Skip to content

Issues: microsoft/torchscale

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

22 Open 57 Closed
22 Open 57 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

train.py: error: unrecognized arguments: --flash-attention --segment-length [2048,4096] --dilated-ratio [1,2]
#112 opened Nov 8, 2024 by github2657529567
No module named 'sentencepiece'
#111 opened Nov 8, 2024 by github2657529567
torchscale 0.3.0 requires fairscale==0.4.0, but you have fairscale 0.4.13 which is incompatible.
#110 opened Sep 6, 2024 by pandayummy
Question about LongNet attention map overlap
#108 opened May 27, 2024 by RmZeta2718
Different batch sizes lead to different evalution results for LongVIT
#107 opened May 14, 2024 by HHHedo
How to test the model
#106 opened May 10, 2024 by ReloJeffrey
pip error
#105 opened Apr 28, 2024 by wanghaoran-ucas
Where is the offset implemented in Multi-head dilated attention ?
#104 opened Apr 20, 2024 by AshStuff
can't use longvit
#103 opened Apr 18, 2024 by abebe9849
Question about learnable segment lengths and dilation rates
#102 opened Apr 10, 2024 by benrousePUC
How to use retention in RetNet for cross-attention?
#101 opened Mar 23, 2024 by yxchng
Checkpoint for RetNet
#99 opened Mar 20, 2024 by macsz
about the longnet's ppl
#95 opened Jan 10, 2024 by robotzheng
2
Wrong Rnm Normalization.
#86 opened Dec 12, 2023 by pdradx
@donglixp
1
Introducing padding_mask to RetNet
#85 opened Dec 9, 2023 by xtwigs
2
Question regarding the configuration of decoder_retention_heads
#84 opened Nov 30, 2023 by Kratos-Wen
@donglixp
2
Training RetNet on A100 GPUs
#83 opened Nov 26, 2023 by Antoine-Bergerault
1
[Minor issue] Discrepancy inside arxiv paper
#82 opened Nov 20, 2023 by radarFudan
@donglixp
retnet traning config
#64 opened Sep 3, 2023 by hanlinxuy
@donglixp
7
embed_tokens
#59 opened Aug 16, 2023 by CodeMiningCZW
@donglixp
4
testing very large attention windows
#36 opened Jul 6, 2023 by fredzannarbor
About running speed
#23 opened Mar 28, 2023 by NieShenRuc
ProTip! no:milestone will show everything without a milestone.