 Sebastian Raschka
|
a6b883c9f9
Gemma 3 270M From Scratch (#771)
|
3 ヶ月 前 |
|
Sebastian Raschka
|
e9c1c1da38
Fix qk_norm comment (#769)
|
3 ヶ月 前 |
|
Sebastian Raschka
|
b14325e56d
Qwen3 and Llama3 equivalency teests with HF transformers (#768)
|
3 ヶ月 前 |
|
Sebastian Raschka
|
5febcf8a1b
MoE Nb readability improvements (#761)
|
3 ヶ月 前 |
|
Sebastian Raschka
|
f92b40e4ab
Qwen3 Coder Flash & MoE from Scratch (#760)
|
3 ヶ月 前 |
 casinca
|
145322ded8
[Minor] Qwen3 typo & optim (#758)
|
3 ヶ月 前 |
|
Sebastian Raschka
|
b12dbf6c68
Interleaved Q and K for RoPE in Llama 2 (#750)
|
4 ヶ月 前 |
|
Sebastian Raschka
|
13f049f6a4
Minor typo: pply -> Apply (#749)
|
4 ヶ月 前 |
|
Sebastian Raschka
|
c6472f1af1
Update Python dependency in pyproject.toml (#748)
|
4 ヶ月 前 |
|
Sebastian Raschka
|
3233ddc475
get rid of redundant memory profiler import (#744)
|
4 ヶ月 前 |
|
Sebastian Raschka
|
7e9ce325de
Add link to official video course (#741)
|
4 ヶ月 前 |
 Matthew Hernandez
|
6f12edb0cc
Fix issue: 731 by resolving semantic error (#738)
|
4 ヶ月 前 |
|
Sebastian Raschka
|
a354555049
Batched KV Cache Inference for Qwen3 (#735)
|
4 ヶ月 前 |
|
Sebastian Raschka
|
b8c8237251
Qwen3 tokenizer sanity checks (#730)
|
4 ヶ月 前 |
|
Sebastian Raschka
|
21c41721cc
Add more sophisticated Qwen3 tokenizer (#729)
|
4 ヶ月 前 |
|
Sebastian Raschka
|
3c9dc4807b
Simplify KV cache usage (#728)
|
4 ヶ月 前 |
|
Sebastian Raschka
|
9cf64170ed
Update Qwen3 tokenizer test (#727)
|
4 ヶ月 前 |
|
Matthew Hernandez
|
83c76891fc
Fix issue 724: unused args (#726)
|
4 ヶ月 前 |
|
Sebastian Raschka
|
c8c6e7814a
Update README.md
|
4 ヶ月 前 |
|
Sebastian Raschka
|
6103acbedb
Add prerequisite section (#723)
|
4 ヶ月 前 |
|
Sebastian Raschka
|
c62fc7cad1
Fix `pip uv` typo in installation instructions (#722)
|
4 ヶ月 前 |
|
Sebastian Raschka
|
0405b0c8e7
Handle other Qwen3 tokenizer settings (#716)
|
4 ヶ月 前 |
|
Sebastian Raschka
|
4e61dc4224
Fix d_out code comment in bonus materials (#715)
|
4 ヶ月 前 |
|
Sebastian Raschka
|
c4ec55edac
Support different Qwen3 sizes in pkg (#714)
|
4 ヶ月 前 |
|
Sebastian Raschka
|
ddbaf0d83e
Use test mode arg in ch07 (#713)
|
4 ヶ月 前 |
|
Sebastian Raschka
|
8b3e4b24b0
Remove unused params for hparam script (#710)
|
4 ヶ月 前 |
|
Sebastian Raschka
|
190c66b3b0
Add Qwen3 1.7, 4B, 8B, and 32B support to from-scratch nb (#709)
|
4 ヶ月 前 |
|
Sebastian Raschka
|
2f53bf5fe5
Link the other KV cache sections (#708)
|
5 ヶ月 前 |
|
Sebastian Raschka
|
47a750014d
Add link to free exercise PDF (#706)
|
5 ヶ月 前 |
|
Sebastian Raschka
|
3bdf18a599
Update Llama 3 table for consistency with Qwen3
|
5 ヶ月 前 |