jax
Here are 154 public repositories matching this topic...
Bidirectional RNN
Is there a way to train a bidirectional RNN (like LSTM or GRU) on trax nowadays?
-
Updated
Jun 21, 2021 - Jupyter Notebook
-
Updated
Jun 6, 2021 - Python
-
Updated
Jun 21, 2021 - Python
-
Updated
Jun 21, 2021 - Python
-
Updated
Jun 8, 2021 - Python
-
Updated
Jun 18, 2021 - Python
-
Updated
Jun 21, 2021 - Jupyter Notebook
-
Updated
Jun 18, 2021 - Python
-
Updated
Jun 21, 2021 - Python
-
Updated
Jun 17, 2021 - Python
After #1016 and #989, it would be nice to port ProdLDA example in Pyro to illustrate some usage of JAX nn frameworks flax/haiku in NumPyro. We might consider replacing SoftmaxNormal there with Dirichlet distribution. This is a good first issue for those who are interested in both NLP and Ba
-
Updated
May 19, 2021 - Python
-
Updated
Jun 5, 2021 - Python
-
Updated
Jun 21, 2021
-
Updated
Jul 28, 2020 - Python
-
Updated
Apr 8, 2021 - Jupyter Notebook
-
Updated
Jun 11, 2021 - Python
-
Updated
Jun 1, 2021 - Python
-
Updated
Jun 12, 2021 - Jupyter Notebook
Description
TIL that pip has a super nice Issue template page
that uses a [.github/ISSUE_TEMPLATE/config.yml](https://github.com/pypa/pip/blob/e6414d6db6db37951988f6f2b11ec530ed0b191d/.github/ISSUE_TEMPLATE/conf
-
Updated
Oct 21, 2020 - Python
See wikipedia table for example patterns: https://en.wikipedia.org/wiki/List_of_integrals_of_Gaussian_functions
-
Updated
Dec 15, 2020 - Python
-
Updated
Jun 21, 2021 - Python
-
Updated
Jun 11, 2021 - Python
-
Updated
Apr 5, 2021 - Python
-
Updated
Jun 9, 2021 - Jupyter Notebook
Improve this page
Add a description, image, and links to the jax topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the jax topic, visit your repo's landing page and select "manage topics."

Add better error message to
HubertForCTC,Wav2Vec2ForCTCif labels are bigger than vocab size.Motivation
Following this issue: huggingface/transformers#12264 it is clear that an error message should be thrown if any of the any of the labels are >
self.config.vocab_sizeor else silent errors can sneak into the training script.So w