commits

🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠

SHA	Message	Author	Date
33ab0228	merge Merge pull request #265 from thanhtcptit/master	vpj <v**i@gm> Committed by: GitHub <ny@g**m>	7 months ago
25e16984	link to jax transformer	Varuna Jayasiri <v**i@g**m>	10 months ago
c3d868ba	gepa paper highlighted	Varuna Jayasiri <v**i@g**m>	11 months ago
e6b3c8a6	jax docs	Varuna Jayasiri <v**i@g**m>	about 1 year ago
f3468242	cleanup jax	Varuna Jayasiri <v**i@g**m>	about 1 year ago
96f7b5a8	jax transformer	Varuna Jayasiri <v**i@g**m>	about 1 year ago
dd451987	sitemap	Varuna Jayasiri <v**i@g**m>	about 1 year ago
ee0ad9ba	version	Varuna Jayasiri <v**i@g**m>	about 1 year ago
9262c57f	flash attention	Varuna Jayasiri <v**i@g**m>	about 1 year ago
47526447	all comments	Varuna Jayasiri <v**i@g**m>	about 1 year ago
3dd36b80	all comments	Varuna Jayasiri <v**i@g**m>	about 1 year ago
73b9892b	all comments	Varuna Jayasiri <v**i@g**m>	about 1 year ago
eb5c004f	sm scale log2	Varuna Jayasiri <v**i@g**m>	about 1 year ago
5a8182d2	backward pass formulas	Varuna Jayasiri <v**i@g**m>	about 1 year ago
a9b5c923	backward pass formulas	Varuna Jayasiri <v**i@g**m>	about 1 year ago
0ae6e6ae	flash comments	Varuna Jayasiri <v**i@g**m>	about 1 year ago
1bc2a698	flash comments	Varuna Jayasiri <v**i@g**m>	about 1 year ago
c4d2e8cd	docs	Varuna Jayasiri <v**i@g**m>	about 1 year ago
00f87148	merge Merge remote-tracking branch 'origin/master'	Varuna Jayasiri <v**i@g**m>	about 1 year ago
d7d63e1f	triton flash wip	Varuna Jayasiri <v**i@g**m>	about 1 year ago
0fcb29d8	Update readme.md	Varuna Jayasiri <v**i@gm> Committed by: GitHub <ny@g**m>	about 1 year ago
ebb94842	cleanup save checkpoint	Varuna Jayasiri <v**i@g**m>	about 1 year ago
5eecda7e	cleanup log activations	Varuna Jayasiri <v**i@g**m>	about 1 year ago
a713c92b	cleanup hook model outputs	Varuna Jayasiri <v**i@g**m>	about 1 year ago
5bdedcff	remove labml_helpers dep	Varuna Jayasiri <v**i@g**m>	about 1 year ago
b1ba92c1	merge Merge pull request #280 from kommentlezz/patch-1	Varuna Jayasiri <v**i@gm> Committed by: GitHub <ny@g**m>	about 1 year ago
47d4231a	seq length in rope	Varuna Jayasiri <v**i@g**m>	about 1 year ago
f6d77c36	cleanup some unused imports	Varuna Jayasiri <v**i@g**m>	about 1 year ago
1b702523	remove labml_helpers dependency: replace Module with nn.Module	Varuna Jayasiri <v**i@g**m>	about 1 year ago
dd1d51ae	Fix typo: language	Pavel Dmitriev <1**z@um> Committed by: GitHub <ny@g**m>	over 1 year ago
90e21b5a	merge Merge pull request #273 from lakshith-403/LoRA	Varuna Jayasiri <v**i@gm> Committed by: GitHub <ny@g**m>	about 2 years ago
309a071b	add labml_nn install command	lakshith <l**e@g**m>	about 2 years ago
f5737203	rename configs to trainer	lakshith <l**e@g**m>	about 2 years ago
6df1d798	version	Varuna Jayasiri <v**i@g**m>	about 2 years ago
49ea8f06	paperswithcode.com list	Varuna Jayasiri <v**i@g**m>	about 2 years ago
3e6a4eca	LoRA Chinese docs	Varuna Jayasiri <v**i@g**m>	about 2 years ago
5731bff5	LoRA docs	Varuna Jayasiri <v**i@g**m>	about 2 years ago
789c31a6	merge Merge pull request #272 from lakshith-403/LoRA	Varuna Jayasiri <v**i@gm> Committed by: GitHub <ny@g**m>	about 2 years ago
9485eec3	fix mapping to match renamed layers	lakshith <l**e@g**m>	about 2 years ago
2fb0e22e	typo fix	lakshith <l**e@g**m>	about 2 years ago
24bd64af	check loaded weights	lakshith <l**e@g**m>	about 2 years ago
9e1b3571	LoRA GPT2 n_heads fix and notes	Varuna Jayasiri <v**i@g**m>	about 2 years ago
b260349c	LoRA GPT2 n_heads fix and notes	Varuna Jayasiri <v**i@g**m>	about 2 years ago
012fc7f0	LoRA GPT2 n_heads fix and notes	Varuna Jayasiri <v**i@g**m>	about 2 years ago
d5768ba4	LoRA typo fix	Varuna Jayasiri <v**i@g**m>	about 2 years ago
9dd97ff1	LoRA transpose	Varuna Jayasiri <v**i@g**m>	about 2 years ago
ce21dcf7	LoRA experiment	Varuna Jayasiri <v**i@g**m>	about 2 years ago
cf755ec9	merge Merge pull request #271 from lakshith-403/LoRA	Varuna Jayasiri <v**i@gm> Committed by: GitHub <ny@g**m>	about 2 years ago
3349afdc	simplify loop def in training	lakshith <l**e@g**m>	about 2 years ago
863772e0	rename layers	lakshith <l**e@g**m>	about 2 years ago
f3465ac9	Chineese translation	Varuna Jayasiri <v**i@g**m>	about 2 years ago
edf875aa	LoRA experiment notes	Varuna Jayasiri <v**i@g**m>	about 2 years ago
d69f1c10	LoRA experiment notes	Varuna Jayasiri <v**i@g**m>	about 2 years ago
64959fdf	merge Merge pull request #267 from pengchzn/master	Varuna Jayasiri <v**i@gm> Committed by: GitHub <ny@g**m>	about 2 years ago
5d384d6b	merge Merge pull request #268 from lakshith-403/LoRA	Varuna Jayasiri <v**i@gm> Committed by: GitHub <ny@g**m>	about 2 years ago
61d32f46	create LoRA experiment	lakshith <l**e@g**m>	about 2 years ago
4aa1bdb8	merge Merge remote-tracking branch 'origin/master'	pengchzn <p**n@g**m>	about 2 years ago
dc26e6c0	Fix Chinese typo	pengchzn <p**n@g**m>	about 2 years ago
d4af40b5	LoRA notes	Varuna Jayasiri <v**i@g**m>	about 2 years ago
eb9337e9	Clean up LoRA	Varuna Jayasiri <v**i@g**m>	about 2 years ago
dc476216	Clean up LoRA	Varuna Jayasiri <v**i@g**m>	about 2 years ago
957ade6d	merge Merge pull request #266 from lakshith-403/LoRA	Varuna Jayasiri <v**i@gm> Committed by: GitHub <ny@g**m>	about 2 years ago
bc32b507	clear notebook outputs	lakshith <l**e@g**m>	about 2 years ago
77d00f08	Add LoRA to GPT2	lakshith <l**e@g**m>	about 2 years ago
0f2a9be6	training loop	lakshith <l**e@g**m>	about 2 years ago
23b7e2ee	create experiment notebook and refactoring	lakshith <l**e@g**m>	about 2 years ago
c82529ce	move LoRA to labml.nn	lakshith <l**e@g**m>	about 2 years ago
8e756f29	lora layers	Varuna Jayasiri <v**i@g**m>	about 2 years ago
d1e8daa1	replace convo1D layers with linear	lakshith <l**e@g**m>	about 2 years ago
50c3cc4e	keep only required configs	lakshith <l**e@g**m>	about 2 years ago
106e7260	remove droput layers	lakshith <l**e@g**m>	about 2 years ago
b3aedf30	remove gelu custom impl and use pytorch impl	lakshith <l**e@g**m>	about 2 years ago
cbc38bb2	GPT 2 implementation	lakshith <l**e@g**m>	about 2 years ago
8c84d6ee	Fix RoPE inner product equation & add note on the difference in implementatio...	thanhtcptit <t**6@g**m>	about 2 years ago
89a3ae88	merge Merge pull request #264 from Seas0/patch-1	Varuna Jayasiri <v**i@gm> Committed by: GitHub <ny@g**m>	about 2 years ago
66e92edb	Fix typo in Wasserstein GAN	Seas0 <s**7@om> Committed by: GitHub <ny@g**m>	about 2 years ago
7d7863c0	Fix Chinese typo	pengchzn <p**n@g**m>	about 2 years ago
f6e913eb	transformer mha chinese translation	Varuna Jayasiri <v**i@g**m>	about 2 years ago
d3f0bd30	merge Merge pull request #259 from pengchzn/master (Transformer MHA Chinese Transla...	Varuna Jayasiri <v**i@gm> Committed by: GitHub <ny@g**m>	about 2 years ago
e03dbc17	Refine Chinese translation	pengchzn <p**n@g**m>	about 2 years ago
1446bb12	Refine Chinese translation	pengchzn <p**n@g**m>	about 2 years ago
730046c9	merge Merge branch 'labmlai:master' into master	Peng Chen <6**n@um> Committed by: GitHub <ny@g**m>	about 2 years ago
391fa391	cleanup notebooks	Varuna Jayasiri <v**i@g**m>	about 2 years ago
26e64a88	zh	Varuna Jayasiri <v**i@g**m>	about 2 years ago
20494ae9	fix gae formula	Varuna Jayasiri <v**i@g**m>	about 2 years ago
a78ca145	refine translation of /__init__.zh.json	pengchzn <p**n@g**m>	about 2 years ago
4699c514	refine translation of /transformers/__init__.zh.json	pengchzn <p**n@g**m>	about 2 years ago
d858f2ee	remove tranding papers link	Varuna Jayasiri <v**i@g**m>	about 2 years ago
0bb4be3f	zh translation	Varuna Jayasiri <v**i@g**m>	about 2 years ago
a631e73b	merge Merge pull request #258 from pengchzn/master	Varuna Jayasiri <v**i@gm> Committed by: GitHub <ny@g**m>	about 2 years ago
7ad78f40	merge Merge branch 'master' into master	Varuna Jayasiri <v**i@gm> Committed by: GitHub <ny@g**m>	about 2 years ago
bf8a4912	chineese translation	Varuna Jayasiri <v**i@g**m>	about 2 years ago
f00ba4a7	paper url fix	Varuna Jayasiri <v**i@g**m>	about 2 years ago
df092056	Refine Chinese translation	pengchzn <p**n@g**m>	about 2 years ago
09d09379	fix value pe double rotation	Varuna Jayasiri <v**i@g**m>	about 2 years ago
2236f638	fix rope test code	Varuna Jayasiri <v**i@g**m>	about 2 years ago
cf565bcc	cleanup	Varuna Jayasiri <v**i@g**m>	about 2 years ago
999f2036	RWKV docs	Varuna Jayasiri <v**i@g**m>	over 2 years ago
418d1ec4	RWKV docs	Varuna Jayasiri <v**i@g**m>	over 2 years ago
df9e1af6	RWKV docs	Varuna Jayasiri <v**i@g**m>	over 2 years ago

← Back to repository

ecosyste.ms

Data

Tools

Indexes

Applications

Experiments

Commits

GitHub / labmlai/annotated_deep_learning_paper_implementations / commits