AlbertForMaskedLM,8
AllenaiLongformerBase,8
BartForCausalLM,8
BertForMaskedLM,32
BlenderbotForCausalLM,32
BlenderbotForConditionalGeneration,16
DebertaV2ForMaskedLM,8
DistilBertForMaskedLM,256
DistillGPT2,32
ElectraForCausalLM,64
GPT2ForSequenceClassification,8
GPTJForCausalLM,1
GPTJForQuestionAnswering,1
GPTNeoForCausalLM,32
GPTNeoForSequenceClassification,32
GoogleFnet,32
LayoutLMForMaskedLM,32
M2M100ForConditionalGeneration,64
MBartForCausalLM,8
MT5ForConditionalGeneration,32
MegatronBertForCausalLM,16
MobileBertForMaskedLM,256
OPTForCausalLM,4
PLBartForCausalLM,16
PegasusForCausalLM,128
RobertaForCausalLM,32
T5ForConditionalGeneration,8
T5Small,8
TrOCRForCausalLM,64
XGLMForCausalLM,32
XLNetLMHeadModel,16
YituTechConvBert,32
meta-llama/Llama-3.2-1B,8
google/gemma-2-2b,8
google/gemma-3-4b-it,8
openai/whisper-tiny,8
Qwen/Qwen3-0.6B,8
mistralai/Mistral-7B-Instruct-v0.3, 8
openai/gpt-oss-20b, 8
