yujunjun/LLMs-from-scratch
1
0
Fork 0
mirror of https://github.com/rasbt/LLMs-from-scratch.git synced 2025-11-04 03:40:21 +00:00
Code Issues Packages Projects Releases Wiki Activity
353 Commits 11 Branches 0 Tags
Commit Graph

61 Commits

Author SHA1 Message Date
speed
7b34833ee1 fix 1024 characters to 1024 tokens (#152) 2024-05-11 13:17:07 -05:00
rasbt
bb59cbc525 link formatting 2024-04-30 06:26:23 -05:00
Sebastian Raschka
a5b353667d Rename drop_resid to drop_shortcut (#136) 2024-04-28 14:31:27 -05:00
rasbt
4abaa168ac fix merge conflict 2024-04-22 07:05:40 -05:00
rasbt
df4fc602d8 update numbering 2024-04-22 07:00:20 -05:00
rasbt
2dd7bf9cda file header 2024-04-22 06:53:38 -05:00
Sebastian Raschka
79d40c25bf remove requests dependency (#125) 2024-04-21 14:15:05 -05:00
Sebastian Raschka
4557d5830e Return nan if val loader is empty (#124) 2024-04-20 08:02:30 -05:00
Sebastian Raschka
ef2de4718e use torch no grad for loss (#119) 2024-04-14 08:13:07 -05:00
Sebastian Raschka
bae4b0fb08 Make datesets and loaders compatible with multiprocessing (#118) 2024-04-13 13:57:56 -05:00
Sebastian Raschka
8fe63a9a0e use correct lr 2024-04-12 19:55:07 -04:00
Sebastian Raschka
bbce1cb143 Automated link checking (#117) 
* Automated link checking

* Fix links in Jupyter Nbs
 2024-04-12 19:08:34 -04:00
Sebastian Raschka
790d0808b2 Organized setup instructions (#115) 
* Organized setup instructions

* update tets

* link checker action

* raise error upon broken link

* fix links

* fix links

* delete duplicated paragraph
 2024-04-10 22:09:46 -04:00
James Holcombe
0b866c133f Use instance tokenizer (#116) 
* Use instance tokenizer

* consistency updates

---------

Co-authored-by: Sebastian Raschka <mail@sebastianraschka.com>
 2024-04-10 21:16:19 -04:00
Daniel Kleine
b01204ca3a Added PDF display support to Docker image and VS Code and updated first step for gutenberg project (#111) 
* added VS Code extensions recommendations

* Added PDF display support to Docker image and VS Code

* fixed steps to download the dataset
 2024-04-08 20:37:55 -04:00
rasbt
8462a777bd address suggestions to improve clarity 2024-04-07 08:41:09 -05:00
rasbt
040ce578be renumber exercises 2024-04-07 06:03:41 -05:00
rasbt
84b785ddd0 variable renaming for clarity 2024-04-05 07:26:42 -05:00
rasbt
c31e99720d rename hparams to settings 2024-04-05 07:24:46 -05:00
Daniel Kleine
7d0b9b78b0 Updated devcontainer, .gitignore and README for gutenberg project (#107) 
* added ch05/03_bonus_pretraining_on_gutenberg model checkpoints and preprocessing output folders to .gitignore

* removed prettier extension, added github alerts markdown extension

* specified download instructions and fixed code markdown

* Update ch05/03_bonus_pretraining_on_gutenberg/README.md

* Update ch05/03_bonus_pretraining_on_gutenberg/README.md

---------

Co-authored-by: Sebastian Raschka <mail@sebastianraschka.com>
 2024-04-05 06:53:01 -05:00
Sebastian Raschka
25f533efe0 Fix Loss in Gutenberg bonus section (#109) 2024-04-04 20:54:09 -05:00
Sebastian Raschka
ccd7cebbb3 Rename variable to context_length to make it easier on readers (#106) 
* rename to context length

* fix spacing
 2024-04-04 07:27:41 -05:00
Sebastian Raschka
5beff4e25a Remove reundant dropout in MLP module (#105) 2024-04-03 20:19:08 -05:00
rasbt
cd12b4a937 rename batch to text 2024-04-02 20:46:53 -05:00
rasbt
21140b98d4 update notes 2024-04-02 18:27:13 -05:00
Sebastian Raschka
809c944d30 Use max size properly 2024-04-02 13:29:23 -05:00
Sebastian Raschka
5af3834760 Gutenberg for Windows users (#99) 2024-04-02 08:54:24 -05:00
rasbt
f30dd2dd2b improve instructions 2024-04-02 07:12:22 -05:00
rasbt
776a517d18 figure scaling 2024-04-01 08:05:01 -05:00
rasbt
ee096986ea upload exercise solutions of ch05 2024-03-31 20:28:51 -05:00
rasbt
83adc4a2ac add weight sizes 2024-03-31 08:48:19 -05:00
rasbt
1c173e4f44 update figures 2024-03-30 09:43:51 -05:00
rasbt
797cfb20de fix test 2024-03-29 09:03:36 -05:00
rasbt
ab1e56a323 reorg files and make standalone download file 2024-03-29 08:16:22 -05:00
rasbt
3c5b288ca0 minor typo fixes 2024-03-28 08:02:05 -05:00
rasbt
c10f5c9bf2 suggest galore 2024-03-27 19:58:32 -05:00
rasbt
88b2dd780a make batch loss calculatution more efficient 2024-03-27 07:11:56 -05:00
rasbt
3cb5a52a1b simplify calc_loss_loader 2024-03-26 20:34:50 -05:00
rasbt
9cc9c4244e simplify 2024-03-26 07:52:36 -05:00
rasbt
12fff1ddcb add endoftext token 2024-03-26 06:47:05 -05:00
rasbt
de576296de simplify .view code 2024-03-25 08:09:31 -05:00
Sebastian Raschka
d4989e01c5 Update README.md 2024-03-25 06:39:43 -05:00
rasbt
45e7826954 Merge branch 'main' of https://github.com/rasbt/LLMs-from-scratch 2024-03-24 07:09:18 -05:00
rasbt
c1d939c64e update chapter reference 2024-03-24 07:09:08 -05:00
rasbt
0f0fdef576 small typo fixes 2024-03-23 11:28:20 -05:00
Sebastian Raschka
cf39abac04 Add and link bonus material (#84) 2024-03-23 07:27:43 -05:00
Sebastian Raschka
5d02559993 small cosmetic updates (#83) 2024-03-22 09:15:40 -05:00
Sebastian Raschka
4582995ced Add alternative weight loading strategy as backup (#82) 2024-03-20 08:43:18 -05:00
rasbt
820d5e3ed1 remove duplicate import 2024-03-19 20:41:35 -05:00
Sebastian Raschka
a2cd8436cb Ch05 supplementary code (#81) 2024-03-19 09:26:26 -05:00