mirror of
https://github.com/pytorch/pytorch.git
synced 2025-10-20 12:54:11 +08:00
f76fdcaaf8
Prune models from TorchInductor dashboard to reduce ci cost. This PR prunes for hugging face models according to the [doc](https://docs.google.com/document/d/1nLPNNAU-_M9Clx9FMrJ1ycdPxe-xRA54olPnsFzdpoU/edit?tab=t.0), which reduces from 46 to 27 models. Pull Request resolved: https://github.com/pytorch/pytorch/pull/164815 Approved by: https://github.com/anijain2305, https://github.com/seemethere, https://github.com/huydhn, https://github.com/malfet
29 lines
604 B
Plaintext
29 lines
604 B
Plaintext
AlbertForMaskedLM,4
|
|
AllenaiLongformerBase,4
|
|
BartForCausalLM,4
|
|
BertForMaskedLM,16
|
|
BigBird,32
|
|
BlenderbotForCausalLM,32
|
|
DebertaV2ForMaskedLM,16
|
|
DistilBertForMaskedLM,128
|
|
DistillGPT2,16
|
|
ElectraForCausalLM,8
|
|
GoogleFnet,16
|
|
GPT2ForSequenceClassification,4
|
|
LayoutLMForMaskedLM,16
|
|
M2M100ForConditionalGeneration,16
|
|
MBartForCausalLM,4
|
|
MegatronBertForCausalLM,4
|
|
MobileBertForMaskedLM,64
|
|
MT5ForConditionalGeneration,16
|
|
OPTForCausalLM,2
|
|
PegasusForCausalLM,32
|
|
PLBartForCausalLM,8
|
|
RobertaForCausalLM,16
|
|
T5ForConditionalGeneration,4
|
|
T5Small,1
|
|
TrOCRForCausalLM,32
|
|
XGLMForCausalLM,8
|
|
XLNetLMHeadModel,8
|
|
YituTechConvBert,16
|