-
Notifications
You must be signed in to change notification settings - Fork 2.6k
Insights: microsoft/unilm
Overview
-
- 3 Merged pull requests
- 0 Open pull requests
- 3 Closed issues
- 8 New issues
Could not load contribution data
Please try again later
3 Pull requests merged by 3 people
-
fix import flex_head_fa
#1679 merged
Jan 7, 2025 -
fix bug
#1674 merged
Dec 15, 2024 -
merge latentlm
#1669 merged
Dec 12, 2024
3 Issues closed by 3 people
-
bug in collate_fn
#1678 closed
Dec 23, 2024 -
BEATs extract feature produce nan value --solved
#1672 closed
Dec 13, 2024 -
Max Attention Logit Calculation Diff Transformer
#1666 closed
Dec 8, 2024
8 Issues opened by 8 people
-
Significant gap in evaluation results of Textdiffuser2
#1677 opened
Dec 22, 2024 -
MH-MoE implementation?
#1676 opened
Dec 19, 2024 -
Beit3 Segmentation and Detection
#1675 opened
Dec 17, 2024 -
How to get the Unet Model used in the Textdiffuser which can map image to character segmentation mask?
#1673 opened
Dec 15, 2024 -
[BEATs] Links for the weights of trained BEATs model are unavailable
#1671 opened
Dec 12, 2024 -
[textdiffuser2] 如何使用textdiffuser 2的angle checkpoint?
#1670 opened
Dec 12, 2024 -
OCREval and MarkdownEval datasets
#1667 opened
Dec 10, 2024
8 Unresolved conversations
Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.
-
How to load WavLM ECAPA-TDNN embeddings for Speaker verification ?
#1369 commented on
Dec 12, 2024 • 0 new comments -
BEATs model produces NaN when using mixed precision with pytorch lightning
#1569 commented on
Dec 13, 2024 • 0 new comments -
YOCO: data and model opensource
#1566 commented on
Dec 13, 2024 • 0 new comments -
textdiffuser-2 inference after lora training
#1391 commented on
Dec 14, 2024 • 0 new comments -
fine-tune other datasets on VQA tasks
#1638 commented on
Dec 16, 2024 • 0 new comments -
Fine-tuning BEATs for ESC50 classification.
#1112 commented on
Dec 17, 2024 • 0 new comments -
[WavLM] Finetuning for speaker diarization
#1452 commented on
Dec 17, 2024 • 0 new comments -
Error doing Textdiffuser2 inpainting demo
#1617 commented on
Jan 5, 2025 • 0 new comments