Skip to content

Pull requests: huggingface/transformers

New pull request New
557 Open 18,304 Closed
557 Open 18,304 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
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Skip failing QwenVL test for now
#35933 opened Jan 28, 2025 by Cyrilvallez Loading…
Add rust to deepspeed image so it can build tokenizers
#35932 opened Jan 28, 2025 by ivarflakstad Loading…
1
Use torch 2.5.0 for deepspeed amd image
#35931 opened Jan 28, 2025 by ivarflakstad Loading…
1
layernorm_decay_fix
#35927 opened Jan 28, 2025 by Ryoo72 Loading…
3 of 5 tasks
[WIP] add deepseekv3
#35926 opened Jan 28, 2025 by bzantium Loading…
2 of 4 tasks
1
Fix usage of unpad_input function
#35925 opened Jan 28, 2025 by pavelgein Loading…
1 of 5 tasks
1
Support batching for UsefulSensors Moonshine
#35922 opened Jan 28, 2025 by njeffrie Loading…
7
Fix Whisper Beam Search Output Tests #32373
#35921 opened Jan 27, 2025 by sambhavnoobcoder Loading…
1
changed MllamaPreTrainedModel._prepare_4d_causal_attention_mask
#35920 opened Jan 27, 2025 by AndriiZelenko Loading…
2 of 5 tasks
1
Update deprecated arguments in jax.numpy.clip.
#35919 opened Jan 27, 2025 by rasmi Loading…
1
Added Support for Custom Quantization
#35915 opened Jan 27, 2025 by keetrap Loading…
2 tasks done
1
10
Missing weights not initialized properly #35437
#35913 opened Jan 27, 2025 by sambhavnoobcoder Loading…
1
1
[don't merge] check log
#35912 opened Jan 27, 2025 by ydshieh • Draft
6
Fix how we compute the final non-padding token for ForSequenceClassification models
#35911 opened Jan 27, 2025 by Rocketknight1 Loading…
3
1
Add generation config validation using Pydantic
#35910 opened Jan 27, 2025 by Manalelaidouni Loading…
Add process_retry util
#35908 opened Jan 27, 2025 by ivarflakstad Loading…
9
Fix Mask2Former Weight Initialization Issues #35877
#35904 opened Jan 27, 2025 by sambhavnoobcoder Loading…
1
4
Fix nighlty CIs: missing atols
#35903 opened Jan 27, 2025 by ArthurZucker • Draft
Introduce modular files for speech models
#35902 opened Jan 27, 2025 by nikosanto13 Loading…
1 of 5 tasks
3
Several fixes related to rotary position embeddings
#35901 opened Jan 27, 2025 by mseeger Loading…
4 of 5 tasks
2
Fix Gradient Checkpointing for Deberta & Deberta-V2 using PEFT / Adapters
#35898 opened Jan 26, 2025 by lenglaender Loading…
1 of 5 tasks
1
add shared experts for upcoming Granite 4.0 language models
#35894 opened Jan 26, 2025 by mayank31398 Loading…
1
Fix synced multi-GPU generation with LLMs and VLMs
#35893 opened Jan 26, 2025 by ManukyanD Loading…
1 of 5 tasks
Add Doge model
#35891 opened Jan 25, 2025 by LoserCheems Loading…
4 of 5 tasks
1
4
Iterative generation using Input embeds and static cache
#35890 opened Jan 25, 2025 by yaswanth19 Loading…
1 of 5 tasks
1
3
ProTip! no:milestone will show everything without a milestone.