952 Commits

Author SHA1 Message Date
casinca
3a5ee8cfa1 - added no chat template comparison in test_chat_wrap_and_equivalence
- removed duplicate comparison
2025-09-15 19:30:31 +02:00
casinca
df504397a8 prevent self.apply_chat_template being applied for base Qwen models 2025-09-15 16:26:17 +02:00
Sebastian Raschka
8add26cbe9
Improve weight tying handling (#826)
* Improve weight tying handling

* fix
2025-09-14 15:46:48 -05:00
rasbt
1412b139f2
main push to sync github ruleset 2025-09-14 11:59:52 -05:00
Sebastian Raschka
8f3e5b024d
Add LoRA scaling (#823) 2025-09-14 11:57:55 -05:00
Sebastian Raschka
fc101b710e
Added Apple Silicon GPU device update (#820)
* Added Apple Silicon GPU device

* Added Apple Silicon GPU device

* delete: remove unused model.pth file from understanding-buffers

* update

* update

---------

Co-authored-by: missflash <missflash@gmail.com>
2025-09-13 12:48:06 -05:00
Andreas Yin
8e170312fe
fix: correct role of the beta hyperparameter on the DPO loss (#818)
Increasing beta leads to less divergence between the new model and the reference model.
2025-09-12 20:21:38 -05:00
Sebastian Raschka
32965e0edd
remove redundant next_cache (#817) 2025-09-11 15:16:08 -05:00
Sebastian Raschka
c7a4362ca4
Add defensive context trimming for multiturn (#815)
* Add defensive context trimming for multiturn

* add all mods
2025-09-09 20:19:00 -05:00
Sebastian Raschka
215abdbcdd
Improve multiturn stopping condition (#814)
* Improve multiturn stopping condition

* improve
2025-09-09 19:37:15 -05:00
Sebastian Raschka
4b0021416a
Clarify Qwen3 notebook purpose (#812)
* Clarify Qwen3 notebook purpose

* Update README.md

* Update README.md
2025-09-06 15:31:35 -05:00
Sebastian Raschka
6d175a22df
Fix IMDb spelling (#811)
* Add SSL instructions

* Fix IMDb spelling
2025-09-06 12:04:47 -05:00
Sebastian Raschka
18c6b970ab
Add additional notes on debugging SSL issues (#810)
* Add SSL instructions

* update old pytorch tests

* update

* update

* update

* update

* update

* update

* update

* update
2025-09-06 11:46:50 -05:00
Sebastian Raschka
290fa10d55
Update code dependencies (#809) 2025-09-05 16:40:00 -05:00
Sebastian Raschka
5ae41c402e
Fix code comment 2025-09-05 14:02:24 -05:00
Sebastian Raschka
623dc65d5d
Update requirements for Intel Macs (#807) 2025-09-04 15:07:46 -05:00
Sebastian Raschka
efad18bd0b
Fix accidental indentation 2025-09-04 14:41:08 -05:00
Sebastian Raschka
9bfa92fb3e
Update README.md 2025-09-03 12:41:32 -05:00
Sebastian Raschka
590d8489d0
Update requirements for Intel macOS (#805) 2025-09-03 12:15:25 -05:00
rasbt
65e67a9681
fix typo 2025-09-02 10:17:51 -05:00
Hayato Hongo
2d8d6224ed
added brief explanations about 2 different ways of RoPE implementations (#802)
* added brief explanations about  2 different ways of RoPE implementations

* improve comment

---------

Co-authored-by: rasbt <mail@sebastianraschka.com>
2025-09-02 10:14:36 -05:00
rasbt
9ea2c57c5f
simplify 2025-09-01 22:15:47 -05:00
rasbt
643f800a94
remove local config files 2025-09-01 20:52:40 -05:00
Sebastian Raschka
9eee9296d9
Interactive qwen3 chat interface (#801)
* Interactive qwen3 chat interface

* update

* update

* update url
2025-09-01 20:50:25 -05:00
Sebastian Raschka
70edd53809
Improve RoPE (#799) 2025-08-31 11:46:36 -05:00
Sebastian Raschka
d87d91b23c
Add KVCache variant of Qwen3 notebook (#800)
* Add KVCache variant of Qwen3 notebook

* cleanup
2025-08-31 11:11:12 -05:00
Sebastian Raschka
0e9cefcdc8
Update pixi powershell command section (#798) 2025-08-30 08:42:06 -05:00
Sebastian Raschka
a51ff65488
reasoning-from-scratch (#793) 2025-08-28 18:36:41 -05:00
Jestine Paul
a3a62c509a
Improve MHA einsum (#781)
Efficiency update for einsum as mentioned in #772
2025-08-22 15:12:26 -05:00
casinca
670f7a4dd0
- added (missing) Gemma3 bullet point in parent folder's readme.md (#788)
- typo in nbs
2025-08-22 15:03:47 -05:00
Sebastian Raschka
4a84cfccf9
Minor cosmetic fixes in Gemma 3 nbs (#780) 2025-08-19 21:08:29 -05:00
Sebastian Raschka
f571b5e493
Add Gemma3 KV cache variant (#776)
* Add Gemma3 KV cache variant

* update
2025-08-19 12:37:49 -05:00
Sebastian Raschka
8c1f9ccf54
Improve MHA einsum (#775) 2025-08-19 10:38:15 -05:00
Sebastian Raschka
80d4732456
add HF equivalency tests for standalone nbs (#774)
* add HF equivalency tests for standalone nbs

* update

* update

* update

* update
2025-08-18 18:58:46 -05:00
Sebastian Raschka
a6b883c9f9
Gemma 3 270M From Scratch (#771)
* Gemma 3 270M From Scratch

* fix path

* update readme
2025-08-17 08:23:05 -05:00
Sebastian Raschka
e9c1c1da38
Fix qk_norm comment (#769) 2025-08-15 08:38:48 -05:00
Sebastian Raschka
b14325e56d
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
5febcf8a1b
MoE Nb readability improvements (#761) 2025-08-01 19:58:18 -05:00
Sebastian Raschka
f92b40e4ab
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
145322ded8
[Minor] Qwen3 typo & optim (#758)
* typo

* remove weight dict after loading
2025-07-28 17:29:44 -05:00
Sebastian Raschka
b12dbf6c68
Interleaved Q and K for RoPE in Llama 2 (#750) 2025-07-23 08:02:02 -05:00
Sebastian Raschka
13f049f6a4
Minor typo: pply -> Apply (#749) 2025-07-22 08:19:25 -05:00
Sebastian Raschka
c6472f1af1
Update Python dependency in pyproject.toml (#748) 2025-07-22 08:03:57 -05:00
Sebastian Raschka
3233ddc475
get rid of redundant memory profiler import (#744) 2025-07-16 07:36:51 -05:00
Sebastian Raschka
7e9ce325de
Add link to official video course (#741) 2025-07-13 10:35:12 -05:00
Matthew Hernandez
6f12edb0cc
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
a354555049
Batched KV Cache Inference for Qwen3 (#735) 2025-07-10 08:09:35 -05:00
Sebastian Raschka
b8c8237251
Qwen3 tokenizer sanity checks (#730) 2025-07-09 13:52:35 -05:00
Sebastian Raschka
21c41721cc
Add more sophisticated Qwen3 tokenizer (#729) 2025-07-09 13:16:26 -05:00
Sebastian Raschka
3c9dc4807b
Simplify KV cache usage (#728)
* Simplify KV cache usage

* Swap mark text with ghostwriter
2025-07-08 12:56:55 -05:00