-
The relationship between app and configuration is a little awkward. Ideally, we'd like to have people import the app and have a registry ready to run. Unfortunately, a lot of the configuration interpr…
-
I was quite surprised when in the definition of `Pseudofunctor`, the lines
```agda
private
module C = Bicategory C
module D = Bicategory D
```
made timings jump up by < .5 seconds to ~…
-
This version is product ready release. We strongly recommend to use this version instead of other previous 3.0.x (xmeta-service connection pool could not automatically expire and reconnect. [#41202](h…
-
启发OpenAI去做GPT的单个[sentiment neuron](https://openai.com/index/unsupervised-sentiment-neuron/)，和后面Issue一样，不仅有具体的location还能editing并且操纵模型。[用GPT-4和数据寻找&解释GPT-2的neuron](https://openai.com/index/language-mode…
-
## Keyword: efficient
### End-to-end codesign of Hessian-aware quantized neural networks for FPGAs and ASICs
- **Authors:** Javier Campos, Zhen Dong, Javier Duarte, Amir Gholami, Michael W. Mahoney,…
-
https://github.com/bclavie/RAGatouille
[Announcement tweet](https://x.com/bclavie/status/1742950315278672040?s=46&t=aOEVGBVv9ICQLUYL4fQHlQ) by bclavie
https://news.ycombinator.com/item?id=388692…
-
Great work and thanks for the codebase!
I want to know the exact detailed of LoRA fine-tuning as mentioned in Table 6 of the main paper.
Also if you could point-out to the bash script to reproduce…
-
Hello,
I see you've been using boolean masks to mask out the weights of the pytorch network. Is there a way to use sparse tensors to achieve an actual speed up in inference in Pytorch currently ?
…
-
### Describe the enhancement requested
Hi! We have a use case, in which we have existing Arrow arrays and we want to compose them to struct. Unfortunately, currently `StructBuilder` does not suppor…
-
Hi,
torch.nn.PixelShuffle is change the number of channels, which is not treated well using torch pruning.
For example, I have layer with shape of 1*16*576*1024, and by using PixelShuffle the output…