Automated PR: Downstream develop rebase new changes#44
Closed
Cemberk wants to merge 176 commits intodevelopfrom tmp-develop-20240812
+22,657-5,880
Commits
Commits on Jul 23, 2024
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
Enhancing SFT Training Efficiency Using Packing and FlashAttention2 with Position IDs (huggingface#31629)
authored- authored
- committed
- authored
- authored
- authored
Commits on Jul 24, 2024
adds: extra_repr() to MambaRMSNorm to include hidden size / size of weights in the layer (huggingface#32171)
authoredfix: default value reflects the runtime environment variables rather than the ones present at import time. (huggingface#32153)
authored- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
Commits on Jul 25, 2024
- authored
- authored
- authored
- authored
- authored
- authored
- authored
Allow a specific microphone to be used by the ffmpeg audio pipeline utility functions. Default to using the currently active microphone on Mac (huggingface#31846)
- authored
Commits on Jul 26, 2024
- authored
- authored
- authored
- authored
Add check for
target_sizes is Noneinpost_process_image_guided_detectionfor owlv2 (huggingface#31934)authored[tests] fix
staticcache implementation is not compatible withattn_implementation==flash_attention_2(huggingface#32039)authored- authored
- authored
Commits on Jul 27, 2024
Commits on Jul 29, 2024
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
Commits on Jul 30, 2024
- authored
- authored
- authored
- authored
- authored
- authored
fixes to properly shard FSDP across cpu and meta for cpu_efficient_loading for prequantized 4bit (huggingface#32276)
authoredfixes huggingface#32329 : The Torch code is correct - to get an average of 10% o… (huggingface#32335)
authored- authored
- authored
Commits on Jul 31, 2024
- authored
- authored
- authored
- authored
- authored
- authored
>3-5x faster torch.compile forward compilation for autoregressive decoder models (huggingface#32227)
authored- authored
- authored
Commits on Aug 1, 2024
- authored
- authored
- authored
- authored
Check device map for saving tokenizer config on TPU (fix for issue huggingface#31971) (huggingface#32043)
authored- authored
- authored
- authored
- authored
- authored
Yell at the user if zero-3 init wasn't performed, but expected to have been done (huggingface#32299)
Commits on Aug 3, 2024
fix: (issue huggingface#32124) Exception raised when running
transformers/examples/flax/language-modeling/t5_tokenizer_model.py. (huggingface#32157)authoredMixtralFlashAttention2: put "plus 1" inside parentheses when calculating rotary_seq_len, allowing None position_ids input. (huggingface#31500)
authored
Commits on Aug 5, 2024
Bump keras from 2.8.0 to 2.13.1 in /examples/research_projects/decision_transformer (huggingface#32393)
authored- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
![dependabot[bot]](https://avatars.githubusercontent.com/in/29110?v=4&size=32){kind=avatar}
Commits on Aug 6, 2024
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- committed
- authored
Revert "fixes to properly shard FSDP across cpu and meta for cpu_effcient_loading for prequantized 4bit (huggingface#32276)" (huggingface#32477)
- authored
- authored
- authored
Commits on Aug 7, 2024
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
Commits on Aug 8, 2024
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
Commits on Aug 9, 2024
- authored
- authored
- authored
- authored
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?v=4&size=32){kind=avatar}
