-
Kingma, Diederik Pieter. [Variational inference & deep learning: A new synthesis](https://pure.uva.nl/ws/files/17891313/Thesis.pdf).
-
@BieHDC wrote on 2021-12-20:
This should be the discussion place of what should be done and etc as the discussion started in [this issue](https://github.com/Immediate-Mode-UI/Nuklear/pull/362).
…
-
It appears that albert classification sometimes fails catastrophically with our compilation defaults. On a standard colab GPU, the follow script will sometime give good results, and sometime hover at …
-
Used the following PDF: https://arxiv.org/pdf/1706.03762
The result looks ok, however the order or pages is incorrect.
Setup
```
git clone ...
pip install -e .
```
```python
import asyn…
-
你好!
我们2023年发表了一篇论文,被EMNLP2023接收,题为:
[Orthogonal Subspace Learning for Language Model Continual Learning](https://arxiv.org/pdf/2310.14152.pdf)
发现和你的论文非常相似,建议增加对比说明。谢谢!
Xiao Wang
-
Could you please consider specifying different representation types for matrix columns? It would address a lot of engineering needs. For example, together with the physical units library, we could imp…
-
微博内容精选
-
Hi @rasbt,
I found that implementation of the `MultiHeadAttention` class has the following line:
```python
mask_unsqueezed = mask_bool.unsqueeze(0).unsqueeze(0)
```
But there is only one unsq…
-
> Another area I started looking into (but haven't deeply explored yet) for both figuring out how to map variable names to sections of code in a 'smart' way, and potentially also for module identifica…
-
https://arxiv.org/abs/2110.05169
https://github.com/facebookresearch/salina/tree/main/salina_examples/rl/subspace_of_policies