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
Shimpei Kojio
1446cfd824
fixed video link ( #646 )
2025-06-13 08:16:18 -05:00
Sebastian Raschka
02ca4ac42d
BPE cosmetics ( #629 )
...
* Llama3 from scratch improvements
* Cosmetic BPE improvements
* restore
* Update ch02/05_bpe-from-scratch/bpe-from-scratch.ipynb
* Update ch02/05_bpe-from-scratch/bpe-from-scratch.ipynb
* endoftext whitespace
2025-04-18 18:57:09 -05:00
Sebastian Raschka
48e98abc8e
add special token handling to bpe from scratch code ( #616 )
2025-04-13 12:38:22 -05:00
Sebastian Raschka
0bdcce4e40
Clarify dataset length in chapter 2 ( #589 )
2025-03-30 16:01:37 -05:00
Sebastian Raschka
634a531223
Cosmetic improvements to the BPE code ( #562 )
2025-03-09 10:49:40 -05:00
Sebastian Raschka
6aec412421
Fix BPE bonus materials ( #561 )
...
* Fix BPE bonus materials
* fix bpe implementation
* update
* Add 'Hello, world. Is this-- a test?' test case
* update link to test file
* update path handling
* update path handling
* fix pytest paths
2025-03-08 17:21:30 -06:00
Sebastian Raschka
5be0e3cbbd
add link to supplementary ch02 video ( #553 )
2025-03-02 13:17:42 -06:00
Sebastian Raschka
839a7e9bfc
Use correct ch02 title ( #551 )
2025-02-28 10:16:21 -06:00
Sebastian Raschka
db58925d7f
Add BPE from scratch link ( #550 )
2025-02-28 09:57:41 -06:00
Kasen
af4b73ca7b
Improve BPE vocabulary saving and pair frequency handling ( #539 )
2025-02-19 09:51:04 -06:00
Kasen
0a5214b804
Fix incorrect indentation ( #536 )
2025-02-18 14:47:31 -06:00
Sebastian Raschka
d684ff418a
Fix typo in Ch02 comments ( #516 )
2025-02-04 20:16:07 -06:00
Sebastian Raschka
dcaac28b92
Bonus material: extending tokenizers ( #496 )
...
* Bonus material: extending tokenizers
* small wording update
2025-01-22 09:26:54 -06:00
Daniel Kleine
9175590ea4
add GPT2TokenizerFast to BPE comparison ( #498 )
...
* added HF BPE Fast
* update benchmarks
* add note about performance
* revert accidental changes
---------
Co-authored-by: rasbt <mail@sebastianraschka.com>
2025-01-22 09:26:44 -06:00
Austin Welch
654734053a
fix: preserve newline tokens in BPE encoder ( #495 )
...
* fix: preserve newline tokens in BPE encoder
* further fixes
* more fixes
---------
Co-authored-by: rasbt <mail@sebastianraschka.com>
2025-01-21 12:47:15 -06:00
Daniel Kleine
3f9facbc55
BPE: fixed typo ( #492 )
...
* fixed typo
* use rel path if exists
* mod gitignore and use existing vocab files
---------
Co-authored-by: rasbt <mail@sebastianraschka.com>
2025-01-20 20:49:53 -06:00
Sebastian Raschka
b17d097742
Implementingthe BPE Tokenizer from Scratch ( #487 )
2025-01-17 12:22:00 -06:00
Henry Shi
15af754304
Print out embeddings for more illustrative learning ( #481 )
...
* print out embeddings for illustrative learning
* suggestion print embeddingcontents
---------
Co-authored-by: rasbt <mail@sebastianraschka.com>
2025-01-13 14:44:06 -06:00
Tao Qian
65ee619d3b
Minor readability improvement in dataloader.ipynb ( #461 )
...
* Minor readability improvement in dataloader.ipynb
- The tokenizer and encoded_text variables at the root level are unused.
- The default params for create_dataloader_v1 are confusing, especially for the default batch_size 4, which happens to be the same as the max_length.
* readability improvements
---------
Co-authored-by: rasbt <mail@sebastianraschka.com>
2025-01-04 11:26:10 -06:00
Sebastian Raschka
42b703fc0b
Note about SSL certificates ( #404 )
2024-10-19 16:27:19 -05:00
Sebastian Raschka
6a9bedc2ec
Update bonus section formatting ( #400 )
2024-10-12 10:26:08 -05:00
rasbt
3cebcce639
minor spelling fix
2024-09-08 15:35:36 -05:00
Gustavo Monti
190910e3d6
updating REAMDE from chapter 02 inclund 04_bonus section ( #344 )
...
* updating REAMDE from chapter 02 inclund 04_bonus section
* Update ch02/README.md
---------
Co-authored-by: Gustavo Monti Rocha <gustavo.rocha@intelliway.com.br>
Co-authored-by: Sebastian Raschka <mail@sebastianraschka.com>
2024-09-05 08:09:46 +02:00
Sebastian Raschka
f66c089f0b
Test with PyTorch 2.0 and 2.4 ( #290 )
...
* Test with PyTorch 2.0 and 2.4
* Update basic-tests-old-pytorch.yml
* skip version cell
2024-07-27 15:09:02 -05:00
Sebastian Raschka
6dd8666d9c
Test code in pytorch 2.4 ( #285 )
...
* test code in pytorch 2.4
* update
2024-07-24 21:53:41 -05:00
Sebastian Raschka
3f6f2af3a3
Simplify embedding vs linear layer code ( #278 )
2024-07-21 12:21:10 -05:00
Thanh Tran
a2bb045984
fix typos & inconsistent texts ( #269 )
...
Co-authored-by: TRAN <you@example.com>
2024-07-17 07:34:51 -05:00
rasbt
ee1d4730ba
fixes bold font #267
2024-07-16 17:51:15 -05:00
Daniel Kleine
7e0dd7f765
minor: removed redundant imports ( #260 )
...
* removed duplicated imports
* removed empty cell
2024-07-05 15:33:19 -05:00
rasbt
bd216fdade
update decode method
2024-07-05 08:34:27 -05:00
Suman Debnath
46f4d9e575
fixing the regular expression used in the SimpleTokenizer ( #259 )
...
* fixing the regular expression used in the SimpleTokenizer class and a typo in the 2.7 Creating token embedding introduction section
* rerun
---------
Co-authored-by: rasbt <mail@sebastianraschka.com>
2024-07-04 12:27:27 -05:00
rasbt
64536ca40f
update figures
2024-07-02 17:12:42 -05:00
rasbt
5e24a042c1
add links to summary sections
2024-06-29 07:33:26 -05:00
Sebastian Raschka
4fef19e016
remove redundant code lines ( #247 )
2024-06-25 21:44:19 -05:00
rasbt
f46441d53f
update with latest versions
2024-06-25 21:09:27 -05:00
Daniel Kleine
7a54d383e7
minor fixes ( #246 )
...
* removed duplicated white spaces
* Update ch07/01_main-chapter-code/ch07.ipynb
* Update ch07/05_dataset-generation/llama3-ollama.ipynb
* removed duplicated white spaces
* fixed title again
---------
Co-authored-by: Sebastian Raschka <mail@sebastianraschka.com>
2024-06-25 17:30:30 -05:00
rasbt
c1f9361428
add main and optional sections
2024-06-19 17:48:25 -05:00
Daniel Kleine
73be1c592f
fixed num_workers ( #229 )
...
* fixed num_workers
* ch06 & ch07: added num_workers to create_dataloader_v1
2024-06-19 17:36:46 -05:00
rasbt
b2ff989174
distinguish better between main chapter code and bonus materials
2024-06-11 21:07:42 -05:00
rasbt
e1adeb14f3
add allowed_special={"<|endoftext|>"}
2024-06-09 06:04:02 -05:00
Sebastian Raschka
40ba3a4068
Remove leftover instances of self.tokenizer ( #201 )
...
* Remove leftover instances of self.tokenizer
* add endoftext token
2024-06-08 14:57:34 -05:00
rasbt
20f1ef553c
update figure 2.13
2024-06-01 09:38:33 -05:00
rasbt
fe8bb9291e
update formatting
2024-05-24 07:20:37 -05:00
rasbt
1407085f07
reset cell count for better nbdiff
2024-05-22 20:27:09 -05:00
rasbt
85c3210105
update regex
2024-05-22 20:15:31 -05:00
rasbt
678fad50bc
formatting for consistency with production chapter
2024-05-18 11:03:42 -05:00
rasbt
6c6321f671
simplify code
2024-05-16 20:16:25 -05:00
Sebastian Raschka
0f03c20483
Data loader intuition with numbers ( #132 )
...
* data loader intuition with numbers
* fix link
* fix tests
2024-04-27 07:56:41 -05:00
rasbt
379a8ab39c
update figures in bonus notebook
2024-04-23 21:01:27 -05:00
