Model Zoo - PyTorch¶
The RBLN PyTorch Model Zoo offers a wide variety of neural network models designed to run on the RBLN NPU. The number of models covered by the RBLN Model Zoo will continuously expand as the RBLN SDK is upated. You can access full list of the models in the RBLN Model Zoo GitHub repository.
Supported models¶
Here is the full list of the models covered by the RBLN PyTorch Model Zoo as of today.
Model | Dataset | Task |
---|---|---|
Stable Diffusion | - | |
Stable Diffusion + LoRA | - | |
Stable Diffusion V3† | - | |
Stable Diffusion XL | - | |
Stable Diffusion XL + multi-LoRA | - | |
SDXL-turbo | - | |
Stable Diffusion + ControlNet | - | |
Stable Diffusion XL + ControlNet | - | |
Kandinsky V2.2 | - | |
DeepSeek-R1-Distill-Llama-8b | Samples generated by DeepSeek-R1 | |
DeepSeek-R1-Distill-Llama-70b | Samples generated by DeepSeek-R1 | |
DeepSeek-R1-Distill-Qwen-1.5b | Samples generated by DeepSeek-R1 | |
DeepSeek-R1-Distill-Qwen-7b | Samples generated by DeepSeek-R1 | |
DeepSeek-R1-Distill-Qwen-14b | Samples generated by DeepSeek-R1 | |
DeepSeek-R1-Distill-Qwen-32b | Samples generated by DeepSeek-R1 | |
Llama3.3-70b | A new mix of publicly available online data | |
Llama3.2-3b | A new mix of publicly available online data | |
Llama3.1-70b | A new mix of publicly available online data | |
Llama3.1-8b | A new mix of publicly available online data | |
Llama3-8b | A new mix of publicly available online data | |
Llama3-8b + LoRA | fingpt-forecaster-dow30-202305-202405 | |
Llama2-7b | A new mix of publicly available online data | |
Llama2-13b | A new mix of publicly available online data | |
Phi-2 | 250B tokens, combination of NLP synthetic data created by AIOAI GPT-3.5 | |
Gemma-7b | 6 trillion tokens of web, code, and mathematics text | |
Gemma-2b | 6 trillion tokens of web, code, and mathematics text | |
Mistral-7b | Publicly available online data | |
Qwen2-7b | 7T tokens of internal data | |
Qwen2.5-7b | 18T tokens of internal data | |
Qwen2.5-14b | 18T tokens of internal data | |
Salamandra-7b | 2.4T tokens of 35 European languages and 92 programming languages | |
KONI-Llama3.1-8b | Approximately 11K SFT data and 7K DPO data | |
EXAONE-3.0-7.8b | 8T tokens of curated English and Korean data | |
EXAONE-3.5-2.4b | 6.5T tokens of curated English and Korean data | |
EXAONE-3.5-7.8b | 6.5T tokens of curated English and Korean data | |
EXAONE-3.5-32b | 6.5T tokens of curated English and Korean data | |
Mi:dm-7b | AI-HUB/the National Institute of Korean Language | |
GPT2 | WebText | |
GPT2-medium | WebText | |
GPT2-large | WebText | |
GPT2-xl | WebText | |
SOLAR-10.7b | alpaca-gpt4-data + etc. | |
EEVE-Korean-10.8b | Korean-translated ver. of Open-Orca/SlimOrca-Dedup and argilla/ultrafeedback-binarized-preferences-cleaned | |
Llava-v1.6-mistral-7b | - | |
T5-small | Colossal Clean Crawled Corpus | |
T5-base | Colossal Clean Crawled Corpus | |
T5-large | Colossal Clean Crawled Corpus | |
T5-3b | Colossal Clean Crawled Corpus | |
BART-base | BookCorpus + etc. | |
BART-large | BookCorpus + etc. | |
KoBART-base | Korean Wiki | |
E5-base-4K | Colossal Clean text Pairs | |
LaBSE | - | |
KR-SBERT-V40K-klueNLI-augSTS | - | |
BERT-base | - BookCorpus & English Wikipedia - SQuAD v2 |
|
BERT-large | - BookCorpus & English Wikipedia - SQuAD v2 |
|
DistilBERT-base | - BookCorpus & English Wikipedia - SQuAD v2 |
|
SecureBERT | a manually crafted dataset from the human readable descriptions of MITRE ATT&CK techniques and tactics | |
RoBERTa | a manually crafted dataset from the human readable descriptions of MITRE ATT&CK techniques and tactics | |
MotionBERT | - Human3.6M & AMASS - NTURGB+D |
|
BGE-Small-EN-v1.5 | MLDR and bge-m3-data | |
BGE-Base-EN-v1.5 | MLDR and bge-m3-data | |
BGE-Large-EN-v1.5 | MLDR and bge-m3-data | |
BGE-M3 | MLDR and bge-m3-data | |
BGE-Reranker-V2-M3 | MLDR and bge-m3-data | |
BGE-Reranker-Base | MLDR and bge-m3-data | |
BGE-Reranker-Large | MLDR and bge-m3-data | |
Ko-Reranker | msmarco-triplets | |
Whisper-tiny | 680k hours of labeled data from the web | |
Whisper-base | 680k hours of labeled data from the web | |
Whisper-small | 680k hours of labeled data from the web | |
Whisper-medium | 680k hours of labeled data from the web | |
Whisper-large-v3 | 680k hours of labeled data from the web | |
Whisper-large-v3-turbo | 680k hours of labeled data from the web | |
Wav2Vec2 | Librispeech | |
ConvTasNet | WSJ | |
Audio-Spectogram-Transformer | AudioSet | |
DPT-large | MIX 6 | |
SAM2.1_hiera_large | SA-V | |
DeepLabV3_ResNet50 | ILSVRC2012 | |
DeepLabV3_ResNet101 | ILSVRC2012 | |
DeepLabV3_MobileNetV3_Large | ILSVRC2012 | |
FCN_ResNet50 | ILSVRC2012 | |
FCN_ResNet101 | ILSVRC2012 | |
UNet | Carvana | |
ViT-large | ImageNet-21k & ImageNet | |
DeiT-tiny | ILSVRC2012 | |
DeiT-tiny distilled | ILSVRC2012 | |
DeiT-small | ILSVRC2012 | |
DeiT-small distilled | ILSVRC2012 | |
DeiT-base | ILSVRC2012 | |
DeiT-base distilled | ILSVRC2012 | |
DeiT-base 384 | ILSVRC2012 | |
DeiT-base distilled 384 | ILSVRC2012 | |
R3D_18 | KINETICS400_V1 | |
MC3_18 | KINETICS400_V1 | |
R(2+1)D_18 | KINETICS400_V1 | |
S3D | KINETICS400_V1 | |
YOLOv3-tiny | COCO | |
YOLOv3 | COCO | |
YOLOv3-spp | COCO | |
YOLOv4 | COCO | |
YOLOv4-csp-s-mish | COCO | |
YOLOv4-csp-x-mish | COCO | |
YOLOv5n | COCO | |
YOLOv5s | COCO | |
YOLOv5m | COCO | |
YOLOv5l | COCO | |
YOLOv5x | COCO | |
YOLOv5-face | WIDERFace | |
YOLOv6s | COCO | |
YOLOv6n | COCO | |
YOLOv6m | COCO | |
YOLOv6l | COCO | |
YOLOv7-tiny | COCO | |
YOLOv7 | COCO | |
YOLOv7x | COCO | |
YOLOv8s | COCO | |
YOLOv8n | COCO | |
YOLOv8m | COCO | |
YOLOv8b | COCO | |
YOLOv8l | COCO | |
YOLOv8x | COCO | |
YOLOv10n | COCO | |
YOLOv10s | COCO | |
YOLOv10m | COCO | |
YOLOv10b | COCO | |
YOLOv10l | COCO | |
YOLOv10x | COCO | |
YOLOX-nano | COCO | |
YOLOX-tiny | COCO | |
YOLOX-s | COCO | |
YOLOX-m | COCO | |
YOLOX-l | COCO | |
YOLOX-x | COCO | |
YOLOX-darknet53 | COCO | |
3DDFA_V2 | 300W-LP | |
ConvNeXtTiny | ILSVRC2012 | |
ConvNeXtSmall | ILSVRC2012 | |
ConvNeXtBase | ILSVRC2012 | |
ConvNeXtLarge | ILSVRC2012 | |
EfficientNetB0 | ILSVRC2012 | |
EfficientNetB1 | ILSVRC2012 | |
EfficientNetB2 | ILSVRC2012 | |
EfficientNetB3 | ILSVRC2012 | |
EfficientNetB4 | ILSVRC2012 | |
EfficientNetB5 | ILSVRC2012 | |
EfficientNetB6 | ILSVRC2012 | |
EfficientNetB7 | ILSVRC2012 | |
EfficientNet_V2_S | ILSVRC2012 | |
EfficientNet_V2_M | ILSVRC2012 | |
EfficientNet_V2_L | ILSVRC2012 | |
Wide_ResNet50_2 | ILSVRC2012 | |
Wide_ResNet101_2 | ILSVRC2012 | |
MNASNet0_5 | ILSVRC2012 | |
MNASNet0_75 | ILSVRC2012 | |
MNASNet1_0 | ILSVRC2012 | |
MNASNet1_3 | ILSVRC2012 | |
MobileNet_V2 | ILSVRC2012 | |
MobileNet_V3_Small | ILSVRC2012 | |
MobileNet_V3_Large | ILSVRC2012 | |
ResNet18 | ILSVRC2012 | |
ResNet34 | ILSVRC2012 | |
ResNet50 | ILSVRC2012 | |
ResNet101 | ILSVRC2012 | |
ResNet152 | ILSVRC2012 | |
ResNet101V2 | ILSVRC2012 | |
ResNet152V2 | ILSVRC2012 | |
VGG11 | ILSVRC2012 | |
VGG11_BN | ILSVRC2012 | |
VGG13 | ILSVRC2012 | |
VGG13_BN | ILSVRC2012 | |
VGG16 | ILSVRC2012 | |
VGG16_BN | ILSVRC2012 | |
VGG19 | ILSVRC2012 | |
VGG19_BN | ILSVRC2012 | |
SqueezeNet1_0 | ILSVRC2012 | |
SqueezeNet1_1 | ILSVRC2012 | |
ShuffleNet_V2_X0_5 | ILSVRC2012 | |
ShuffleNet_V2_X1_0 | ILSVRC2012 | |
ShuffleNet_V2_X1_5 | ILSVRC2012 | |
ShuffleNet_V2_X2_0 | ILSVRC2012 | |
DenseNet121 | ILSVRC2012 | |
DenseNet161 | ILSVRC2012 | |
DenseNet169 | ILSVRC2012 | |
DenseNet201 | ILSVRC2012 | |
RegNet_X_400MF | ILSVRC2012 | |
RegNet_X_800MF | ILSVRC2012 | |
RegNet_X_1_6GF | ILSVRC2012 | |
RegNet_X_3_2GF | ILSVRC2012 | |
RegNet_X_8GF | ILSVRC2012 | |
RegNet_X_16GF | ILSVRC2012 | |
RegNet_X_32GF | ILSVRC2012 | |
RegNet_Y_400MF | ILSVRC2012 | |
RegNet_Y_800MF | ILSVRC2012 | |
RegNet_Y_1_6GF | ILSVRC2012 | |
RegNet_Y_3_2GF | ILSVRC2012 | |
RegNet_Y_8GF | ILSVRC2012 | |
RegNet_Y_16GF | ILSVRC2012 | |
RegNet_Y_32GF | ILSVRC2012 | |
RegNet_Y_128GF | ILSVRC2012 | |
ResNeXt50_32x4D | ILSVRC2012 | |
ResNeXt101_32x8D | ILSVRC2012 | |
ResNeXt101_64x4D | ILSVRC2012 | |
AlexNet | ILSVRC2012 | |
GoogLeNet | ILSVRC2012 | |
Inception_V3 | ILSVRC2012 |