-
In the interests of defense-in-depth, this feature request is for "Digest Auth" on the front end of the server so that the user's password is never sent to the server. This would limit exposure of sec…
-
I'm looking for a way to generate sentence embeddings in a completely unsupervised way, and came across your work in TSDAE https://huggingface.co/kwang2049/TSDAE-scidocs2nli_stsb I was hoping you cou…
-
### Search before asking
- [X] I have searched the Ultralytics YOLO [issues](https://github.com/ultralytics/ultralytics/issues) and [discussions](https://github.com/ultralytics/ultralytics/discussion…
-
Claude Dev is especially powerful when augmented with extensive custom instructions that inform the AI about the design of the project, API's of significant libraries or services in use, the architect…
-
### 🐛 Describe the bug
Hi, I was testing FlexAttention by comparing its output with that of `nn.MultiheadAttention` and `torch.nn.functional.scaled_dot_product_attention`. In the end, I tracked down …
-
Thank you for your excellent work! However, I raised some questions regarding the Dimba architecture after reading the paper and the code.
TL;DR: the code seems to implement Dimba as Self-Attention…
-
Hi,
Could you please give the implementation details and explanation about how to decode based on the hybrid ctc/attention architecture?
(how to linearly combine the ctc score and attention score…
-
Hey there!
We're using Segment to integrate with Amplitude (through the Amplitude Actions destination) in both our web app (using Analytics V2) and React Native App. While working on a bug ticket, …
-
Hi,
The 2.2 release of Torch added a great integration to speed up transformer attention based architectures.
> FlashAttentionV2 backend for scaled dot product attention
An example of how it…
-
This issues describes the high level directions that "create LLM Engine V2". We want the design to be as transparent as possible and created this issue to track progress and solicit feedback.
Goal…