[Mistral&Mixtral]Add sliding window param to sdpa after torch 2.2.0#29220
Closed
ehuaa wants to merge 55 commits intohuggingface:mainfrom ehuaa:add_sliding_window_for_sdpa
+3,503-784
Commits
Commits on Feb 22, 2024
- committed
- committed
- committed
Merge branch 'add_sliding_window_for_sdpa' of https://mirror.ghproxy.com/https://github.com/ehuaa/transformers into add_sliding_window_for_sdpa
committed- committed
- committed
- committed
Commits on Feb 24, 2024
Commits on Feb 27, 2024
- committed
- authored
- authored
- authored
- authored
- authored
Commits on Feb 28, 2024
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
Commits on Feb 29, 2024
- authored
- authored
- authored
- authored
- authored
- authored
Commits on Mar 1, 2024
Expose
offload_buffersparameter ofacceleratetoPreTrainedModel.from_pretrainedmethod (huggingface#28755)authored- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
Commits on Mar 2, 2024
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
Merge branch 'add_sliding_window_for_sdpa' of https://mirror.ghproxy.com/https://github.com/ehuaa/transformers into add_sliding_window_for_sdpa
committed