Skip to content

Issues: huggingface/transformers

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

Clear current search query, filters, and sorts
21 Open 33 Closed
21 Open 33 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

LlavaForConditionalGeneration._merge_input_ids_with_image_features throws error bug Multimodal WIP Label your PR/Issue with WIP for some long outstanding Issues/PRs that are work in progress
#35169 opened Dec 9, 2024 by NicolasDrapier
4 tasks done
1
@zucchini-nlp
1
[Idefics 3] Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cuda:1 bug Multimodal Vision
#35031 opened Nov 30, 2024 by shyshin
2 of 4 tasks
1
2
Flash attention 2 broke when batch inference bug Multimodal Vision
#34824 opened Nov 20, 2024 by pspdada
2 of 4 tasks
1
@zucchini-nlp
1
Add GOT-OCR 2.0 to Transformers Multimodal New model run-slow
#34721 opened Nov 13, 2024 by yonigozlan Loading…
3 tasks done
30
uniformize kwargs for SAM Multimodal Processing Vision
#34578 opened Nov 2, 2024 by tibor-reiss Loading…
16
Compile Grounding DINO Compilation Issues related to torchdynamo and torchinductor Feature request Request for a new feature Multimodal Vision
#34556 opened Nov 1, 2024 by pspdada
2
uniformize kwargs for OneFormer Multimodal Processing Vision
#34547 opened Oct 31, 2024 by tibor-reiss Loading…
20
Vision (Auto)Processor multiple images finetuning example. Examples Which is related to examples in general Feature request Request for a new feature Multimodal
#34489 opened Oct 29, 2024 by lovodkin93
4
Add support for Aria model Feature request Request for a new feature Multimodal New model
#34078 opened Oct 10, 2024 by fakerybakery
2
Add Loss Functions for QFormer Training in BLIP-2 Model (ITC, ITM, and ITG) Feature request Request for a new feature Multimodal
#34019 opened Oct 8, 2024 by thisisiron
1
Enabled Flash Attention for PaliGemma models Flash Attention Multimodal run-slow
#34009 opened Oct 7, 2024 by aroun-coumar Loading…
1 of 5 tasks
1
12
Add ColPali to 🤗 transformers Multimodal New model run-slow Vision
#33736 opened Sep 26, 2024 by tonywu71 Loading…
16 tasks done
92
Add support for Molmo Feature request Request for a new feature Multimodal New model Vision
#33710 opened Sep 26, 2024 by fakerybakery
6
Qwen2-VL: Multi-GPU training bug Distributed Training / Models Feature request Request for a new feature Multimodal trainer Vision
#33666 opened Sep 23, 2024 by ManuelFay
2 of 4 tasks
8
Video Processor as a separate class Feature request Request for a new feature Multimodal Vision
#33504 opened Sep 16, 2024 by zucchini-nlp
6 tasks
1
@zucchini-nlp
3
The same situation as #31377 occurred when using Qwen/Qwen2-VL-7B-Instruct bug Cache Multimodal
#33399 opened Sep 10, 2024 by toondata
3 of 4 tasks
@zucchini-nlp
21
Track progress for VLMs refactoring Generation Multimodal Vision WIP Label your PR/Issue with WIP for some long outstanding Issues/PRs that are work in progress
#33374 opened Sep 8, 2024 by zucchini-nlp
13 of 16 tasks
@zucchini-nlp
1
Support Unified Multimodal Model Feature request Request for a new feature Multimodal New model
#33368 opened Sep 7, 2024 by KevinZeng08
1
Kosmos-2.5 implementation in transformers Multimodal New model
#30877 opened May 17, 2024 by Natyren
2 tasks done
@ydshieh
8
Adding imagebind Multimodal New model run-slow
#30690 opened May 7, 2024 by EduardoPach Loading…
1
231
Mixture of All Intelligence (MoAI) Multimodal New model
#29823 opened Mar 23, 2024 by Dev-Khant
2 tasks done
4
ProTip! Find all open issues with in progress development work with linked:pr.