
|
Sebastian Raschka
|
cd03d5008a
|
Add link to free exercise PDF (#706)
|
2025-06-24 08:24:02 -05:00 |
|
Sebastian Raschka
|
28b5d4e8a6
|
Update Llama 3 table for consistency with Qwen3
|
2025-06-23 18:33:04 -05:00 |
|
Sebastian Raschka
|
58b30e2f7b
|
Improve KV cache code for torch.compile (#705)
* Improve KV cache code for torch.compile
* cleanup
* cleanup
|
2025-06-23 18:08:49 -05:00 |
|
Martin Ma
|
ad16b1fbee
|
Fix bug in masking when kv cache is used. (#697)
* Fix bug in masking when kv cache is used.
* add tests
* dd tests
* upd
* add kv cache test to gh workflow
* explicit mask slicing
* upd
---------
Co-authored-by: rasbt <mail@sebastianraschka.com>
|
2025-06-23 13:12:56 -05:00 |
|
Sebastian Raschka
|
e9ffdbace4
|
CPU compile performance for Qwen3 models (#704)
* Ch06 classifier function asserts
* Qwen3 cpu compilation perf
|
2025-06-23 11:06:10 -05:00 |
|
Sebastian Raschka
|
d7c7393af7
|
Ch06 classifier function asserts (#703)
|
2025-06-23 08:21:55 -05:00 |
|
Shamik
|
f051a5fe6b
|
Update README.md (#702)
Typo in kv cache readme
|
2025-06-23 07:21:51 -05:00 |
|
Matthew Hernandez
|
f3fadd6c0a
|
Fix issue #684: Minor docstring edit (#699)
|
2025-06-23 07:18:28 -05:00 |
|
Sebastian Raschka
|
984cca3f64
|
Fix code comment: embed_dim -> d_out (#698)
|
2025-06-22 16:36:39 -05:00 |
|
Sebastian Raschka
|
a5ea296259
|
Use more recent sentencepiece tokenizer API (#696)
|
2025-06-22 13:52:30 -05:00 |
|
Sebastian Raschka
|
2351a1f282
|
Fix some wording issues in the notes (#695)
|
2025-06-22 13:46:16 -05:00 |
|
Sajjad Baloch
|
cfdf22330b
|
Fix: Typo in appendix_d.py comments. (#682)
* Fix: pkg/llms_from_scratch/appendix_d.py
* minor language typo fix
* fix 691
---------
Co-authored-by: PrinceSajjadHussain <PrinceSajjadHussain@users.noreply.github.com>
Co-authored-by: rasbt <mail@sebastianraschka.com>
|
2025-06-22 12:15:12 -05:00 |
|
casinca
|
c4b19d7eb6
|
fix issue #664 - inverted token and pos emb layers (#665)
* fix inverted token and pos layers
* remove redundant code
---------
Co-authored-by: rasbt <mail@sebastianraschka.com>
|
2025-06-22 12:15:01 -05:00 |
|
Sebastian Raschka
|
0b15a00574
|
Qwen3 KV cache (#688)
|
2025-06-21 17:34:39 -05:00 |
|
Daniel Kleine
|
2a530b49fe
|
added pkg fixes (#676)
Co-authored-by: Sebastian Raschka <mail@sebastianraschka.com>
|
2025-06-21 16:07:50 -05:00 |
|
Sebastian Raschka
|
bb57756444
|
Add GPT-2 KV cache to pkg (#687)
|
2025-06-21 12:29:04 -05:00 |
|
Sebastian Raschka
|
9d62ca0598
|
Llama 3 KV Cache (#685)
* Llama 3 KV Cache
* skip expensive tests on Gh actions
* Update __init__.py
|
2025-06-21 10:55:20 -05:00 |
|
Sebastian Raschka
|
9f6f514191
|
Fix formatting in Qwen3 nb (#680)
* Fix formatting in Qwen3 nb
* upd
|
2025-06-20 07:28:27 -05:00 |
|
casinca
|
374cb94af0
|
minor readability improvements (#668)
|
2025-06-19 18:56:49 -05:00 |
|
Daniel Kleine
|
e79bb50a1b
|
fixed plot_losses (#677)
|
2025-06-19 18:55:43 -05:00 |
|
Sebastian Raschka
|
3d4bce6d57
|
Qwen3 From Scratch (#678)
* Qwen3 From Scratch
* rev other file
* upd
* upd
* upd
* url fixes
|
2025-06-19 18:44:38 -05:00 |
|
casinca
|
e700c66b7a
|
removed old args in GQA class (#674)
|
2025-06-17 13:09:53 -05:00 |
|