Ecosyste.ms: Issues

An open API service for providing issue and pull request metadata for open source projects.

GitHub / hyunwoongko/transformer issues and pull requests

#32 - Could this lead to a bug due to dimension mismatch?

Issue - State: open - Opened by sonrisa07 2 months ago

#31 - complete the embedding function

Pull Request - State: open - Opened by EdgeObserver 3 months ago

#30 - empty function

Issue - State: closed - Opened by TimelyRain6821 3 months ago - 2 comments

#29 - Feature/basic modifications

Pull Request - State: closed - Opened by msaberp 6 months ago

#28 - About share weight between embeddings

Issue - State: open - Opened by TIPTOEHIGHERZ 6 months ago - 1 comment

#27 - About parameter nums of the model

Issue - State: closed - Opened by BeRikes 8 months ago - 3 comments

#26 - chore: format

Pull Request - State: closed - Opened by hoongeun 10 months ago

#25 - About initial learing rate

Issue - State: open - Opened by Marcusryz 10 months ago - 1 comment

#24 - Weight matrix sharing confusion

Issue - State: open - Opened by Jerry-hyl about 1 year ago

#22 - shaollow copy

Issue - State: closed - Opened by xxoospring about 1 year ago - 1 comment

#21 - About MultiHeadAttention's split method

Issue - State: closed - Opened by 0x6f6f over 1 year ago - 3 comments

#20 - src_pad_idx and trg_pad_idx

Issue - State: closed - Opened by sonrisa07 over 1 year ago

#19 - About multi-head attention in attention is all you need, thanks.

Issue - State: open - Opened by sonrisa07 over 1 year ago - 2 comments

#18 - how to resolve the issue ”No module named 'torch._C'“

Issue - State: open - Opened by linlone over 1 year ago

#17 - fix typos

Pull Request - State: closed - Opened by egliette almost 2 years ago - 2 comments

#16 - How to convert TorchText 0.9 to the latest version

Issue - State: open - Opened by zliguo almost 2 years ago - 10 comments

#15 - Question about implementation in the multi-head attention part

Issue - State: open - Opened by Acatsama0871 almost 2 years ago - 4 comments

#14 - fix pad bug

Pull Request - State: closed - Opened by GJ98 about 2 years ago

#14 - fix pad bug

Pull Request - State: closed - Opened by GJ98 about 2 years ago

#13 - The experimental results have a large gap with the one in README

Issue - State: open - Opened by Sun-Happy-YKX about 2 years ago - 1 comment

#12 - how to get dataset

Issue - State: open - Opened by Sun-Happy-YKX about 2 years ago - 5 comments

#11 - Potential bug in the pad mask

Issue - State: closed - Opened by RicardoDominguez about 2 years ago - 5 comments

#10 - Masked attention

Issue - State: closed - Opened by RicardoDominguez about 2 years ago - 3 comments

#9 - Reporting a bug during test time

Issue - State: closed - Opened by mediadepp over 2 years ago - 2 comments

#8 - [Bug] Dropout should comes before residual connection and layer norm

Issue - State: closed - Opened by ayaka14732 almost 3 years ago - 1 comment

#7 - LayerNorm implement

Issue - State: closed - Opened by GasolSun36 almost 3 years ago - 4 comments

#6 - [Bug] LayerNorm should not contain learnable parameters

Issue - State: closed - Opened by ayaka14732 about 3 years ago - 4 comments

#5 - Fix bug in README.md

Pull Request - State: closed - Opened by ayaka14732 about 3 years ago - 1 comment

#4 - modify transpose

Pull Request - State: closed - Opened by serotoninpm about 3 years ago - 2 comments

#3 - Questions regarding the implementation

Issue - State: open - Opened by yuvaraj91 over 3 years ago - 10 comments

#2 - masking and embedding issue

Pull Request - State: closed - Opened by GJ98 almost 4 years ago

#1 - pad masking issue

Pull Request - State: closed - Opened by GJ98 almost 4 years ago