A Julia DSL for language models
|
|
14
|
1871
|
February 28, 2024
|
Zygote with Tullio gives wrong gradients/pullbacks using CUDA
|
|
1
|
227
|
February 26, 2024
|
Deep learning with Flux.jl and gumbel-softmax trick
|
|
2
|
349
|
February 27, 2024
|
Fitted Flux model is "off" by one
|
|
2
|
254
|
February 24, 2024
|
Dumb question: why autodifferentiation is needed in Neural Networks
|
|
9
|
780
|
February 24, 2024
|
Help with Flux.jl, Metal.jl (Apple Silicon) and Conv layers
|
|
2
|
1004
|
February 23, 2024
|
How can I solve complex-valued ordinary differential equations (ODEs) using neural networks, given limitations with complex data types in libraries like Lux?
|
|
2
|
397
|
February 22, 2024
|
Can't run a Resnet code
|
|
3
|
276
|
February 19, 2024
|
Do not update neural network weights with a value of 0
|
|
5
|
528
|
February 19, 2024
|
Using LSTM cell in Lux with explicit parameters
|
|
0
|
300
|
February 14, 2024
|
How hard is it to rebuild a tensorflow model in julia?
|
|
2
|
697
|
February 17, 2024
|
Moving a custom loss function to GPU
|
|
5
|
405
|
February 15, 2024
|
Slow LSTM on GPU in Flux
|
|
21
|
2138
|
February 15, 2024
|
Speeding up gradient of logpdf
|
|
19
|
774
|
February 12, 2024
|
Crystal Graphs w/ GeometricFlux.jl
|
|
0
|
156
|
February 6, 2024
|
Lux (And Flux), "parallel" Network Input. When Input is flat, Zygote gradient works, when input is not flat it doesn't
|
|
10
|
689
|
February 5, 2024
|
Parser for safetensors
|
|
6
|
580
|
February 5, 2024
|
Memoization in mcmc
|
|
0
|
221
|
February 4, 2024
|
Physics-informed training of a surrogate model involving finite element analysis
|
|
4
|
1056
|
February 2, 2024
|
Understanding `Flux.Data.DataLoader` when training an LSTM model
|
|
1
|
797
|
February 2, 2024
|
Enzyme autodiff: Why am I getting allocations?
|
|
20
|
890
|
January 29, 2024
|
cuDNN, julia-1.10 and linux
|
|
10
|
1052
|
January 28, 2024
|
Why doesn't the loss calculated by Flux `withgradient` match what I have calculated?
|
|
2
|
255
|
January 26, 2024
|
A discrepancy in self-attention between python and Julia (Transformers)
|
|
7
|
419
|
January 26, 2024
|
GPU memory in Julia
|
|
5
|
291
|
January 25, 2024
|
Forcing Lux to use Enzyme instead of Zygote?
|
|
10
|
484
|
January 25, 2024
|
[English help] An imputer that works with any supervised model, a "GeneralImputer" or a "UniversalImputer" (or other?)
|
|
0
|
136
|
January 24, 2024
|
Inverse problem with NeuralPDE and GPU support
|
|
5
|
396
|
January 23, 2024
|
Issue with Zygote over ForwardDiff.derivative
|
|
10
|
1246
|
January 21, 2024
|
Maliar, Maliar, and Winant using Flux.jl (I just want to write a custom objective)
|
|
8
|
696
|
January 19, 2024
|