-
Dear MobileSAM Developers,
I hope this message finds you well. I am reaching out to discuss potential enhancements to the MobileSAM framework, particularly concerning its lightweight encoder's perf…
-
### **Initial action plans**
Copying these things from the wav2vec2 repo for safe housekeeping.
* An immediate quantize could be to convert the fine-tuned model using TFLite APIs. [Post-trainin…
-
I have tryied the example [【 Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation 】](https://github.com/UKPLab/sentence-transformers/tree/master/examples/training/multiling…
-
Hello, your work on knowledge distillation is great!
However, I have some problems about the code of FitNets.
I found you just use sum of losses to get backward, specifically, the `loss_feat` and `l…
-
Hi, thanks for your great work. Dose the code contain the feature distillation part?
-
Hi @akshaychawla, can you give me access to the GCS data? Thanks so much.
-
Hi there!
Now that using adapters works, does it make sense to include it that you can use an adapter for the query / and the sentence2 natively with model.train?
-
## 집현전 중급반 스터디
- 2022년 6월 26일 일요일 9시
- 장동건님 김제우님 김종은님 이기성님 발표
- 논문 링크: https://arxiv.org/abs/1910.01108
> ### Abstract
> As Transfer Learning from large-scale pre-trained models becomes more pr…
-
Hi,
Thanks for releasing your code in this repository! It would be exciting to try the neural topic models with Knowledge Distillation.
I was wondering whether you would like to give a simple e…
-
## タイトル: 2ヘッド知識蒸留: 補助ヘッドによるロジット活用の強化
## リンク: https://arxiv.org/abs/2411.08937
## 概要:
従来の知識蒸留は、生徒モデルの予測確率を正解ラベルと教師モデルの予測確率の両方に合わせることに注力しています。しかし、ロジットから予測確率への変換は、ある種の不可欠な情報を曖昧にする可能性があります。この問題に対処するため…