AMD-SHARK-Studio/tank/torch_model_list.csv

1	model_name	use_tracing	model_type	dynamic	param_count	tags	notes
2	microsoft/MiniLM-L12-H384-uncased	True	hf	True	66M	nlp;bert-variant;transformer-encoder	Large version has 12 layers; 384 hidden size; Smaller than BERTbase (66M params vs 109M params)
3	bert-base-uncased	True	hf	True	109M	nlp;bert-variant;transformer-encoder	12 layers; 768 hidden; 12 attention heads
4	bert-base-cased	True	hf	True	109M	nlp;bert-variant;transformer-encoder	12 layers; 768 hidden; 12 attention heads
5	google/mobilebert-uncased	True	hf	True	25M	nlp,bert-variant,transformer-encoder,mobile	24 layers, 512 hidden size, 128 embedding
6	alexnet	False	vision	True	61M	cnn,parallel-layers	The CNN that revolutionized computer vision (move away from hand-crafted features to neural networks),10 years old now and probably no longer used in prod.
7	resnet18	False	vision	True	11M	cnn,image-classification,residuals,resnet-variant	1 7x7 conv2d and the rest are 3x3 conv2d
8	resnet50	False	vision	True	23M	cnn,image-classification,residuals,resnet-variant	Bottlenecks with only conv2d (1x1 conv -> 3x3 conv -> 1x1 conv blocks)
9	resnet101	False	vision	True	29M	cnn,image-classification,residuals,resnet-variant	Bottlenecks with only conv2d (1x1 conv -> 3x3 conv -> 1x1 conv blocks)
10	squeezenet1_0	False	vision	True	1.25M	cnn,image-classification,mobile,parallel-layers	Parallel conv2d (1x1 conv to compress -> (3x3 expand | 1x1 expand) -> concat)
11	wide_resnet50_2	False	vision	True	69M	cnn,image-classification,residuals,resnet-variant	Resnet variant where model depth is decreased and width is increased.
12	mobilenet_v3_small	False	vision	True	2.5M	image-classification,cnn,mobile	N/A
13	google/vit-base-patch16-224	True	hf_img_cls	False	86M	image-classification,vision-transformer,transformer-encoder	N/A
14	microsoft/resnet-50	True	hf_img_cls	False	23M	image-classification,cnn,residuals,resnet-variant	Bottlenecks with only conv2d (1x1 conv -> 3x3 conv -> 1x1 conv blocks)
15	facebook/deit-small-distilled-patch16-224	True	hf_img_cls	False	22M	image-classification,vision-transformer,cnn	N/A
16	microsoft/beit-base-patch16-224-pt22k-ft22k	True	hf_img_cls	False	86M	image-classification,transformer-encoder,bert-variant,vision-transformer	N/A
17	nvidia/mit-b0	True	hf_img_cls	False	3.7M	image-classification,transformer-encoder	SegFormer
18	mnasnet1_0	False	vision	True	-	cnn, torchvision, mobile, architecture-search	Outperforms other mobile CNNs on Accuracy vs. Latency
19	resnet50_fp16	False	vision	True	23M	cnn,image-classification,residuals,resnet-variant	Bottlenecks with only conv2d (1x1 conv -> 3x3 conv -> 1x1 conv blocks)
20	bert-base-uncased_fp16	True	fp16	False	109M	nlp;bert-variant;transformer-encoder	12 layers; 768 hidden; 12 attention heads