scratches/ml-test
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
No description
19 commits 1 branch 0 tags 556 KiB
Find a file
Exact
qwjyh 38dacdacf1 (WIP) implement Encoder and Decoder layer with built-in MultiHeadAttention 
TODO: fix layer norm
2025-04-19 20:13:24 +09:00
notebooks updated to 1.11.2 2024-12-04 22:23:36 +09:00
old refactor: moved custom multiheadattention impls to olds dir 2025-04-19 19:21:37 +09:00
.gitignore done: training a simple LSTM 2024-11-22 21:30:46 +09:00
.JuliaFormatter.toml add formatter config 2025-01-28 22:19:15 +09:00
LocalPreferences.toml updated to 1.11.2 2024-12-04 22:23:36 +09:00
Manifest.toml update dependencies 2025-04-19 19:22:49 +09:00
Project.toml fix: support batched input in MultiheadAttention using Dense 2025-04-19 19:18:03 +09:00
test_transformer.jl fix: support batched input in MultiheadAttention using Dense 2025-04-19 19:18:03 +09:00
transformers.jl (WIP) implement Encoder and Decoder layer with built-in MultiHeadAttention 2025-04-19 20:13:24 +09:00