dse

dse copied to clipboard

I am trying to understand this [code snippet](https://github.com/amazon-science/dse/blob/f645d74efd8b6a8b12593f9294f1d482e42946ae/pretrain/utils/contrastive_utils.py#L46C9-L51C26): ``` negimp = neg.log().exp() Ng = (negimp*neg).sum(dim = -1) / negimp.mean(dim = -1) loss_pos = (-posmask * torch.log(pos / (Ng+pos))).sum() / posmask.sum()...

voorhs

Bumps [transformers](https://github.com/huggingface/transformers) from 4.8.1 to 4.30.0. Release notes Sourced from transformers's releases. v4.30.0: 100k, Agents improvements, Safetensors core dependency, Swiftformer, Autoformer, MobileViTv2, timm-as-a-backbone 100k Transformers has just reached 100k stars...

dependabot[bot]

Hello, What impressive work! Would you please release the weights of DSE-dropout and DSE-dianli to facilitate further research？ thank you！

Zeng-WH

Hi, Thanks for sharing great work! I have a question about the dataset in the evaluation process. Currently, I want to use dstc2 data to reproduce dialogue action prediction. However,...

yukyunglee

Hi @Dejiao2018 May I ask where can I find the file hwu64_label2id.json? Thank you!

MatthewCYM