---
`VastModelZOO`是瀚博半导体维护的AI模型平台，提供了人工智能多个领域（CV、AUDIO、NLP、LLM、MLLM等）的开源模型在瀚博训推芯片上的部署、训练示例。
`VastModelZOO`旨在基于瀚博半导体的硬件产品和软件SDK，展示最佳的编程实践，以达成模型的快速移植和最优性能。
为方便大家使用`VastModelZOO`，我们将持续增加典型模型和基础插件。
## 依赖软件
基于瀚博半导体的硬件产品使用`VastModelZOO`前，需联系销售代表获取部署软件包。
- 版本号：[VVI-25.11](https://developer.vastaitech.com/downloads/delivery-center?version_uid=484479150992789504)
## 模型列表
CV Models
- classification
| model | codebase | model list | model type | runtime |
| :------: | :------: | :------: | :------: | :-----: |
| [CSPNet](./cv/classification/cspnet/README.md) | [timm](https://github.com/rwightman/pytorch-image-models/blob/v0.6.5/timm/models/cspnet.py) | model name
cspresnet50
cspresnext50
cspdarknet53
| classification | Build_In |
| [CSPNet](./cv/classification/cspnet/README.md) | [mmcls](https://github.com/open-mmlab/mmclassification/blob/v0.23.1/configs/cspnet/README.md) | model name
cspresnet50
cspresnext50
cspdarknet53
| classification | Build_In |
| [CSPNet](./cv/classification/cspnet/README.md) | [ppcls](https://github.com/PaddlePaddle/PaddleClas/blob/v2.4.0/docs/zh_CN/models/Others.md) | model name
cspdarknet53
| classification | Build_In |
| [DenseNet](./cv/classification/densenet/README.md) | [timm](https://github.com/rwightman/pytorch-image-models/blob/v0.6.5/timm/models/densenet.py) | model name
densenet121
densenet161
densenet169
densenet201
densenetblur121d
| classification | Build_In |
| [DenseNet](./cv/classification/densenet/README.md) | [torchvision](https://github.com/pytorch/vision/blob/v0.9.0/torchvision/models/densenet.py) | model name
densenet121
densenet161
densenet169
densenet201
| classification | Build_In |
| [DenseNet](./cv/classification/densenet/README.md) | [mmcls](https://github.com/open-mmlab/mmclassification/blob/master/mmcls/models/backbones/densenet.py) | model name
densenet121
densenet161
densenet169
densenet201
| classification | Build_In |
| [DenseNet](./cv/classification/densenet/README.md) | [keras](https://github.com/keras-team/keras/blob/2.3.1/keras/applications/densenet.py) | model name
densenet121
densenet169
densenet201
| classification | Build_In |
| [DenseNet](./cv/classification/densenet/README.md) | [ppcls](https://github.com/PaddlePaddle/PaddleClas/blob/release/2.4/docs/zh_CN/algorithm_introduction/ImageNet_models.md#dpn-与-densenet-系列-1415) | model name
densenet121
densenet161
densenet169
densenet201
densenet264
| classification | Build_In |
| [DLANet](./cv/classification/dlanet/README.md) | [timm](https://github.com/rwightman/pytorch-image-models/blob/v0.6.5/timm/models/dla.py) | model name
dla34
dla46_c
dla46x_c
dla60
dla60x
dla60x_c
dla102
dla102x
dla102x2
dla169
dla60_res2net
dla60_res2next
| classification | Build_In |
| [DLANet](./cv/classification/dlanet/README.md) | [ppcls](https://github.com/PaddlePaddle/PaddleClas/blob/v2.4.0/docs/zh_CN/models/DLA.md) | model name
dla34
dla46_c
dla60
dla60x
dla60x_c
dla102
dla102x
dla102x2
dla169
| classification | Build_In |
| [DLANet](./cv/classification/dlanet/README.md) | [ucbdrive](https://github.com/ucbdrive/dla/blob/master/dla.py) | model name
dla34
dla46_c
dla46x_c
dla60
dla60x
dla60x_c
dla102
dla102x
dla102x2
dla169
| classification | Build_In |
| [EfficientNet](./cv/classification/efficientnet/README.md) | [timm](https://github.com/rwightman/pytorch-image-models/blob/v0.6.5/timm/models/efficientnet.py) | model name
efficientnet_b0
efficientnet_b1
efficientnet_b2
efficientnet_b3
efficientnet_b4
tf_efficientnet_b5
tf_efficientnet_b6
tf_efficientnet_b7
tf_efficientnet_b8
| classification | Build_In |
| [EfficientNet_v2](./cv/classification/efficientnet_v2/README.md) | [timm](https://github.com/rwightman/pytorch-image-models/blob/v0.6.5/timm/models/efficientnet.py) | model name
efficientnetv2_rw_t
efficientnetv2_rw_s
efficientnetv2_rw_m
| classification | Build_In |
| [ESNet](./cv/classification/esnet/README.md) | [ppcls](https://github.com/PaddlePaddle/PaddleClas/blob/v2.4.0/ppcls/arch/backbone/legendary_models/esnet.py) | model name
ESNet_x0_25
ESNet_x0_5
ESNet_x0_75
ESNet_x1_0
| classification | Build_In |
| [GhostNet](./cv/classification/ghostnet/README.md) | [timm](https://github.com/rwightman/pytorch-image-models/blob/v0.6.5/timm/models/ghostnet.py) | model name
ghostnet_100
| classification | Build_In |
| [GhostNet](./cv/classification/ghostnet/README.md) | [ppcls](https://github.com/PaddlePaddle/PaddleClas/blob/release%2F2.5/docs/zh_CN/models/ImageNet1k/GhostNet.md) | model name
ghostnet_x0_5
ghostnet_x1_0
ghostnet_x1_3
ghostnet_x1_3_ssld
| classification | Build_In |
| [HRNet](./cv/classification/hrnet/README.md) | [official](https://github.com/HRNet/HRNet-Image-Classification) | model name
HRNet_w18_small_model_v1
HRNet_w18_small_model_v2
HRNet_w18
HRNet_w30
HRNet_w32
HRNet_w40
HRNet_w44
HRNet_w48
HRNet_w64
| classification | Build_In |
| [HRNet](./cv/classification/hrnet/README.md) | [mmcls](https://github.com/open-mmlab/mmclassification/blob/master/mmcls/models/backbones/hrnet.py) | model name
HRNet_w18
HRNet_w30
HRNet_w32
HRNet_w40
HRNet_w44
HRNet_w48
HRNet_w64
| classification | Build_In |
| [HRNet](./cv/classification/hrnet/README.md) | [timm](https://github.com/rwightman/pytorch-image-models/blob/v0.6.5/timm/models/hrnet.py) | model name
HRNet_w18_small_model_v1
HRNet_w18_small_model_v2
HRNet_w18
HRNet_w30
HRNet_w32
HRNet_w40
HRNet_w44
HRNet_w48
HRNet_w64
| classification | Build_In |
| [HRNet](./cv/classification/hrnet/README.md) | [ppcls](https://github.com/PaddlePaddle/PaddleClas/blob/release/2.4/docs/zh_CN/algorithm_introduction/ImageNet_models.md#hrnet-系列-13) | model name
HRNet_W18_C
HRNet_W18_C_ssld
HRNet_W30_C
HRNet_W32_C
HRNet_W40_C
HRNet_W44_C
HRNet_W48_C
HRNet_W48_C_ssld
HRNet_W64_C
SE_HRNet_W64_C_ssld
| classification | Build_In |
| [Inception_v3](./cv/classification/inception_v3/README.md) | [timm](https://github.com/rwightman/pytorch-image-models/blob/v0.6.5/timm/models/inception_v3.py) | model name
inception_v3
tf_inception_v3
adv_inception_v3
gluon_inception_v3
| classification | Build_In |
| [Inception_v3](./cv/classification/inception_v3/README.md) | [torchvision](https://github.com/pytorch/vision/blob/main/torchvision/models/inception.py) | model name
inception_v3
| classification | Build_In |
| [Inception_v3](./cv/classification/inception_v3/README.md) | [ppcls](https://github.com/PaddlePaddle/PaddleClas/blob/v2.4.0/docs/zh_CN/models/Inception.md) | model name
inception_v3
| classification | Build_In |
| [Inception_v4](./cv/classification/inception_v4/README.md) | [timm](https://github.com/rwightman/pytorch-image-models/blob/v0.6.5/timm/models/inception_v4.py) | model name
inception v4
| classification | Build_In |
| [Inception_v4](./cv/classification/inception_v4/README.md) | [ppcls](https://github.com/PaddlePaddle/PaddleClas/blob/v2.4.0/docs/zh_CN/models/Inception.md) | model name
inception v4
| classification | Build_In |
| [IResNet](./cv/classification/iresnet/README.md) | [official](https://github.com/iduta/iresnet/blob/master/models/iresnet.py) | model name
iresnet50
iresnet101
iresnet152
iresnet200
| classification | Build_In |
| [MNasNet](./cv/classification/mnasnet/README.md) | [torchvision](https://github.com/pytorch/vision/blob/v0.9.0/torchvision/models/mnasnet.py) | model name
mnasnet0_5
mnasnet1_0
| classification | Build_In |
| [MobileNet_v1](./cv/classification/mobilenet_v1/README.md) | [keras](https://github.com/keras-team/keras/blob/v2.9.0/keras/applications/mobilenet.py) | model name
mobilenetv1
| classification | Build_In |
| [MobileNet_v1](./cv/classification/mobilenet_v1/README.md) | [ppcls](https://github.com/PaddlePaddle/PaddleClas/blob/v2.4.0/ppcls/arch/backbone/legendary_models/mobilenet_v1.py) | model name
mobilenet_v1_x0.25
mobilenet_v1_x0.5
mobilenet_v1_x0.75
mobilenet_v1
mobilenet_v1_ssld
| classification | Build_In |
| [MobileNet_v2](./cv/classification/mobilenet_v2/README.md) | [torchvision](https://github.com/pytorch/vision/blob/v0.9.0/torchvision/models/mobilenetv2.py) | model name
mobilenetv2
| classification | Build_In |
| [MobileNet_v2](./cv/classification/mobilenet_v2/README.md) | [timm](https://github.com/rwightman/pytorch-image-models/blob/master/timm/models/efficientnet.py#L92) | model name
mobilenetv2
| classification | Build_In |
| [MobileNet_v2](./cv/classification/mobilenet_v2/README.md) | [mmcls](https://github.com/open-mmlab/mmclassification/blob/master/mmcls/models/backbones/mobilenet_v2.py) | model name
mobilenetv2
| classification | Build_In |
| [MobileNet_v2](./cv/classification/mobilenet_v2/README.md) | [keras](https://github.com/keras-team/keras/blob/v2.9.0/keras/applications/mobilenet_v2.py) | model name
mobilenetv2
| classification | Build_In |
| [MobileNet_v2](./cv/classification/mobilenet_v2/README.md) | [ppcls](https://github.com/PaddlePaddle/PaddleClas/blob/v2.4.0/ppcls/arch/backbone/model_zoo/mobilenet_v2.py) | model name
mobilenet_v2_x0.25
mobilenet_v2_x0.5
mobilenet_v2_x0.75
mobilenet_v2
mobilenet_v2_x1.5
mobilenet_v2_x2.0
mobilenet_v2_ssld
| classification | Build_In |
| [MobileNet_v3](./cv/classification/mobilenet_v3/README.md) | [torchvision](https://github.com/pytorch/vision/blob/v0.9.0/torchvision/models/mobilenetv3.py) | model name
mobilenet_v3_small
mobilenet_v3_large
| classification | Build_In |
| [MobileNet_v3](./cv/classification/mobilenet_v3/README.md) | [timm](https://github.com/rwightman/pytorch-image-models/blob/v0.6.5/timm/models/mobilenetv3.py) | model name
mobilenet_v3_x1.0
mobilenet_v3_small_x0.5
mobilenet_v3_small_x0.75
mobilenet_v3_small_x1.0
mobilenet_v3_large_x1.0
| classification | Build_In |
| [MobileNet_v3](./cv/classification/mobilenet_v3/README.md) | [ppcls](https://github.com/PaddlePaddle/PaddleClas/blob/v2.4.0/ppcls/arch/backbone/legendary_models/mobilenet_v3.py) | model name
mobilenet_v3_small_x0.35
mobilenet_v3_small_x0.35_ssld
mobilenet_v3_small_x0.5
mobilenet_v3_small_x0.75
mobilenet_v3_small_x1.0
mobilenet_v3_small_x1.0_ssld
mobilenet_v3_small_x1.25
mobilenet_v3_large_x0.35
mobilenet_v3_large_x0.5
mobilenet_v3_large_x0.75
mobilenet_v3_large_x1.0
mobilenet_v3_large_x1.0_ssld
mobilenet_v3_large_x1.25
| classification | Build_In |
| [MobileNet_v3](./cv/classification/mobilenet_v3/README.md) | [showlo](https://github.com/ShowLo/MobileNetV3) | model name
mobilenet_v3_small
| classification | Build_In |
| [MobileNet_v3](./cv/classification/mobilenet_v3/README.md) | [sqlai](https://github.com/xiaolai-sqlai/mobilenetv3) | model name
mobilenet_v3_small
mobilenet_v3_large
| classification | Build_In |
| [MobileOne](./cv/classification/mobileone/README.md) | [official](https://github.com/apple/ml-mobileone/blob/main/mobileone.py) | model name
mobileone_s0
mobileone_s1
mobileone_s2
mobileone_s3
mobileone_s4
| classification | Build_In |
| [MobileViT](./cv/classification/mobilevit/README.md) | [apple](https://github.com/apple/ml-cvnets) | model name
mobilevit-s
| classification | Build_In |
| [PPLCNet](./cv/classification/pplcnet/README.md) | [ppcls](https://github.com/PaddlePaddle/PaddleClas/blob/v2.4.0/ppcls/arch/backbone/legendary_models/pp_lcnet.py) | model name
PPLCNet_x0_25
PPLCNet_x0_35
PPLCNet_x0_5
PPLCNet_x0_75
PPLCNet_x1_0
PPLCNet_x1_5
PPLCNet_x2_0
PPLCNet_x2_5
PPLCNet_x0_5_ssld
PPLCNet_x1_0_ssld
PPLCNet_x2_5_ssld
| classification | Build_In |
| [PPLCNet_v2](./cv/classification/pplcnet_v2/README.md) | [ppcls](https://github.com/PaddlePaddle/PaddleClas/blob/v2.4.0/ppcls/arch/backbone/legendary_models/pp_lcnet_v2.py) | model name
PPLCNetV2_base
PPLCNetV2_base_ssld
| classification | Build_In |
| [RepOPT](./cv/classification/repopt/README.md) | [official](https://github.com/DingXiaoH/RepOptimizers) | model name
RepOpt-VGG-B1
RepOpt-VGG-B2
RepOpt-VGG-L1
RepOpt-VGG-L2
| classification | Build_In |
| [RepVGG](./cv/classification/repvgg/README.md) | [official](https://github.com/DingXiaoH/RepVGG) | model name
RepVGG-A0
RepVGG-A1
RepVGG-A2
RepVGG-B0
RepVGG-B1
RepVGG-B2
RepVGG-B1g2
RepVGG-B1g4
RepVGG-B2g4
RepVGG-B3
RepVGG-B3g4
| classification | Build_In |
| [Res2Net](./cv/classification/res2net/README.md) | [ppcls](https://github.com/PaddlePaddle/PaddleClas/blob/release/2.5/docs/zh_CN/models/ImageNet1k/Res2Net.md) | model name
res2net50_14w_8s
res2net50_26w_4s
res2net50_vd_26w_4s
res2net50_vd_26w_4s_ssld
res2net101_vd_26w_4s
res2net101_vd_26w_4s_ssld
res2net200_vd_26w_4s
res2net200_vd_26w_4s_ssld
| classification | Build_In |
| [ResNeSt](./cv/classification/resnest/README.md) | [official](https://github.com/zhanghang1989/ResNeSt) | model name
resnest50
resnest101
resnest200
resnest269
| classification | Build_In |
| [ResNet](./cv/classification/resnet/README.md) | [timm](https://github.com/rwightman/pytorch-image-models/blob/v0.6.5/timm/models/resnet.py) | model name
resnet18
resnet26
resnet34
resnet50
resnet101
resnet152
gluon_resnet18_v1b
gluon_resnet34_v1b
gluon_resnet50_v1b
gluon_resnet50_v1c
gluon_resnet50_v1d
gluon_resnet50_v1s
gluon_resnet101_v1b
gluon_resnet101_v1c
gluon_resnet101_v1d
gluon_resnet101_v1s
gluon_resnet152_v1b
gluon_resnet152_v1c
gluon_resnet152_v1d
gluon_resnet152_v1s
| classification | Build_In |
| [ResNet](./cv/classification/resnet/README.md) | [torchvision](https://github.com/pytorch/vision/blob/v0.9.0/torchvision/models/resnet.py) | model name
resnet18
resnet34
resnet50
resnet101
resnet152
| classification | Build_In |
| [ResNet](./cv/classification/resnet/README.md) | [mmcls](https://github.com/open-mmlab/mmclassification/blob/v0.23.2/configs/resnet/README.md) | model name
resnet18
resnet34
resnet50
resnet101
resnet152
| classification | Build_In |
| [ResNet](./cv/classification/resnet/README.md) | [ppcls](https://github.com/PaddlePaddle/PaddleClas/blob/v2.4.0/docs/zh_CN/models/ResNet.md) | model name
resnet18
resnet18_vd
resnet34
resnet34_vd
resnet34_vd_ssld
resnet50
resnet50_vc
resnet50_vd
resnet50_vd_ssld
resnet101
resnet101_vd
resnet101_vd_ssld
resnet152
resnet152_vd
resnet200_vd
| classification | Build_In |
| [ResNet](./cv/classification/resnet/README.md) | [keras](https://github.com/keras-team/keras/blob/2.3.1/keras/applications/resnet.py) | model name
resnet50
resnet50v2
resnet101
resnet101v2
resnet152
resnet152v2
| classification | Build_In |
| [ResNet](./cv/classification/resnet/README.md) | [oneflow](https://github.com/Oneflow-Inc/vision/blob/main/flowvision/models/resnet.py) | model name
resnet18
resnet34
resnet50
resnet101
resnet152
| classification | Build_In |
| [ResNeXt](./cv/classification/resnext/README.md) | [timm](https://github.com/rwightman/pytorch-image-models/blob/v0.6.5/timm/models/resnet.py) | model name
resnext50_32x4d
resnext50d_32x4d
resnext101_32x8d
resnext101_64x4d
tv_resnext50_32x4d
| classification | Build_In |
| [ResNeXt](./cv/classification/resnext/README.md) | [torchvision](https://github.com/pytorch/vision/blob/v0.9.0/torchvision/models/resnet.py) | model name
resnext50_32x4d
resnext101_32x8d
| classification | Build_In |
| [ResNeXt](./cv/classification/resnext/README.md) | [mmcls](https://github.com/open-mmlab/mmclassification/blob/v0.23.2/configs/resnext/README.md) | model name
resnext50_32x4d
resnext101_32x4d
resnext101_32x8d
resnext152_32x4d
| classification | Build_In |
| [ResNeXt](./cv/classification/resnext/README.md) | [ppcls](https://github.com/PaddlePaddle/PaddleClas/blob/v2.4.0/docs/zh_CN/models/SEResNext_and_Res2Net.md) | model name
resnext50_32x4d
resnext50_64x4d
resnext50_vd_32x4d
resnext50_vd_64x4d
resnext101_32x4d
resnext101_64x4d
resnext101_vd_32x4d
resnext101_vd_64x4d
resnext152_32x4d
resnext152_64x4d
resnext152_vd_32x4d
resnext152_vd_64x4d
resnext101_32x8d_wsl
resnext101_32x16d_wsl
resnext101_32x32d_wsl
| classification | Build_In |
| [SENet](./cv/classification/senet/README.md) | [timm](https://github.com/rwightman/pytorch-image-models/blob/v0.6.5/timm/models/resnet.py) | model name
seresnet50
seresnet152d
seresnext26d_32x4d
seresnext26t_32x4d
seresnext50_32x4d
seresnext101_32x8d
seresnext101d_32x8d
legacy_seresnet18
legacy_seresnet34
legacy_seresnet50
legacy_senet154
legacy_seresnext26_32x4d
legacy_seresnext50_32x4d
legacy_seresnext101_32x4d
legacy_seresnet101
legacy_seresnet152
| classification | Build_In |
| [ShuffleNet_v1](./cv/classification/shufflenet_v1/README.md) | [mmcls](https://github.com/open-mmlab/mmclassification/tree/v0.23.1/configs/shufflenet_v1) | model name
shufflenet_v1
| classification | Build_In |
| [ShuffleNet_v1](./cv/classification/shufflenet_v1/README.md) | [megvii](https://github.com/megvii-model/ShuffleNet-Series/tree/master/ShuffleNetV1) | model name
Group3_0.5x
Group3_1.0x
Group3_1.5x
Group3_2.0x
Group8_0.5x
Group8_1.0x
Group8_1.5x
Group8_2.0x
| classification | Build_In |
| [ShuffleNet_v2](./cv/classification/shufflenet_v2/README.md) | [torchvision](https://github.com/pytorch/vision/blob/v0.9.0/torchvision/models/shufflenetv2.py) | model name
shufflenet_v2_x0_5
shufflenet_v2_x1_0
| classification | Build_In |
| [ShuffleNet_v2](./cv/classification/shufflenet_v2/README.md) | [mmcls](https://github.com/open-mmlab/mmclassification/blob/master/mmcls/models/backbones/shufflenet_v2.py) | model name
shufflenet_v2_x1_0
| classification | Build_In |
| [ShuffleNet_v2](./cv/classification/shufflenet_v2/README.md) | [ppcls](https://github.com/PaddlePaddle/PaddleClas/blob/v2.4.0/ppcls/arch/backbone/model_zoo/shufflenet_v2.py) | model name
shufflenet_v2_x0_25
shufflenet_v2_x0_33
shufflenet_v2_x0_5
shufflenet_v2_x1_0
shufflenet_v2_x1_5
shufflenet_v2_x2_0
shufflenet_v2_swish
| classification | Build_In |
| [ShuffleNet_v2](./cv/classification/shufflenet_v2/README.md) | [megvii](https://github.com/megvii-model/ShuffleNet-Series/blob/master/ShuffleNetV2/README.md) | model name
shufflenet_v2_x0.5
shufflenet_v2_x1.0
shufflenet_v2_x1.5
shufflenet_v2_x2.0
| classification | Build_In |
| [Swin](./cv/classification/swin_transformer/README.md) | [microsoft](https://github.com/microsoft/Swin-Transformer?tab=readme-ov-file) | model name
swin-b
| classification | Build_In |
| [VGG](./cv/classification/vgg/README.md) | [timm](https://github.com/rwightman/pytorch-image-models/blob/v0.6.5/timm/models/vgg.py) | model name
vgg11
vgg11_bn
vgg13
vgg13_bn
vgg16
vgg16_bn
vgg19
vgg19_bn
| classification | Build_In |
| [VGG](./cv/classification/vgg/README.md) | [torchvision](https://github.com/pytorch/vision/blob/v0.9.0/torchvision/models/vgg.py) | model name
vgg11
vgg11_bn
vgg13
vgg13_bn
vgg16
vgg16_bn
vgg19
vgg19_bn
| classification | Build_In |
| [VGG](./cv/classification/vgg/README.md) | [mmcls](https://github.com/open-mmlab/mmclassification/blob/v0.23.2/configs/vgg/README.md) | model name
vgg11
vgg11_bn
vgg13
vgg13_bn
vgg16
vgg16_bn
vgg19
vgg19_bn
| classification | Build_In |
| [VGG](./cv/classification/vgg/README.md) | [ppcls](https://github.com/PaddlePaddle/PaddleClas/blob/release/2.5/docs/zh_CN/models/ImageNet1k/VGG.md) | model name
vgg11
vgg13
vgg16
vgg19
| classification | Build_In |
| [ViT](./cv/classification/vision_transformer/README.md) | [huggingface](https://huggingface.co/google/vit-base-patch16-224) | model name
vit-base-patch16-224
| classification | Build_In |
| [VOVNet](./cv/classification/vovnet/README.md) | [timm](https://github.com/rwightman/pytorch-image-models/blob/v0.6.5/timm/models/vovnet.py) | model name
ese_vovnet19b_dw
ese_vovnet39b
| classification | Build_In |
| [Wide ResNet](./cv/classification/wide_resnet/README.md) | [timm](https://github.com/rwightman/pytorch-image-models/blob/v0.6.5/timm/models/resnet.py) | model name
wide_resnet50_2
wide_resnet101_2
| classification | Build_In |
| [Wide ResNet](./cv/classification/wide_resnet/README.md) | [torchvision](https://github.com/pytorch/vision/blob/v0.9.0/torchvision/models/resnet.py) | model name
wide_resnet50_2
wide_resnet101_2
| classification | Build_In |
| [Xception](./cv/classification/xception/README.md) | [ppcls](https://github.com/PaddlePaddle/PaddleClas/blob/release/2.3/docs/zh_CN/models/Inception.md) | model name
xception41
xception41_deeplab
xception65
xception65_deeplab
xception71
| classification | Build_In |
- object detection
| model | codebase | model list | model type | runtime |
| :------: | :------: | :------: | :------: | :-----: |
| [CenterNet](./cv/detection/centernet/README.md) | [official](https://github.com/xingyizhou/CenterNet) | model name
centernet_res18
| object detection | Build_In |
| [DETR](./cv/detection/detr/README.md) | [facebook](https://github.com/facebookresearch/detr?tab=readme-ov-file) | model name
detr_res50
| object detection | Build_In |
| [FastestDet](./cv/detection/fastestdet/README.md) | [official](https://github.com/dog-qiuqiu/FastestDet) | model name
fastestdet
| object detection | Build_In |
| [Grounding-DINO](./cv/detection/grounding_dino/README.md) | [official](https://github.com/IDEA-Research/GroundingDINO) | model name
groundingdino_swint_ogc
groundingdino_swinb_cogcoor
| object detection | Build_In |
| [NanoDet](./cv/detection/nanodet/README.md) | [official](https://github.com/RangiLyu/nanodet) | model name
nanodet_m
nanodet_plus_m
nanodet_plus_m_1.5x
| object detection | Build_In |
| [RetinaNet](./cv/detection/retinanet/README.md) | [pytorch](https://github.com/yhenon/pytorch-retinanet/tree/master) | model name
retinanet_resnet50
| object detection | Build_In |
| [RetinaNet](./cv/detection/retinanet/README.md) | [mlcommons](https://github.com/mlcommons/inference/tree/master/vision/classification_and_detection) | model name
retinanet_resnext50_32x4d_fpn
| object detection | Build_In |
| [RetinaNet](./cv/detection/retinanet/README.md) | [mmdet](https://github.com/open-mmlab/mmdetection/tree/v3.1.0) | model name
retinanet_r18_fpn_1x_coco
retinanet_r18_fpn_1x8_1x_coco
retinanet_r50_fpn_1x_coco
retinanet_r50_fpn_2x_coco
retinanet_r50_fpn_fp16_1x_coco
retinanet_r50_caffe_fpn_1x_coco
retinanet_r101_fpn_1x_coco
retinanet_r101_fpn_2x_coco
retinanet_r101_caffe_fpn_1x_coco
retinanet_x101_32x4d_fpn_1x_coco
retinanet_x101_32x4d_fpn_2x_coco
retinanet_x101_64x4d_fpn_1x_coco
retinanet_x101_64x4d_fpn_2x_coco
retinanet_r50_fpn_mstrain_3x_coco
retinanet_r101_caffe_fpn_mstrain_3x_coco
retinanet_r101_fpn_mstrain_3x_coco
retinanet_x101_64x4d_fpn_mstrain_3x_coco
| object detection | Build_In |
| [RT-DETR](./cv/detection/rtdetr/README.md) | [official](https://github.com/lyuwenyu/RT-DETR) | model name
rtdetr_r18vd
| object detection | Build_In |
| [YOLO-World](./cv/detection/yolo_world/README.md) | [official](https://github.com/AILab-CVC/YOLO-World) | model name
yolo_world_v2_l
| object detection | Build_In |
| [YOLOF](./cv/detection/yolof/README.md) | [mmdet](https://github.com/open-mmlab/mmdetection/tree/main/configs/yolof) | model name
yolof
| object detection | Build_In |
| [YoloFastV2](./cv/detection/yolofastv2/README.md) | [official](https://github.com/dog-qiuqiu/Yolo-FastestV2) | model name
yolofastv2
| object detection | Build_In |
| [YOLOR](./cv/detection/yolor/README.md) | [official](https://github.com/WongKinYiu/yolor/tree/paper) | model name
yolor_d6
yolor_e6
yolor_w6
yolor_p6
| object detection | Build_In |
| [Yolov3](./cv/detection/yolov3/README.md) | [pytorch(u)](https://github.com/ultralytics/yolov3/tree/v9.5.0) | model name
yolov3
yolov3-spp
yolov3-tiny
| object detection | Buid_In |
| [Yolov4](./cv/detection/yolov4/README.md) | [darknet](https://github.com/AlexeyAB/darknet) | model name
yolov4
yolov4_tiny
yolov4_csp
yolov4_csp_swish
yolov4_csp_x_swish
yolov4x_mish
| object detection | Buid_In |
| [Yolov4](./cv/detection/yolov4/README.md) | [bubbliiiing](https://github.com/bubbliiiing/yolov4-pytorch) | model name
yolov4
yolov4_tiny
| object detection | Buid_In |
| [Yolov4](./cv/detection/yolov4/README.md) | [tianxiaomo](https://github.com/Tianxiaomo/pytorch-YOLOv4) | model name
yolov4
| object detection | Buid_In |
| [Yolov5](./cv/detection/yolov5/README.md) | [pytorch(u)](https://github.com/ultralytics/yolov5/tree/v6.1) | model name
yolov5n
yolov5s
yolov5m
yolov5l
yolov5x
yolov5n6
yolov5s6
yolov5m6
yolov5l6
yolov5x6
| object detection | Build_In |
| [Yolov5](./cv/detection/yolov5/README.md) | [mmyolo](https://github.com/open-mmlab/mmyolo/tree/v0.1.3/configs/yolov5) | model name
yolov5n
yolov5s
yolov5m
yolov5l
yolov5n6
yolov5s6
yolov5m6
yolov5l6
| object detection | Build_In |
| [yolov6](./cv/detection/yolov6/README.md) | [yolov6](https://github.com/meituan/YOLOv6) | model name
YOLOv6-n
YOLOv6-tiny
YOLOv6-s
| object detection | Build_In |
| [yolov7](./cv/detection/yolov7/README.md) | [yolov7](https://github.com/WongKinYiu/yolov7) | model name
YOLOv7
YOLOv7x
YOLOv7-w6
YOLOv7-e6
YOLOv7-d6
YOLOv7-e6e
| object detection | Build_In |
| [yolov8](./cv/detection/yolov8/README.md) | [yolov8](https://github.com/ultralytics/ultralytics) | model name
YOLOv8n
YOLOv8s
YOLOv8m
YOLOv8b
YOLOv8l
YOLOv8x
| object detection | Build_In |
| [yolov10](./cv/detection/yolov10/README.md) | [yolov10](https://github.com/THU-MIG/yolov10.git) | model name
YOLOv10-N
YOLOv10-S
YOLOv10-M
YOLOv10-B
YOLOv10-L
YOLOv10-X
| object detection | Build_In |
| [Yolov11](./cv/detection/yolov11/README.md) | [official](https://github.com/ultralytics/ultralytics) | model name
yolo11n
yolo11s
yolo11m
yolo11l
yolo11x
| object detection | Build_In |
| [Yolov12](./cv/detection/yolov12/README.md) | [official](https://github.com/sunsmarterjie/yolov12.git) | model name
yolov12n
yolov12s
yolov12m
yolov12l
yolov12x
| object detection | Build_In |
| [Yolox](./cv/detection/yolox/README.md) | [official](https://github.com/Megvii-BaseDetection/YOLOX) | model name
yolox_s
yolox_m
yolox_l
yolox_x
yolox_darknet
yolox_tiny
yolox_nano
| object detection | Build_In |
| [Yolox](./cv/detection/yolox/README.md) | [mmyolo](https://github.com/open-mmlab/mmyolo/blob/main/configs/yolox/README.md) | model name
yolox_s
yolox_tiny
| object detection | Build_In |
- segmentation
| model | codebase | model list | model type | runtime |
| :------: | :------: | :------: | :------: | :-----: |
| [BiSeNet](./cv/segmentation/bisenet/README.md) | [pytorch](https://github.com/CoinCheung/BiSeNet/) | model name
bisenetv1
bisenetv2
| segmentation | Build_In |
| [BiSeNet](./cv/segmentation/bisenet/README.md) | [pytorch](https://github.com/zllrunning/face-parsing.PyTorch) | model name
bisenet
bisenet_2class
| face segmentation | Build_In |
| [Deeplab_v3](./cv/segmentation/deeplab_v3/README.md) | [pytorch](https://github.com/VainF/DeepLabV3Plus-Pytorch) | model name
deeplabv3_resnet50
deeplabv3_resnet101
| segmentation | Build_In |
| [Deeplab_v3_plus](./cv/segmentation/deeplab_v3/README.md) | [pytorch](https://github.com/VainF/DeepLabV3Plus-Pytorch) | model name
deeplabv3plus_resnet50
deeplabv3plus_resnet101
| segmentation | Build_In |
| [FCN](./cv/segmentation/fcn/README.md) | [pytorch](https://github.com/Tramac/awesome-semantic-segmentation-pytorch/blob/master/README.md) | model name
fcn8s
fcn16s
fcn32s
| segmentation | Build_In |
| [FCN](./cv/segmentation/fcn/README.md) | [mmseg](https://github.com/open-mmlab/mmsegmentation/tree/master/configs/fcn) | model name
fcn_r50_d8_20k
fcn_r50_d8_40k
fcn_r101_d8_20k
fcn_r101_d8_40k
| segmentation | Build_In |
| [HRNet_Seg](./cv/segmentation/hrnet/README.md) | [pytorch](https://github.com/HRNet/HRNet-Semantic-Segmentation/tree/pytorch-v1.1) | model name
HRNetV2-W48
HRNetV2-W18-Small-v1
HRNetV2-W18-Small-v2
| segmentation | Build_In |
| [Human_Seg](./cv/segmentation/human_seg/README.md) | [pytorch](https://github.com/thuyngch/Human-Segmentation-PyTorch) | model name
unet_resnet18
deeplabv3plus_resnet18
| human segmentation | Build_In |
| [Mask2Former](./cv/segmentation/mask2former/README.md) | [official](https://github.com/facebookresearch/Mask2Former) | model name
maskformer2_R50
| instance segmentation | Build_In |
| [MODNet](./cv/segmentation/modnet/README.md) | [official](https://github.com/ZHKKKe/MODNet) | model name
modnet
| matting | Build_In |
| [ParseNet](./cv/segmentation/parsenet/README.md) | [pytorch](https://github.com/yangxy/GPEN/blob/main/face_parse/parse_model.py) | model name
parsenet
| face segmentation | Build_In |
| [R2U_Net](./cv/segmentation/r2u_net/README.md) | [pytorch](https://github.com/Andy-zhujunwen/UNET-ZOO) | model name
r2u_net
| segmentation | Build_In |
| [RefineNet](./cv/segmentation/refinenet/README.md) | [pytorch](https://github.com/DrSleep/light-weight-refinenet) | model name
refinenet_resnet101
refinenet_lw_resnet50
refinenet_lw_resnet101
refinenet_lw_resnet152
refinenet_lw_mobilenetv2
| segmentation | Build_In |
| [STDC](./cv/segmentation/stdc/README.md) | [official](https://github.com/MichaelFan01/STDC-Seg) | model name
stdc1
| segmentation | Build_In |
| [Unet](./cv/segmentation/unet/README.md) | [bubbliiiing](https://github.com/bubbliiiing/unet-pytorch) | model name
unet_vgg16
unet_resnet50
| segmentation | Build_In |
| [Unet](./cv/segmentation/unet/README.md) | [milesial](https://github.com/milesial/Pytorch-UNet) | model name
unet_scale0.5
unet_scale1.0
| segmentation | Build_In |
| [Unet](./cv/segmentation/unet/README.md) | [keras](https://github.com/zhixuhao/unet) | model name
unet
| segmentation | Build_In |
| [Unet3P](./cv/segmentation/unet3p/README.md) | [pytorch](https://github.com/avBuffer/UNet3plus_pth) | model name
unet3p
unet3p_deepsupervision
| segmentation | Build_In |
| [UnetPP](./cv/segmentation/unetpp/README.md) | [pytorch](https://github.com/Andy-zhujunwen/UNET-ZOO) | model name
unetpp
| segmentation | Build_In |
| [Yolov8-seg](./cv/segmentation/yolov8_seg/README.md) | [ultralytics](https://github.com/ultralytics/ultralytics/tree/main) | model name
yolov8n-seg
yolov8s-seg
yolov8m-seg
yolov8l-seg
yolov8x-seg
| instance segmentation | Build_In |
- face alignment
| model | codebase | model list | model type | runtime |
| :------: | :------: | :------: | :------: | :-----: |
| [HIH](./cv/face_alignment/hih/README.md) | [pytorch](https://github.com/starhiking/HeatmapInHeatmap) | model name
hih_wflw_s
hih_wflw_b
| face alignment | Build_In |
| [HRNet_Face_Alignment](./cv/face_alignment/hrnet_face_alignment/README.md) | [pytorch](https://github.com/HRNet/HRNet-Facial-Landmark-Detection) | model name
HR18_300W
HR18_AFLW
HR18_COFW
HR18_WFLW
| face alignment | Build_In |
| [PFLD](./cv/face_alignment/pfld/README.md) | [pytorch](https://github.com/polarisZhao/PFLD-pytorch) | model name
pfld
| face alignment | Build_In |
| [PIPNet](./cv/face_alignment/pipnet/README.md) | [official](https://github.com/jhb86253817/PIPNet/tree/master) | model name
pip_resnet18
pip_resnet101
pipnet_mobilenet_v2
pipnet_mobilenet_v3
| face alignment | Build_In |
- face detection
| model | codebase | model list | model type | runtime |
| :------: | :------: | :------: | :------: | :-----: |
| [CenterFace](./cv/face_detection/centerface/README.md) | [onnx](https://github.com/Star-Clouds/CenterFace) | model name
centerface
centerface_bnmerged
| face detection | Build_In |
| [RetinaFace](./cv/face_detection/retinaface/README.md) | [pytorch](https://github.com/biubug6/Pytorch_Retinaface) | model name
retinaface-resnet50
retinaface-mobilenet0.25
| face detection | Build_In |
| [SCRFD](./cv/face_detection/scrfd/README.md) | [insightface](https://github.com/deepinsight/insightface/tree/master/detection/scrfd) | model name
scrfd_500m
scrfd_500m_bnkps
scrfd_1g
scrfd_2.5g
scrfd_2.5g_bnkps
scrfd_10g
scrfd_10g_bnkps
scrfd_34g
| face detection | Build_In |
| [YOLO5Face](./cv/face_detection/yolov5_face/README.md) | [pytorch](https://github.com/deepcam-cn/yolov5-face) | model name
yolov5n0.5_face
yolov5n_face
yolov5s_face
yolov5m_face
yolov5l_face
| face detection | Build_In |
- facial quality
| model | codebase | model list | model type | runtime |
| :------: | :------: | :------: | :------: | :-----: |
| [SDD-FIQA](./cv/face_quality/sdd_fiqa/README.md) | [sdd_fiqa](https://github.com/Tencent/TFace/tree/quality) | model name
sdd_fiqa
| face quality | Build_In |
- face recognize
| model | codebase | model list | model type | runtime |
| :------: | :------: | :------: | :------: | :-----: |
| [FaceNet](./cv/face_recognize/facenet/README.md) | [tensorflow](https://github.com/davidsandberg/facenet) | model name
facenet_vggface2
facenet_casia_webface
| face recognize | Build_In |
| [FaceNet](./cv/face_recognize/facenet/README.md) | [pytorch](https://github.com/timesler/facenet-pytorch) | model name
facenet_vggface2
facenet_casia_webface
| face recognize | Build_In |
- facial attribute
| model | codebase | model list | model type | runtime |
| :------: | :------: | :------: | :------: | :-----: |
| [FairFace](./cv/facial_attribute/fairface/README.md) | [official](https://github.com/dchen236/FairFace) | model name
fairface_res34
| face attribute | Build_In |
- image colorization
| model | codebase | model list | model type | runtime |
| :------: | :------: | :------: | :------: | :-----: |
| [GPEN](./cv/image_colorization/gpen/README.md) | [official](https://github.com/yangxy/GPEN) | model name
gpen
| image colorization | Build_In |
- image compress
| model | codebase | model list | model type | runtime |
| :------: | :------: | :------: | :------: | :-----: |
| [Elic](./cv/image_compress/elic/README.md) | [official](https://github.com/JiangWeibeta/ELIC) | model name
elic
| image compress | Build_In |
| [Mlicpp](./cv/image_compress/mlic_pp/README.md) | [official](https://github.com/JiangWeibeta/MLIC) | model name
mlicpp
| image compress | Build_In |
- image retrieval
| model | codebase | model list | model type | runtime |
| :------: | :------: | :------: | :------: | :-----: |
| [DINOv2](./cv/image_retrieval/dinov2/README.md) | [official](https://github.com/facebookresearch/dinov2) | model name
dinov2_vitl14_reg4
| image_retrieval | Build_In |
- low light image enhancement
| model | codebase | model list | model type | runtime |
| :------: | :------: | :------: | :------: | :-----: |
| [PairLIE](./cv/low_light_image_enhancement/pairlie/README.md) | [official](https://github.com/zhenqifu/PairLIE) | model name
pairlie
| low light image enhancement | Build_In |
| [USUIR](./cv/low_light_image_enhancement/usuir/README.md) | [official](https://github.com/zhenqifu/USUIR) | model name
uieb
ruie
| low light image enhancement | Build_In |
- mot
| model | codebase | model list | model type | runtime |
| :------: | :------: | :------: | :------: | :-----: |
| [ByteTrack](./cv/mot/bytetrack/README.md) | [official](https://github.com/ifzhang/ByteTrack) | model name
ByteTrack_ablation
bytetrack_x_mot17
bytetrack_l_mot17
bytetrack_m_mot17
bytetrack_s_mot17
bytetrack_nano_mot17
bytetrack_tiny_mot17
bytetrack_x_mot20
| mot | Build_In |
| [DeepSort](./cv/mot/deep_sort/README.md) | [pytorch](https://github.com/ZQPei/deep_sort_pytorch) | model name
fast reid
| mot | Build_In |
| [FairMOT](./cv/mot/fairmot/README.md) | [official](https://github.com/ifzhang/FairMOT) | model name
fairmot_yolov5s
| mot | Build_In |
| [JDE](./cv/mot/jde/README.md) | [pytorch](https://github.com/Zhongdao/Towards-Realtime-MOT/tree/master) | model name
jde_1088x608_uncertainty
jde_864x480_uncertainty
jde_576x320_uncertainty
| mot | Build_In |
| [OCSORT](./cv/mot/ocsort/README.md) | [pytorch](https://github.com/noahcao/OC_SORT/tree/master) | model name
ocsort_mot17_ablation
ocsort_x_mot17
ocsort_x_mot20
ocsort_dance_model
| mot | Build_In |
- pose
| model | codebase | model list | model type | runtime |
| :------: | :------: | :------: | :------: | :-----: |
| [OpenPose](./cv/pose/openpose/README.md) | [pytorch](https://github.com/Hzzone/pytorch-openpose) | model name
body model
hand model
| pose | Build_In |
| [HRNet_Pose](./cv/pose/hrnet_pose/README.md) | [mmpose](https://github.com/open-mmlab/mmpose/blob/master/configs/body/2d_kpt_sview_rgb_img/associative_embedding/coco/higherhrnet_w32_coco_512x512.py) | model name
hrnet_pose
| pose | Build_In |
| [Yolov8_Pose](./cv/pose/yolov8_pose/README.md) | [ultralytics](https://docs.ultralytics.com/tasks/pose/) | model name
yolov8n_pose
yolov8s_pose
yolov8m_pose
yolov8l_pose
yolov8x_pose
yolov8x_pose_p6
| pose | Build_In |
- reid
| model | codebase | model list | model type | runtime |
| :------: | :------: | :------: | :------: | :-----: |
| [Fast_Reid](./cv/reid/fast_reid/README.md) | [official](https://github.com/JDAI-CV/fast-reid) | model name
market_bot_R50
market_bot_S50
market_bot_R50_ibn
market_bot_R101_ibn
| reid | Build_In |
- salient object detection
| model | codebase | model list | model type | runtime |
| :------: | :------: | :------: | :------: | :-----: |
| [BSANet](./cv/salient_object_detection/bsanet/README.md) | [official](https://github.com/xuebinqin/BASNet) | model name
bsanet
| salient object detection | Build_In |
| [BSANet](./cv/salient_object_detection/bsanet/README.md) | [salod](https://github.com/moothes/SALOD/tree/master) | model name
bsanet
| salient object detection | Build_In |
| [DHSNet](./cv/salient_object_detection/dhsnet/README.md) | [salod](https://github.com/moothes/SALOD/tree/master) | model name
dhsnet
| salient object detection | Build_In |
| [EGNet](./cv/salient_object_detection/egnet/README.md) | [salod](https://github.com/moothes/SALOD) | model name
egnet
| salient object detection | Build_In |
| [F3Net](./cv/salient_object_detection/f3net/README.md) | [official](https://github.com/weijun88/F3Net) | model name
f3net
| salient object detection | Build_In |
| [GCPANet](./cv/salient_object_detection/gcpanet/README.md) | [salod](https://github.com/moothes/SALOD/tree/master) | model name
gcpanet
| salient object detection | Build_In |
| [ISNet](./cv/salient_object_detection/isnet/README.md) | [official](https://github.com/xuebinqin/DIS) | model name
isnet
| salient object detection | Build_In |
| [SCRN](./cv/salient_object_detection/scrn/README.md) | [salod](https://github.com/moothes/SALOD/tree/master) | model name
scrn
| salient object detection | Build_In |
| [U2Net](./cv/salient_object_detection/u2net/README.md) | [official](https://github.com/xuebinqin/U-2-Net/tree/master) | model name
u2net
u2net_human_seg
u2netp
| salient object detection | Build_In |
- super_resolution
| model | codebase | model list | model type | runtime |
| :------: | :------: | :------: | :------: | :-----: |
| [Bicubic_PlusPlus](./cv/super_resolution/bicubic_plusplus/README.md) | [official](https://github.com/aselsan-research-imaging-team/bicubic-plusplus) | model name
bicubic_plusplus_2x
bicubic_plusplus_3x
| super resolution | Build_In |
| [BSRGAN](./cv/super_resolution/bsrgan/README.md) | [official](https://github.com/cszn/BSRGAN) | model name
bsrnet_x4
bsrgan_x4
bsrgan_x2
| super resolution | Build_In |
| [ECBSR](./cv/super_resolution/ecbsr/README.md) | [official](https://github.com/xindongzhang/ECBSR) | model name
ecbsr_plain_2x
| super resolution | Build_In |
| [ECBSR](./cv/super_resolution/ecbsr/README.md) | [basicsr](https://github.com/XPixelGroup/BasicSR) | model name
ecbsr_rgb_2x
| super resolution | Build_In |
| [EDSR](./cv/super_resolution/edsr/README.md) | [basicsr](https://github.com/XPixelGroup/BasicSR/blob/v1.4.2/docs/ModelZoo_CN.md#图像超分官方模型) | model name
edsr_1x
edsr_m2x
| super resolution | Build_In |
| [EDSR](./cv/super_resolution/edsr/README.md) | [official](https://github.com/sanghyun-son/EDSR-PyTorch) | model name
edsr_x2
edsr_baseline_x2
edsr_baseline_x4
| super resolution | Build_In |
| [ESRGAN](./cv/super_resolution/esrgan/README.md) | [official](https://github.com/xinntao/ESRGAN) | model name
esrgan_x4
| super resolution | Build_In |
| [FSRNet*](./cv/super_resolution/fsrnet/README.md) | [pytorch](https://github.com/cs-giung/FSRNet-pytorch) | model name
fsrnet
| super resolution | Build_In |
| [GPEN](./cv/super_resolution/gpen/README.md) | [official](https://github.com/yangxy/GPEN) | model name
gpen
| super resolution | Build_In |
| [LESRCNN](./cv/super_resolution/lesrcnn/README.md) | [official](https://github.com/hellloxiaotian/LESRCNN) | model name
lesrcnn_x2
lesrcnn_x4
| super resolution | Build_In |
| [MSRN](./cv/super_resolution/msrn/README.md) | [official](https://github.com/MIVRC/MSRN-PyTorch) | model name
msrn
| super resolution | Build_In |
| [NCNet](./cv/super_resolution/ncnet/README.md) | [official](https://github.com/Algolzw/NCNet) | model name
ncnet
| super resolution | Build_In |
| [PFSRNet](./cv/super_resolution/pfsrnet/README.md) | [official](https://github.com/DeokyunKim/Progressive-Face-Super-Resolution) | model name
pfsrnet
| face super resolution | Build_In |
| [RCAN](./cv/super_resolution/rcan/README.md) | [official](https://github.com/yulunzhang/RCAN) | model name
rcan
rcan2
| super resolution | Build_In |
| [RCAN](./cv/super_resolution/rcan/README.md) | [basicsr](https://github.com/XPixelGroup/BasicSR) | model name
rcan
| super resolution | Build_In |
| [Real_ESRGAN](./cv/super_resolution/real_esrgan/README.md) | [official](https://github.com/xinntao/Real-ESRGAN) | model name
real_esrgan_x4plus
real_esrnet_x4plus
real_esrgan_x4plus_anime_6b
| super resolution | Build_In |
| [RealSR](./cv/super_resolution/realsr/README.md) | [official](https://github.com/Tencent/Real-SR) | model name
DF2K
DF2K-JPEG
DPED
| super resolution | Build_In |
| [SPARNet](./cv/super_resolution/sparnet/README.md) | [official](https://github.com/chaofengc/Face-SPARNet) | model name
sparnet_light_attn3d
| super resolution | Build_In |
| [VDSR](./cv/super_resolution/vdsr/README.md) | [pytorch](https://github.com/twtygqyy/pytorch-vdsr) | model name
vdsr
| super resolution | Build_In |
- text detection
| model | codebase | model list | model type | runtime |
| :------: | :------: | :------: | :------: | :-----: |
| [CT](./cv/text_detection/ct/README.md) | [ppocr](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.7/doc/doc_ch/algorithm_det_ct.md) | model name
det_r18_vd_ct
| text detection | Build_In |
| [DBNet](./cv/text_detection/dbnet/README.md) | [ppocr](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.6/doc/doc_ch/algorithm_det_db.md) | model name
dbnet_mobilenet_v3
dbnet_resnet50_vd
ch_PP_OCRv3_det
ch_PP_OCRv4_det
en_PP_OCRv3_det
| text detection | Build_In |
| [DBNet](./cv/text_detection/dbnet/README.md) | [official](https://github.com/MhLiao/DB) | model name
dbnet_resnet18
dbnet_resnet50
| text detection | Build_In |
| [DBNet](./cv/text_detection/dbnet/README.md) | [mmocr](https://github.com/open-mmlab/mmocr/tree/main/configs/textdet/dbnet) | model name
dbnet_resnet18_fpnc_1200e_icdar2015
dbnet_resnet18_fpnc_1200e_totaltext
dbnet_resnet18_fpnc_100k_synthtext
dbnet_resnet50_1200e_icdar2015
dbnet_resnet50_oclip_1200e_icdar2015
| text detection | Build_In |
| [EAST](./cv/text_detection/east/README.md) | [ppocr](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.7/doc/doc_ch/algorithm_det_east.md) | model name
det_r50_vd_east
det_mv3_east
| text detection | Build_In |
| [FAST](./cv/text_detection/fast/README.md) | [pytorch](https://github.com/czczup/FAST/tree/main) | model name
fast_base_ic17mlt_640
fast_small_ic17mlt_640
fast_tiny_ic17mlt_640
fast_tiny_tt_448_finetune_ic17mlt
fast_tiny_tt_512_finetune_ic17mlt
fast_tiny_tt_640_finetune_ic17mlt
fast_small_tt_512_finetune_ic17mlt
fast_small_tt_640_finetune_ic17mlt
fast_base_tt_512_finetune_ic17mlt
fast_base_tt_640_finetune_ic17mlt
fast_base_tt_800_finetune_ic17mlt
fast_tiny_ctw_512_finetune_ic17mlt
fast_small_ctw_512_finetune_ic17mlt
fast_base_ctw_512_finetune_ic17mlt
fast_base_ctw_640_finetune_ic17mlt
fast_tiny_ic15_736_finetune_ic17mlt
fast_small_ic15_736_finetune_ic17mlt
fast_base_ic15_736_finetune_ic17mlt
fast_base_ic15_896_finetune_ic17mlt
fast_base_ic15_1280_finetune_ic17mlt
fast_tiny_msra_512_finetune_ic17mlt
fast_tiny_msra_736_finetune_ic17mlt
fast_small_msra_736_finetune_ic17mlt
fast_base_msra_736_finetune_ic17mlt
| text detection | Build_In |
| [FCENet](./cv/text_detection/fcenet/README.md) | [mmocr](https://github.com/open-mmlab/mmocr/tree/main/configs/textdet/fcenet) | model name
fcenet_resnet50_fpn_1500e_icdar2015
fcenet_resnet50_oclip_fpn_1500e_icdar2015
fcenet_resnet50_fpn_1500e_totaltext
fcenet_resnet50_oclip_fpn_1500e_ctw1500
| text detection | Build_In |
| [PAN](./cv/text_detection/pan/README.md) | [pan_pp.pytorch](https://github.com/whai362/pan_pp.pytorch/blob/master/config/pan/README.md) | model name
pan_r18_ctw
pan_r18_ctw_finetune
pan_r18_ic15
pan_r18_ic15_finetune
pan_r18_tt
pan_r18_tt_finetune
pan_r18_msra
pan_r18_msra_finetune
| text detection | Build_In |
| [PAN++ detection only](./cv/text_detection/pan++/README.md) | [pan_pp.pytorch](https://github.com/whai362/pan_pp.pytorch/blob/master/config/pan_pp/pan_pp_r18_ic15_736_det_only.py) | model name
panpp_r18_ic15_det
| text detection | Build_In |
| [PSENet](./cv/text_detection/psenet/README.md) | [pytorch](https://github.com/whai362/pan_pp.pytorch/blob/master/config/psenet/README.md) | model name
psenet_r50_ic15_736
psenet_r50_ic15_1024
psenet_r50_ic15_736_finetune
psenet_r50_ic15_1024_finetune
psenet_r50_ctw
psenet_r50_ctw_finetune
psenet_r50_tt
psenet_r50_tt_finetune
| text detection | Build_In |
| [Text Snake](./cv/text_detection/text_snake/README.md) | [mmocr](https://github.com/open-mmlab/mmocr/tree/main/configs/textdet/textsnake) | model name
textsnake_resnet50_fpn
textsnake_resnet50_oclip_fpn
| text detection | Build_In |
- text recognition
| model | codebase | model list | model type | runtime |
| :------: | :------: | :------: | :------: | :-----: |
| [CNN_CTC](./cv/text_recognition/cnn_ctc/README.md) | [pytorch](https://github.com/Media-Smart/vedastr) | model name
resnet_fc
| ocr recognize | Build_In |
| [CRNN](./cv/text_recognition/crnn/README.md) | [ppocr](https://github.com/PaddlePaddle/PaddleOCR/blob/v2.6.0/doc/doc_ch/algorithm_rec_crnn.md) | model name
resnet34_vd
| text recognition | Build_In |
| [PPOCR_V4_REC](./cv/text_recognition/ppocr_v4_rec/README.md) | [ppocr](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.7/doc/doc_ch/PP-OCRv4_introduction.md) | model name
ppocr_v4_rec
| ocr recognize | Build_In |
NLP Models
- information extraction
| model | codebase | model list | model type | runtime |
| :------: | :------: | :------: | :------: | :-----: |
| [uie](./nlp/information_extraction/uie/README.md) | [uie_pytorch](https://github.com/HUSTAI/uie_pytorch) | model name
uie-base
| Information extraction | Build_In |
- named entity recognition
| model | codebase | model list | model type | runtime |
| :------: | :------: | :------: | :------: | :-----: |
| [BERT](./nlp/named_entity_recognition/bert/README.md) | [huggingface](https://github.com/huggingface/transformers/blob/main/src/transformers/models/bert/modeling_bert.py) | model name
bert_base_zh_ner-256
| named entity recognition | Build_In |
| [RoBERTa](./nlp/named_entity_recognition/roberta/README.md) | [huggingface](https://github.com/huggingface/transformers/blob/main/src/transformers/models/roberta/modeling_roberta.py) | model name
roberta_wwm_ext_base_zh-256
| named entity recognition | Build_In |
| [ERNIE](./nlp/named_entity_recognition/ernie/README.md) | [huggingface](https://github.com/huggingface/transformers/blob/main/src/transformers/models/ernie/modeling_ernie.py) | model name
ernie1.0_base_zh
ernie2.0_base_en
ernie2.0_large_en
ernie3.0_base_zh
ernie3.0_medium_zh
ernie3.0_xbase_zh
| named entity recognition | Build_In |
| [RoBERTa](./nlp/named_entity_recognition/roberta/README.md) | [huggingface](https://github.com/huggingface/transformers/blob/main/src/transformers/models/roberta/modeling_roberta.py) | model name
roberta_wwm_ext_base_zh
| named entity recognition | Build_In |
| [XLMRoBERTa](./nlp/named_entity_recognition/xlmroberta/README.md) | [huggingface](https://github.com/huggingface/transformers/blob/main/src/transformers/models/xlm_roberta/modeling_xlm_roberta.py) | model name
xlmroberta_base_zh_ner
| named entity recognition | Build_In |
- question answering
| model | codebase | model list | model type | runtime |
| :------: | :------: | :------: | :------: | :-----: |
| [BERT](./nlp/question_answering/bert/README.md) | [tensorflow](https://github.com/google-research/bert) | model name
bert_base_en_qa-384
bert_large_en_qa-384
| question answering | Build_In |
| [BERT](./nlp/question_answering/bert/README.md) | [huggingface](https://github.com/huggingface/transformers/blob/main/src/transformers/models/bert/modeling_bert.py) | model name
bert_base_en_qa-384
bert_large_en_qa-384
| question answering | Build_In |
| [ERNIE](./nlp/question_answering/ernie/README.md) | [huggingface](https://github.com/huggingface/transformers/blob/main/src/transformers/models/ernie/modeling_ernie.py) | model name
ernie1.0_base_zh
ernie2.0_base_en
ernie2.0_large_en
ernie3.0_base_zh
ernie3.0_medium_zh
ernie3.0_xbase_zh
| question answering | Build_In |
- sentence classification
| model | codebase | model list | model type | runtime |
| :------: | :------: | :------: | :------: | :-----: |
| [BERT](./nlp/sentence_classification/bert/README.md) | [tensorflow](https://github.com/google-research/bert) | model name
bert_base_mrpc_cls-128
bert_large_mrpc_cls-128
| sentence classification | Build_In |
| [BERT](./nlp/sentence_classification/bert/README.md) | [huggingface](https://github.com/huggingface/transformers/blob/main/src/transformers/models/bert/modeling_bert.py) | model name
bert_base_mrpc_cls-128
bert_base_mrpc_cls-512
bert_large_mrpc_cls-128
bert_large_mrpc_cls-512
bert_base_imdb_cls-128
bert_base_sst2_cls-128
| sentence classification | Build_In |
| [BERT](./nlp/sentence_classification/bert/README.md) | [modelscope](https://www.modelscope.cn/models/iic/nlp_structbert_sentiment-classification_chinese-base/summary) | model name
| sentence classification | Build_In |
| [Electra](./nlp/sentence_classification/electra/README.md) | [CIB](https://drive.google.com/drive/folders/1ii0Kz6nxZujiMkoMozrWLbBCGpjmWqh2?usp=sharing) | model name
electra_small-512
| sentence classification | Build_In |
| [Electra](./nlp/sentence_classification/electra/README.md) | [huggingface](https://github.com/huggingface/transformers/blob/main/src/transformers/models/electra/modeling_electra.py) | model name
electra_small_dc_mrpc-128
electra_small_gen_mrpc-128
electra_base_dc_mrpc-128
electra_base_gen_mrpc-128
electra_large_dc_mrpc-128
| sentence classification | Build_In |
| [ERNIE](./nlp/sentence_classification/ernie/README.md) | [huggingface](https://github.com/huggingface/transformers/blob/main/src/transformers/models/ernie/modeling_ernie.py) | model name
ernie1.0_base_zh
ernie2.0_base_en
ernie2.0_large_en
ernie3.0_base_zh
ernie3.0_medium_zh
ernie3.0_xbase_zh
| sentence classification | Build_In |
| [RoBERTa](./nlp/sentence_classification/roberta/README.md) | [huggingface](https://github.com/huggingface/transformers/blob/main/src/transformers/models/roberta/modeling_roberta.py) | model name
roberta_base_en_cls-128
| sentence classification | Build_In |
| [XLMRoBERTa](./nlp/sentence_classification/xlmroberta/README.md) | [huggingface](https://github.com/huggingface/transformers/blob/main/src/transformers/models/xlm_roberta/modeling_xlm_roberta.py) | model name
xlmroberta_base_en_cls
| sentence classification | Build_In |
- Text2Vec
- 以下是Embedding模型
| model | codebase | model list | model type | runtime |
| :------: | :------: | :------: | :------: | :-----: |
| [acge](./nlp/text2vec/acge/README.md) | [huggingface](https://huggingface.co/aspire/acge_text_embedding) | model name
acge_text_embedding
| Embedding model | Build_In |
| [bge](./nlp/text2vec/bge/README.md) | [huggingface](https://huggingface.co/collections/BAAI/bge-66797a74476eb1f085c7446d) | model name
bge-m3
bge-small-en-v1.5
bge-base-en-v1.5
bge-large-en-v1.5
| Embedding model | Build_In |
| [bce](./nlp/text2vec/bce/README.md) | [huggingface](https://huggingface.co/maidalun1020/bce-embedding-base_v1) | model name
bce-embedding-base_v1
| Embedding model | Build_In |
| [e5](./nlp/text2vec/e5/README.md)| [huggingface](https://huggingface.co/collections/intfloat/multilingual-e5-text-embeddings-67b2b8bb9bff40dec9fb3534) | model name
multilingual-e5-small
multilingual-e5-base
multilingual-e5-large
multilingual-e5-large-instruct
| Embedding model | Build_In |
| [gte](./nlp/text2vec/gte/README.md) | [huggingface](https://huggingface.co/thenlper) | model name
gte-small
gte-base
gte-large
| Embedding model | Build_In |
| [m3e](./nlp/text2vec/m3e/README.md)| [huggingface](https://huggingface.co/moka-ai) | model name
m3e-small
m3e-base
m3e-large
| Embedding model | Build_In |
| [text2vec](./nlp/text2vec/text2vec/README.md) | [huggingface](https://huggingface.co/GanymedeNil/text2vec-large-chinese) | model name
text2vec-base-chinese
text2vec-base-multilingual
text2vec-large-chinese
| Embedding model | Build_In |
- 以下是Reranker模型
| model | codebase | model list | model type | runtime |
| :------: | :------: | :------: | :------: | :-----: |
| [bge]((./nlp/text2vec/bge/README.md)) | [huggingface](https://huggingface.co/BAAI/) | model name
bge-reranker-base
bge-reranker-large
bge-reranker-v2-m3
| Reranker model | Build_In |
| [bce](./nlp/text2vec/bce/README.md) | [huggingface](https://huggingface.co/maidalun1020/bce-reranker-base_v1) | model name
bce-reranker-base_v1
| Reranker model | Build_In |
LLM Models
| model | codebase | model list | model type | runtime |
| :------: | :------: | :------: | :------: | :-----: |
| [Aquila2](./llm/aquila/README.md) | [huggingface](https://huggingface.co/collections/BAAI/aquila-6698657124de09d10cd7a83f/) | model name
Aquila2-7B
Aquila2-34B
| large language model | Build_In |
| [BaiChuan2](./llm/baichuan2/README.md) | [huggingface](https://huggingface.co/baichuan-inc) | model name
Baichuan2-7B-Base
Baichuan2-7B-Chat
Baichuan2-13B-Base
Baichuan2-13B-Chat
| large language model | Build_In |
| [ChatGLM2](./llm/chatglm2/README.md) | [huggingface](https://huggingface.co/THUDM/chatglm2-6b) | model name
chatglm2-6b
| large language model | Build_In |
| [ChatGLM3](./llm/chatglm3/README.md) | [huggingface](https://huggingface.co/THUDM/chatglm2-6b) | model name
chatglm3-6b-base
chatglm3-6b
| large language model | Build_In |
| [ChatGLM4](./llm/chatglm4/README.md) | [huggingface](https://huggingface.co/THUDM/chatglm2-6b) | model name
glm-4-9b-hf
glm-4-9b-chat-hf
| large language model | Build_In |
| [DeepSeek-R1-Distill](./llm/deepseek_r1/README.md) | [huggingface](https://huggingface.co/deepseek-ai) | model name
DeepSeek-R1-Distill-Qwen-1.5B
DeepSeek-R1-Distill-Qwen-7B
DeepSeek-R1-Distill-Qwen-14B
DeepSeek-R1-Distill-Qwen-32B
DeepSeek-R1-Distill-Llama-8B
DeepSeek-R1-Distill-Llama-70B
| large language model | Build_In |
| [Falcon](./lllm/falcon/README.md) | [huggingface](https://huggingface.co/tiiuae/) | model name
falcon-7b
| large language model | Build_In |
| [Gemma](./llm/gemma/README.md) | [huggingface](https://huggingface.co/collections/google/gemma-release-65d5efbccdbb8c4202ec078b) | model name
gemma-2b
gemma-2b-it
gemma-7b
gemma-7b-it
| large language model | Build_In |
| [Gemma-1.1](./llm/gemma/README.md) | [huggingface](https://huggingface.co/collections/google/gemma-release-65d5efbccdbb8c4202ec078b) | model name
gemma-1.1-2b-it
gemma-1.1-7b-it
| large language model | Build_In |
| [Internlm2](./llm/internlm2/README.md) | [huggingface](https://huggingface.co/internlm) | model name
internlm2-1_8b
internlm2-chat-1_8b
internlm2-7b
internlm2-chat-7b
internlm2-20b
internlm2-chat-20b
| large language model | Build_In |
| [Internlm2_5](./llm/internlm2_5/README.md) | [huggingface](https://huggingface.co/internlm) | model name
internlm2_5-1_8b
internlm2_5-1_8b-chat
internlm2_5-7b
internlm2_5-7b-chat
internlm2_5-20b
internlm2_5-20b-chat
| large language model | Build_In |
| [Internlm3](./llm/internlm3/README.md) | [huggingface](https://huggingface.co/internlm) | model name
internlm3-8b-instruct
| large language model | Build_In |
| [LLaMA](./llm/llama/README.md) | [huggingface](https://huggingface.co/meta-llama) | model name
meta-llama-33b
| large language model | Build_In |
| [LLaMA-2](./llm/llama2/README.md) | [huggingface](https://huggingface.co/meta-llama) | model name
Llama-2-7b-hf
Llama-2-7b-chat-hf
Llama-2-13b-hf
Llama-2-13b-chat-hf
Llama-2-70b-hf
Llama-2-70b-chat-hf
| large language model | Build_In |
| [LLaMA-3](./llm/llama3/README.md) | [huggingface](https://huggingface.co/meta-llama) | model name
Meta-Llama-3-8B
Meta-Llama-3-8B-Instruct
Meta-Llama-3-70B
Meta-Llama-3-70B-Instruct
| large language model | Build_In |
| [LLaMA-3.1](./llm/llama3/README.md) | [huggingface](https://huggingface.co/meta-llama) | model name
Meta-Llama-3.1-8B
Meta-Llama-3.1-8B-Instruct
Meta-Llama-3.1-70B
Meta-Llama-3.1-70B-Instruct
| large language model | Build_In |
| [LLaMA-3.2](./llm/llama3/README.md) | [huggingface](https://huggingface.co/meta-llama) | model name
Llama-3.2-1B
Llama-3.2-1B-Instruct
Llama-3.2-3B
Llama-3.2-3B-Instruct
| large language model | Build_In |
| [LLaMA-3.3](./llm/llama3/README.md) | [huggingface](https://huggingface.co/meta-llama) | model name
Llama-3.3-70B-Instruct
| large language model | Build_In |
| [Mistral](./llm/mistral/README.md) | [huggingface](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) | model name
Mistral-7B-Instruct-v0.2
Ministral-8B-Instruct-2410-HF
| large language model | Build_In |
| [Mobillama](./llm/mobillama/README.md) | [huggingface](https://huggingface.co/collections/MBZUAI/mobillama-65dd4182d588c91e8230332e) | model name
MobiLlama-05B
MobiLlama-05B-Chat
MobiLlama-1B
MobiLlama-1B-Chat
| large language model | Build_In |
| [OpenBuddy](./llm/openbuddy/README.md) | [huggingface](https://huggingface.co/collections/OpenBuddy/our-selected-models-65369270912eef259074d3dc) | model name
openbuddy-mistral2-7b-v20.3-32k
openbuddy-qwen1.5-14b-v21.1-32k
openbuddy-deepseek-67b-v18.1-4k
| large language model | Build_In |
| [Phi-3](./lllm/phi/README.md) | [huggingface](https://hf-mirror.com/microsoft/Phi-3-mini-4k-instruct) | model name
Phi-3-mini-4k-instruct
| large language model | Build_In |
| [Qwen1.5](./llm/qwen1.5/README.md) | [huggingface](https://huggingface.co/Qwen) | model name
Qwen1.5-0.5B
Qwen1.5-0.5B-Chat
Qwen1.5-1.8B
Qwen1.5-1.8B-Chat
Qwen1.5-4B
Qwen1.5-4B-Chat
Qwen1.5-7B
Qwen1.5-7B-Chat
Qwen1.5-14B
Qwen1.5-14B-Chat
Qwen1.5-32B
Qwen1.5-32B-Chat
Qwen1.5-72B
Qwen1.5-72B-Chat
Qwen1.5-110B-Chat
| large language model | Build_In |
| [Qwen2](./llm/qwen2/README.md) | [huggingface](https://huggingface.co/Qwen) | model name
Qwen2-0.5B
Qwen2-0.5B-Instruct
Qwen2-1.5B
Qwen2-1.5B-Instruct
Qwen2-7B
Qwen2-7B-Instruct
Qwen2-72B
Qwen2-72B-Instruct
| large language model | Build_In |
| [Qwen2.5](./llm/qwen2/README.md) | [huggingface](https://huggingface.co/Qwen) | model name
Qwen2.5-0.5B
Qwen2.5-0.5B-Instruct
Qwen2.5-1.5B
Qwen2.5-1.5B-Instruct
Qwen2.5-3B
Qwen2.5-3B-Instruct
Qwen2.5-7B
Qwen2.5-7B-Instruct
Qwen2.5-14B
Qwen2.5-14B-Instruct
Qwen2.5-32B
Qwen2.5-32B-Instruct
Qwen2.5-72B
Qwen2.5-72B-Instruct
| large language model | Build_In |
| [Qwen3](./llm/qwen3/README.md) | [huggingface](https://huggingface.co/Qwen) | model name
Qwen3-0.6B
Qwen3-1.7B
Qwen3-4B
Qwen3-8B
Qwen3-4B-Instruct-2507
Qwen3-4B-Thinking-2507
| large language model | Build_In |
| [QWQ](./llm/qwq/README.md) | [huggingface](https://huggingface.co/Qwen) | model name
QwQ-32B-Preview
QwQ-32B
| large language model | Build_In |
| [Skywork-OR1](./llm/skywork_or1/README.md) | [huggingface](https://hf-mirror.com/collections/Skywork/skywork-or1-67fa1bcb41b436ef2def76b9) | model name
Skywork-OR1-Math-7B
Skywork-OR1-7B-Preview
Skywork-OR1-32B-Preview
| large language model | Build_In |
| [Stablelm](./llm/stablelm/README.md) | [huggingface](https://huggingface.co/stabilityai) | model name
12b
| large language model | Build_In |
| [Tigerbot](./llm/tigerbot/README.md) | [huggingface](https://huggingface.co/TigerResearch) | model name
tigerbot-7b
tigerbot-13b
| large language model | Build_In |
| [wizardlm](./llm/wizardlm/README.md) | [huggingface](https://hf-mirror.com/dreamgen/WizardLM-2-7B) | model name
WizardLM-2-7B
| large language model | Build_In |
| [Yi](./llm/yi/README.md) | [huggingface](https://huggingface.co/01-ai) | model name
yi-6b
yi-9b
yi-34b
| large language model | Build_In |
| model | codebase | model list | model type | runtime |
| :------: | :------: | :------: | :------: | :-----: |
| [Qwen2.5](./llm/qwen2/README.md) | [huggingface](https://hf-mirror.com/Qwen)| model name
Qwen2.5-7B-Instruct-GPTQ-Int4
Qwen2.5-14B-Instruct-GPTQ-Int4
Qwen2.5-32B-Instruct-GPTQ-Int4
| large language model | vLLM |
| [Qwen3](./llm/qwen3/README.md) | [huggingface](https://huggingface.co/Qwen) | model name
Qwen3-30B-A3B-FP8
Qwen3-30B-A3B-Instruct-2507-FP8
Qwen3-30B-A3B-Thinking-2507-FP8
Qwen3-Coder-30B-A3B-Instruct-FP8
| large language model | vLLM |
| [DeepSeek-V3](./llm/deepseek_v3/README.md) | [huggingface](https://huggingface.co/deepseek-ai) | model name
DeepSeek-V3-Base
DeepSeek-V3
DeepSeek-V3-0324
DeepSeek-V3.1
DeepSeek-V3.1-Base
DeepSeek-V3.1-Terminus
| large language model | vLLM |
| [DeepSeek-R1](./llm/deepseek_r1/README.md) | [huggingface](https://huggingface.co/deepseek-ai) | model name
DeepSeek-R1
DeepSeek-R1-0528
| large language model | vLLM |
> 以下模型为Domain-LLM专业领域模型（医疗、金融、DeepResearch等），一般基于General-LLM模型为基座+专业领域数据集微调+强化学习而来
| model | codebase | model list | model type | runtime | priority |
| :------: | :------: | :------: | :------: | :-----: | :------: |
|[Tongyi-DeepResearch](llm/tongyi_deepresearch/README.md) | [huggingface](https://huggingface.co/Alibaba-NLP/Tongyi-DeepResearch-30B-A3B)| model name
Tongyi-DeepResearch-30B-A3B-PF8
|LLM | vLLM | p1 |
VLM Models
| model | codebase | model list | model type | runtime |
| :------: | :------: | :------: | :------: | :------: |
| [CLIP](./vlm/clip/README.md) | [openai](https://github.com/openai/CLIP/tree/main) | model name
clip
| vision-language model | Build_In |
| [Logics_Parsing](./vlm/logics_parsing/README.md) | [huggingface](https://hf-mirror.com/Logics-MLLM/Logics-Parsing)| model name
Logics-Parsing
| vision-language model | Build_In |
| [OCRFlux](./vlm/ocrflux/README.md) | [huggingface](https://hf-mirror.com/ChatDOC/OCRFlux-3B)| model name
OCRFlux-3B
| vision-language model | Build_In |
| [olmOCR2](./vlm/olmocr2/README.md) | [huggingface](https://hf-mirror.com/allenai/olmOCR-2-7B-1025)| model name
olmOCR-2-7B-1025
| vision-language model | Build_In |
| [Qwen2-VL](./vlm/qwen2_vl/README.md) | [huggingface](https://hf-mirror.com/collections/Qwen/qwen2-vl-66cee7455501d7126940800d) | model name
Qwen2-VL-2B-Instruct
Qwen2-VL-7B-Instruct
| vision-language model | Build_In |
| [Qwen2.5-VL](./vlm/qwen2_5_vl/README.md) | [huggingface](https://hf-mirror.com/collections/Qwen/qwen25-vl-6795ffac22b334a837c0f9a5) | model name
Qwen2.5-VL-3B-Instruct
Qwen2.5-VL-7B-Instruct
Qwen2.5-VL-32B-Instruct
| vision-language model | Build_In |
| [RolmOCR](./vlm/rolmocr/README.md) | [huggingface](https://hf-mirror.com/reducto/RolmOCR)| model name
RolmOCR
| vision-language model | Build_In |
| [SigLip](./vlm/siglip/README.md) | [google](https://github.com/google-research/big_vision) | model name