# List of models
albert,albert/albert-base-v2
align,kakaobrain/align-base,xfail,Compile error: AvgPool: Kernel after dilation has size (dim: 640) larger than the data shape after padding (dim: 9) at axis 0.
altclip,BAAI/AltCLIP
audio-spectrogram-transformer,MIT/ast-finetuned-audioset-10-10-0.4593
autoformer,huggingface/autoformer-tourism-monthly,xfail,Load error: mat1 and mat2 shapes cannot be multiplied
bark,suno/bark,xfail,Load error: got an unexpected keyword argument 'input_ids'
bart,facebook/bart-large-mnli
beit,microsoft/beit-base-patch16-224-pt22k-ft22k
bert,sentence-transformers/all-MiniLM-L6-v2
bert-generation,google/bert_for_seq_generation_L-24_bbc_encoder
big_bird,google/bigbird-roberta-base
bigbird_pegasus,google/bigbird-pegasus-large-arxiv
biogpt,microsoft/biogpt
bit,google/bit-50
blenderbot,facebook/blenderbot-400M-distill
blenderbot-small,facebook/blenderbot_small-90M
blip,Salesforce/blip-image-captioning-large
blip_2_qformer,ZinengTang/qformer
blip_2_vision_model,ZinengTang/clip_last_layer_removed
blip-2,Salesforce/blip2-opt-2.7b:language_projection
blip-2,Salesforce/blip2-opt-2.7b:qformer
blip-2,Salesforce/blip2-opt-2.7b:vision_model
bort,stefan-it/bort-full
bridgetower,regisss/bridgetower-newyorker-a100-8x
bros,naver-clova-ocr/bros-base-uncased
camembert,Jean-Baptiste/camembert-ner
canine,google/canine-c,xfail,aten::slice: Parameter axis 3 out of the tensor rank range
chinese_clip,OFA-Sys/chinese-clip-vit-base-patch16
clap,laion/clap-htsat-unfused:audio_model
clap,laion/clap-htsat-unfused:audio_projection
clip,openai/clip-vit-large-patch14
clip_text_model,maze/CLIP-ViT-bigG-14
clip_vision_model,SajjadAyoubi/clip-fa-vision
clipseg,CIDAS/clipseg-rd64-refined
clvp,susnato/clvp_dev
codegen,Salesforce/codegen-350M-mono
conditional_detr,microsoft/conditional-detr-resnet-50
convbert,YituTech/conv-bert-base
convnext,facebook/convnext-large-224
convnextv2,Pavarissy/ConvNextV2-large-DogBreed
ctrl,Salesforce/ctrl
cvt,microsoft/cvt-13
data2vec-audio,m-a-p/music2vec-v1
data2vec-text,facebook/data2vec-text-base
data2vec-vision,facebook/data2vec-vision-large-ft1k
deberta,microsoft/deberta-base
deberta-v2,MoritzLaurer/mDeBERTa-v3-base-xnli-multilingual-nli-2mil7
decision_transformer,edbeeching/decision-transformer-gym-hopper-expert
deformable_detr,SenseTime/deformable-detr,xfail,Trace error: op->outputs().size() == 1 INTERNAL ASSERT FAILED
deit,facebook/deit-base-distilled-patch16-224
deta,jozhang97/deta-swin-large,xfail,ValueError: operands could not be broadcast together with shapes
detr,facebook/detr-resnet-50
dinov2,facebook/dinov2-base
distilbert,distilbert/distilbert-base-uncased-finetuned-sst-2-english
donut-swin,pasusarla/donut_encoder
dpr,facebook/dpr-question_encoder-single-nq-base
dpt,Intel/dpt-large
efficientformer,DunnBC22/efficientformer-l3-300-Brain_Tumors_Image_Classification
efficientnet,google/efficientnet-b7,xfail,Compile error: AvgPool: Kernel after dilation has size (dim: 2560) larger than the data shape after padding (dim: 19) at axis 0.
electra,google/electra-base-discriminator
encodec,facebook/encodec_24khz
encoder_decoder,patrickvonplaten/bert2gpt2-cnn_dailymail-fp16,xfail,Load error: You have to specify either input_ids or inputs_embeds
encoder-decoder,raynardj/wenyanwen-chinese-translate-to-ancient
ernie,nghuyong/ernie-3.0-base-zh
ernie_m,MoritzLaurer/ernie-m-large-mnli-xnli
esm,InstaDeepAI/nucleotide-transformer-500m-human-ref
f_t5,flax-community/ft5-cnn-dm
fastspeech2_conformer,espnet/fastspeech2_conformer,xfail,Compile error: CPU plug-in doesn't support Tile operation with dynamic rank. Operation name: aten::repeat_interleave/Tile
fastspeech2_conformer_with_hifigan,espnet/fastspeech2_conformer_with_hifigan,xfail,Compile error: CPU plug-in doesn't support Tile operation with dynamic rank. Operation name: __module.model/aten::repeat_interleave/Tile
flaubert,lincoln/flaubert-mlsum-topic-classification
flava,facebook/flava-full
flava_image_codebook,facebook/flava-image-codebook
fnet,google/fnet-base
focalnet,microsoft/focalnet-small
fsmt,facebook/wmt19-en-ru,xfail,Trace error: Only tensors lists tuples of tensors or dictionary of tensors can be output from traced functions
funnel,funnel-transformer/small
git,microsoft/git-large-coco,xfail,Trace error: We don't have an op for aten::full but it isn't a special case
glpn,vinvino02/glpn-nyu
gpt_bigcode,bigcode/tiny_starcoder_py
gpt_neo,EleutherAI/gpt-neo-2.7B
gptsan-japanese,Tanrei/GPTSAN-japanese,xfail,Unsupported op aten::index_put_ prim::TupleConstruct prim::TupleUnpack
graphormer,clefourrier/graphormer-base-pcqm4mv2,xfail,Load error: GraphormerForGraphClassification.forward() missing 6 required positional arguments: 'input_edges' 'attn_bias' 'in_degree' 'out_degree' 'spatial_pos' and 'attn_edge_type'
grounding-dino,IDEA-Research/grounding-dino-base,xfail,Trace error: op->outputs().size() == 1 INTERNAL ASSERT FAILED
groupvit,nvidia/groupvit-gcc-yfcc
hiera,namangarg110/hiera_base_224
hifigan,microsoft/speecht5_hifigan,xfail,Load error: The size of tensor a (100) must match the size of tensor b (80) at non-singleton dimension 1
hubert,facebook/hubert-large-ls960-ft
hybridbert,gokuls/bert_12_layer_model_v1
ibert,DunnBC22/ibert-roberta-base-Abusive_Or_Threatening_Speech
idefics,HuggingFaceM4/tiny-random-idefics
imagegpt,openai/imagegpt-small
informer,huggingface/informer-tourism-monthly,xfail,Load error: mat1 and mat2 shapes cannot be multiplied
instructblip,Salesforce/instructblip-vicuna-7b
jukebox,openai/jukebox-1b-lyrics,xfail,Load error: Module [JukeboxModel] is missing the required "forward" function
jukebox_vqvae,ArthurZ/jukebox-vqvae,skip,Load error: The checkpoint you are trying to load has model type `jukebox_vqvae` but Transformers does not recognize this architecture
kobert,weonjae0211/ds-kobert
kosmos-2,microsoft/kosmos-2-patch14-224
LanguageBindDepth,LanguageBind/LanguageBind_Depth
LanguageBindImage,LanguageBind/LanguageBind_Image
LanguageBindThermal,LanguageBind/LanguageBind_Thermal
layoutlm,impira/layoutlm-document-qa
layoutlmv3,microsoft/layoutlmv3-base
led,pszemraj/led-large-book-summary
levit,facebook/levit-128S,xfail,Trace error: Cannot insert a Tensor that requires grad as a constant
lilt,nielsr/lilt-xlm-roberta-base
llama_with_landmark,Leooyii/Landmark_512_Slimpajama_1B
longformer,allenai/longformer-base-4096
longt5,pszemraj/long-t5-tglobal-base-16384-book-summary
luke,oshizo/sbert-jsnli-luke-japanese-base-lite
lxmert,unc-nlp/lxmert-base-uncased
m2m_100,facebook/nllb-200-distilled-600M
mamba,dominguesm/mambarim-110m,xfail,Trace error: Tracer cannot infer type of tensor
marian,Helsinki-NLP/opus-mt-zh-en
markuplm,microsoft/markuplm-base
mask2former,facebook/mask2former-swin-large-coco-panoptic
maskformer,facebook/maskformer-swin-large-ade
mbart,facebook/mbart-large-50-many-to-many-mmt
mctct,speechbrain/m-ctc-t-large
mega,Bingsu/mega-150m-arch,xfail,Trace error: Cannot insert a Tensor that requires grad as a constant
megatron-bert,UFNLP/gatortron-base
mgp-str,alibaba-damo/mgp-str-base
mobilebert,google/mobilebert-uncased
mobilenet_v1,google/mobilenet_v1_0.75_192
mobilenet_v2,google/mobilenet_v2_1.0_224
mobilevit,apple/mobilevit-small
mobilevitv2,apple/mobilevitv2-1.0-imagenet1k-256
mpnet,sentence-transformers/all-mpnet-base-v2
mra,uw-madison/mra-base-512-4
mt5,csebuetnlp/mT5_multilingual_XLSum
musicgen,facebook/musicgen-large
musicgen_melody,ylacombe/musicgen-melody,xfail,Accuracy validation failed
mvp,RUCAIBox/mtl-data-to-text
nezha,sijunhe/nezha-cn-base
nllb_moe,hf-tiny-model-private/tiny-random-NllbMoeForConditionalGeneration,xfail,Trace error: Tracer cannot infer type of Seq2SeqMoEOutput
nystromformer,uw-madison/nystromformer-4096
olmo,DrNicefellow/Microscopic-Olmo-2B-1.1k-steps
oneformer,shi-labs/oneformer_ade20k_swin_tiny,xfail,Different number of outputs between framework and OpenVINO
openai-gpt,openai-community/openai-gpt
open-llama,aerner/lm-v2
owlv2,google/owlv2-base-patch16-ensemble
owlvit,google/owlvit-base-patch32
patchtsmixer,ibm-granite/granite-timeseries-patchtsmixer,xfail,Only tensors lists tuples of tensors or dictionary of tensors can be output from traced functions
patchtst,ibm/patchtst-etth1-pretrain,xfail,Conversion is failed for: aten::unfold
pegasus,tuner007/pegasus_paraphrase
pegasus_x,pszemraj/pegasus-x-large-book-summary
perceiver,hf-internal-testing/tiny-random-vision_perceiver_conv
phi,susnato/phi-1_5_dev
phi3,MaziyarPanahi/calme-2.1-phi3-4b
pix2struct,google/deplot,xfail,Accuracy validation failed
pix2struct_vision_model,UiPath/pix2struct-vision-base
plbart,uclanlp/plbart-base
poolformer,sail/poolformer_m36
prophetnet,microsoft/prophetnet-large-uncased-squad-qg
pvt,Zetatech/pvt-tiny-224
rag,facebook/rag-token-nq,xfail,Load error: Make sure that `context_input_ids` are passed if no `retriever` is set.
realm,google/realm-orqa-nq-openqa,xfail,Load error: 'NoneType' object is not callable
reformer,google/reformer-enwik8,xfail,Trace error: _Map_base::at
regnet,facebook/regnet-x-002
rembert,google/rembert
resnet,microsoft/resnet-50
roberta,deepset/roberta-base-squad2
roberta-prelayernorm,andreasmadsen/efficient_mlm_m0.40
roc_bert,weiweishi/roc-bert-base-zh
roformer,junnyu/roformer_chinese_sim_char_small
rt_detr,rafaelpadilla/porting_rt_detr,xfail,Trace error: Only tensors lists tuples of tensors or dictionary of tensors can be output from traced functions
rwkv,RWKV/rwkv-4-169m-pile
sam,facebook/sam-vit-huge
scibert,Goutham-Vignesh/ContributionSentClassification-scibert
seamless_m4t,facebook/hf-seamless-m4t-medium
segformer,mattmdjaga/segformer_b2_clothes
seg-ment-tation,NiCy/seg-ment-tation
sew,anton-l/sew-mid-100k-ft-keyword-spotting
sew-d,asapp/sew-d-base-plus-400k-ft-ls100h
siglip,google/siglip-base-patch16-224
siglip_vision_model,bczhou/TinyLLaVA-3.1B-SigLIP
speech_to_text,facebook/s2t-small-librispeech-asr
speech_to_text_2,pirxus/s2t2_decoder_base
speech-encoder-decoder,facebook/wav2vec2-xls-r-300m-en-to-15
speecht5,microsoft/speecht5_tts,xfail,Unsupported op aten::bernoulli
splinter,tau/splinter-base-qass
squeezebert,typeform/squeezebert-mnli
superpoint,stevenbucaille/superpoint,xfail,Unsupported prim::TupleConstruct prim::TupleUnpack
swiftformer,MBZUAI/swiftformer-xs
swin,microsoft/swin-tiny-patch4-window7-224
swin2sr,caidas/swin2SR-classical-sr-x2-64
swinv2,microsoft/swinv2-tiny-patch4-window8-256
switch_transformers,google/switch-base-8,xfail,Unsupported aten::index_put_ aten::logsumexp prim::TupleConstruct prim::TupleUnpack
t5,google/flan-t5-base
table-transformer,microsoft/table-transformer-detection
tapas,google/tapas-base-finetuned-wtq
tapex,nielsr/tapex-large
time_series_transformer,huggingface/time-series-transformer-tourism-monthly
timesformer,facebook/timesformer-base-finetuned-k400
trajectory_transformer,CarlCochet/trajectory-transformer-halfcheetah-medium-v2
transfo-xl,transfo-xl/transfo-xl-wt103,xfail,Load error: type_as() missing 1 required positional arguments: "other"
tvlt,ZinengTang/tvlt-base,xfail,Load error: Matching task requires labels
tvp,Intel/tvp-base,xfail,Load error: 'NoneType' object has no attribute 'dtype'
udop,nielsr/udop-large,xfail,Trace error: We don't have an op for aten::full_like but it isn't a special case
umt5,EleutherAI/pile-t5-large
unispeech,microsoft/unispeech-1350-en-17h-ky-ft-1h
unispeech-sat,microsoft/unispeech-sat-base-100h-libri-ft
univnet,dg845/univnet-dev,xfail,Load error: "normal_kernel_cpu" not implemented for 'Long'
upernet,openmmlab/upernet-convnext-small
van,Visual-Attention-Network/van-tiny
videomae,MCG-NJU/videomae-base-finetuned-kinetics
vilt,dandelin/vilt-b32-finetuned-vqa,xfail,Accuracy validation failed
vision-encoder-decoder,nlpconnect/vit-gpt2-image-captioning
visual_bert,uclanlp/visualbert-vqa-coco-pre
vit,google/vit-base-patch16-224
vit_mae,facebook/vit-mae-base
vit_msn,facebook/vit-msn-large-7
vit-hybrid,google/vit-hybrid-base-bit-384
vitmatte,nielsr/vitmatte-small-composition-1k,xfail,Unsupported aten::FloatImplicit aten::__contains__ aten::__isnot__ aten::append prim::Uninitialized prim::unchecked_cast
vits,facebook/mms-tts-eng,xfail,operands could not be broadcast together with shapes
vivit,google/vivit-b-16x2-kinetics400
wav2vec2,jonatasgrosman/wav2vec2-large-xlsr-53-english
wav2vec2_base,gelbanna/test,xfail,Load error: expected scalar type Long but found Float
wav2vec2-conformer,codenamewei/speech-to-text
wavlm,microsoft/wavlm-large
whisper,openai/whisper-large-v3
xclip,microsoft/xclip-base-patch32
xglm,facebook/xglm-564M
xlm,FacebookAI/xlm-mlm-100-1280
xlm-prophetnet,microsoft/xprophetnet-large-wiki100-cased
xlm-roberta,FacebookAI/xlm-roberta-base
xlm-roberta-xl,facebook/xlm-roberta-xl
xlnet,xlnet/xlnet-base-cased
xmod,facebook/xmod-base
yolos,hustvl/yolos-tiny
yoso,MrAnderson/yoso-4096-full-trivia
