모델주 - 파이토치¶
RBLN SDK는 RBLN NPU로 동작시킬 수 있는 다양한 파이토치 레퍼런스 모델들을 포함하는 RBLN 파이토치 모델주를 제공합니다. RBLN SDK 업데이트와 함께 지원하는 레퍼런스 모델들도 꾸준히 확장되고 있습니다. RBLN 모델주는 GitHub repository를 통해 다운로드할 수 있습니다.
지원 모델¶
RBLN 파이토치 모델주에서 제공하는 파이토치 레퍼런스 모델들은 아래와 같습니다.
| Model | Dataset | Task |
|---|---|---|
| Cosmos-Predict1-7B-Text2World† | - | |
| Cosmos-Predict1-14B-Text2World† | - | |
| Cosmos-Predict1-7B-Video2World† | - | |
| Cosmos-Predict1-14B-Video2World† | - | |
| Cosmos-Transfer1-7B† | - | |
| Cosmos-Transfer1-7B-Distilled† | - | |
| Cosmos-Transfer1-7B-Sample-AV† | - | |
| Cosmos-Transfer1-7B-4KUpscaler† | - | |
| Cosmos-Transfer1-7B-Sample-AV-Single2MultiView† | - | |
| 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 | Text Generation |
| DeepSeek-R1-Distill-Llama-70b | Samples generated by DeepSeek-R1 | Text Generation |
| DeepSeek-R1-Distill-Qwen-1.5b | Samples generated by DeepSeek-R1 | Text Generation |
| DeepSeek-R1-Distill-Qwen-7b | Samples generated by DeepSeek-R1 | Text Generation |
| DeepSeek-R1-Distill-Qwen-14b | Samples generated by DeepSeek-R1 | Text Generation |
| DeepSeek-R1-Distill-Qwen-32b | Samples generated by DeepSeek-R1 | Text Generation |
| Llama3.3-70b | A new mix of publicly available online data | Text Generation |
| Llama3.2-3b | A new mix of publicly available online data | Text Generation |
| Llama3.1-70b | A new mix of publicly available online data | Text Generation |
| Llama3.1-8b | A new mix of publicly available online data | Text Generation |
| Llama3-8b | A new mix of publicly available online data | Text Generation |
| Llama3-8b + LoRA | fingpt-forecaster-dow30-202305-202405 | Text Generation |
| Llama2-7b | A new mix of publicly available online data | Text Generation |
| Llama2-13b | A new mix of publicly available online data | Text Generation |
| Phi-2 | 250B tokens, combination of NLP synthetic data created by AIOAI GPT-3.5 | Text Generation |
| Gemma-7b | 6 trillion tokens of web, code, and mathematics text | Text Generation |
| Gemma-2b | 6 trillion tokens of web, code, and mathematics text | Text Generation |
| OPT-2.7b | BookCorpus, CC-Storeis, The Pile, etc. | Text Generation |
| Mistral-7b | Publicly available online data | Text Generation |
| A.X-4.0-Light | Large-scale Korean datasets | Text Generation |
| Qwen2-7b | 7T tokens of internal data | Text Generation |
| Qwen2.5-0.5b | 18T tokens of internal data | Text Generation |
| Qwen2.5-1.5b | 18T tokens of internal data | Text Generation |
| Qwen2.5-3b | 18T tokens of internal data | Text Generation |
| Qwen2.5-7b | 18T tokens of internal data | Text Generation |
| Qwen2.5-14b | 18T tokens of internal data | Text Generation |
| Qwen2.5-32b | 18T tokens of internal data | Text Generation |
| Qwen2.5-72b | 18T tokens of internal data | Text Generation |
| Qwen3-0.6b | 18T tokens of internal data | Text Generation |
| Qwen3-1.7b | 18T tokens of internal data | Text Generation |
| Qwen3-4b | 18T tokens of internal data | Text Generation |
| Qwen3-8b | 18T tokens of internal data | Text Generation |
| Qwen3-32b | 18T tokens of internal data | Text Generation |
| Midm-2.0-Mini | - | Text Generation |
| Midm-2.0-Base | - | Text Generation |
| Salamandra-7b | 2.4T tokens of 35 European languages and 92 programming languages | Text Generation |
| KONI-Llama3.1-8b | Approximately 11K SFT data and 7K DPO data | Text Generation |
| EXAONE-3.0-7.8b | 8T tokens of curated English and Korean data | Text Generation |
| EXAONE-3.5-2.4b | 6.5T tokens of curated English and Korean data | Text Generation |
| EXAONE-3.5-7.8b | 6.5T tokens of curated English and Korean data | Text Generation |
| EXAONE-3.5-32b | 6.5T tokens of curated English and Korean data | Text Generation |
| GPT2 | WebText | Text Generation |
| GPT2-medium | WebText | Text Generation |
| GPT2-large | WebText | Text Generation |
| GPT2-xl | WebText | Text Generation |
| OPT-6.7b | BookCorpus, CC-Storeis, The Pile, etc. | Text Generation |
| SOLAR-10.7b | alpaca-gpt4-data + etc. | Text Generation |
| EEVE-Korean-10.8b | Korean-translated ver. of Open-Orca/SlimOrca-Dedup and argilla/ultrafeedback-binarized-preferences-cleaned | Text Generation |
| T5-11b | Colossal Clean Crawled Corpus | Text Generation |
| T5-Enc-11b | Colossal Clean Crawled Corpus | Sentence Similarity |
| Qwen3-Embedding-4b | 18T tokens of internal data | Sentence Similarity |
| Qwen3-Reranker-4b | 18T tokens of internal data | Sentence Similarity |
| Gemma3-4b | - | |
| Gemma3-12b | - | |
| Gemma3-27b | - | |
| Qwen2-VL-7b | - | |
| Qwen2.5-VL-7b | - | |
| Idefics3-8B-Llama3 | - | |
| Llava-v1.5-7b | - | |
| Llava-v1.6-mistral-7b | - | |
| Pixtral-12b | - | |
| BLIP2-6.7b | LAION | |
| ColPali-v1.3 | academic datsets + Synthetic datasets | |
| T5-small | Colossal Clean Crawled Corpus | Text Generation |
| T5-base | Colossal Clean Crawled Corpus | Text Generation |
| T5-large | Colossal Clean Crawled Corpus | Text Generation |
| T5-3b | Colossal Clean Crawled Corpus | Text Generation |
| BART-base | BookCorpus + etc. | Text Generation |
| BART-large | BookCorpus + etc. | Text Generation |
| KoBART-base | Korean Wiki | Text Generation |
| Pegasus | XSUM | Text Generation |
| BERT-base | - BookCorpus & English Wikipedia - SQuAD v2 |
|
| BERT-large | - BookCorpus & English Wikipedia - SQuAD v2 |
|
| DistilBERT-base | - BookCorpus & English Wikipedia - SQuAD v2 |
Question Answering |
| SecureBERT | a manually crafted dataset from the human readable descriptions of MITRE ATT&CK techniques and tactics | Masked Language Modeling |
| RoBERTa | a manually crafted dataset from the human readable descriptions of MITRE ATT&CK techniques and tactics | Text Classification |
| MotionBERT | - Human3.6M & AMASS - NTURGB+D |
|
| Qwen3-Embedding-0.6b | 18T tokens of internal data | Sentence Similarity |
| Qwen3-Reranker-0.6b | 18T tokens of internal data | Sentence Similarity |
| E5-base-4K | Colossal Clean text Pairs | Sentence Similarity |
| LaBSE | - | Sentence Similarity |
| KR-SBERT-V40K-klueNLI-augSTS | - | Sentence Similarity |
| BGE-Small-EN-v1.5 | MLDR and bge-m3-data | Sentence Similarity |
| BGE-Base-EN-v1.5 | MLDR and bge-m3-data | Sentence Similarity |
| BGE-Large-EN-v1.5 | MLDR and bge-m3-data | Sentence Similarity |
| BGE-M3/Dense-Embedding | MLDR and bge-m3-data | Sentence Similarity |
| BGE-M3/Multi-Vector | MLDR and bge-m3-data | Sentence Similarity |
| BGE-M3/Sparse-Embedding | MLDR and bge-m3-data | Sentence Similarity |
| BGE-Reranker-V2-M3 | MLDR and bge-m3-data | Sentence Similarity |
| BGE-Reranker-Base | MLDR and bge-m3-data | Sentence Similarity |
| BGE-Reranker-Large | MLDR and bge-m3-data | Sentence Similarity |
| Ko-Reranker | msmarco-triplets | Sentence Similarity |
| Time-Series-Transformer | tourism-monthly dataset | Time-series Forecasting |
| BLIP2-2.7b | LAION | |
| Whisper-tiny | 680k hours of labeled data from the web | Speech to Text |
| Whisper-base | 680k hours of labeled data from the web | Speech to Text |
| Whisper-small | 680k hours of labeled data from the web | Speech to Text |
| Whisper-medium | 680k hours of labeled data from the web | Speech to Text |
| Whisper-large-v3 | 680k hours of labeled data from the web | Speech to Text |
| Whisper-large-v3-turbo | 680k hours of labeled data from the web | Speech to Text |
| Wav2Vec2 | Librispeech | Speech to Text |
| ConvTasNet | WSJ | Speech Separation |
| Audio-Spectogram-Transformer | AudioSet | Audio Classification |
| GroundingDino-Tiny | O365, GoldG, Cap4M | |
| GroundingDino-Base | O365, GoldG, Cap4M | |
| Depth-Anything-V2-Small | 595K synthetic labeled & 62M+ real unlabeled images | Monocular Depth Estimation |
| Depth-Anything-V2-Base | 595K synthetic labeled & 62M+ real unlabeled images | Monocular Depth Estimation |
| Depth-Anything-V2-Large | 595K synthetic labeled & 62M+ real unlabeled images | Monocular Depth Estimation |
| DPT-large | MIX 6 | Monocular Depth Estimation |
| SAM2_hiera_large/Video-Prediction | SA-V | Video Segmentation |
| SAM2_hiera_large/Image-Prediction | SA-V | Semantic Segmentation |
| DeepLabV3_ResNet50 | ILSVRC2012 | Semantic Segmentation |
| DeepLabV3_ResNet101 | ILSVRC2012 | Semantic Segmentation |
| DeepLabV3_MobileNetV3_Large | ILSVRC2012 | Semantic Segmentation |
| FCN_ResNet50 | ILSVRC2012 | Semantic Segmentation |
| FCN_ResNet101 | ILSVRC2012 | Semantic Segmentation |
| UNet | Carvana | Semantic Segmentation |
| ViT-large | ImageNet-21k & ImageNet | Image Classification |
| DeiT-tiny | ILSVRC2012 | Image Classification |
| DeiT-tiny distilled | ILSVRC2012 | Image Classification |
| DeiT-small | ILSVRC2012 | Image Classification |
| DeiT-small distilled | ILSVRC2012 | Image Classification |
| DeiT-base | ILSVRC2012 | Image Classification |
| DeiT-base distilled | ILSVRC2012 | Image Classification |
| DeiT-base 384 | ILSVRC2012 | Image Classification |
| DeiT-base distilled 384 | ILSVRC2012 | Image Classification |
| R3D_18 | KINETICS400_V1 | Video Classification |
| MC3_18 | KINETICS400_V1 | Video Classification |
| R(2+1)D_18 | KINETICS400_V1 | Video Classification |
| S3D | KINETICS400_V1 | Video Classification |
| YOLOv3-tiny | COCO | Object Detection |
| YOLOv3 | COCO | Object Detection |
| YOLOv3-spp | COCO | Object Detection |
| YOLOv4 | COCO | Object Detection |
| YOLOv4-csp-s-mish | COCO | Object Detection |
| YOLOv4-csp-x-mish | COCO | Object Detection |
| YOLOv5n | COCO | Object Detection |
| YOLOv5s | COCO | Object Detection |
| YOLOv5m | COCO | Object Detection |
| YOLOv5l | COCO | Object Detection |
| YOLOv5x | COCO | Object Detection |
| YOLOv5-face | WIDERFace | Face Detection |
| YOLOv6s | COCO | Object Detection |
| YOLOv6n | COCO | Object Detection |
| YOLOv6m | COCO | Object Detection |
| YOLOv6l | COCO | Object Detection |
| YOLOv7-tiny | COCO | Object Detection |
| YOLOv7 | COCO | Object Detection |
| YOLOv7x | COCO | Object Detection |
| YOLOv8s | COCO | Object Detection |
| YOLOv8n | COCO | Object Detection |
| YOLOv8m | COCO | Object Detection |
| YOLOv8b | COCO | Object Detection |
| YOLOv8l | COCO | Object Detection |
| YOLOv8x | COCO | Object Detection |
| YOLOv10n | COCO | Object Detection |
| YOLOv10s | COCO | Object Detection |
| YOLOv10m | COCO | Object Detection |
| YOLOv10b | COCO | Object Detection |
| YOLOv10l | COCO | Object Detection |
| YOLOv10x | COCO | Object Detection |
| YOLOX-nano | COCO | Object Detection |
| YOLOX-tiny | COCO | Object Detection |
| YOLOX-s | COCO | Object Detection |
| YOLOX-m | COCO | Object Detection |
| YOLOX-l | COCO | Object Detection |
| YOLOX-x | COCO | Object Detection |
| YOLOX-darknet53 | COCO | Object Detection |
| YOLO11n-seg | COCO | Semantic Segmentation |
| YOLO11s-seg | COCO | Semantic Segmentation |
| YOLO11m-seg | COCO | Semantic Segmentation |
| YOLO11l-seg | COCO | Semantic Segmentation |
| YOLO11x-seg | COCO | Semantic Segmentation |
| ConvNeXtTiny | ILSVRC2012 | Image Classification |
| ConvNeXtSmall | ILSVRC2012 | Image Classification |
| ConvNeXtBase | ILSVRC2012 | Image Classification |
| ConvNeXtLarge | ILSVRC2012 | Image Classification |
| EfficientNetB0 | ILSVRC2012 | Image Classification |
| EfficientNetB1 | ILSVRC2012 | Image Classification |
| EfficientNetB2 | ILSVRC2012 | Image Classification |
| EfficientNetB3 | ILSVRC2012 | Image Classification |
| EfficientNetB4 | ILSVRC2012 | Image Classification |
| EfficientNetB5 | ILSVRC2012 | Image Classification |
| EfficientNetB6 | ILSVRC2012 | Image Classification |
| EfficientNetB7 | ILSVRC2012 | Image Classification |
| EfficientNet_V2_S | ILSVRC2012 | Image Classification |
| EfficientNet_V2_M | ILSVRC2012 | Image Classification |
| EfficientNet_V2_L | ILSVRC2012 | Image Classification |
| Wide_ResNet50_2 | ILSVRC2012 | Image Classification |
| Wide_ResNet101_2 | ILSVRC2012 | Image Classification |
| MNASNet0_5 | ILSVRC2012 | Image Classification |
| MNASNet0_75 | ILSVRC2012 | Image Classification |
| MNASNet1_0 | ILSVRC2012 | Image Classification |
| MNASNet1_3 | ILSVRC2012 | Image Classification |
| MobileNet_V2 | ILSVRC2012 | Image Classification |
| MobileNet_V3_Small | ILSVRC2012 | Image Classification |
| MobileNet_V3_Large | ILSVRC2012 | Image Classification |
| ResNet18 | ILSVRC2012 | Image Classification |
| ResNet34 | ILSVRC2012 | Image Classification |
| ResNet50 | ILSVRC2012 | Image Classification |
| ResNet101 | ILSVRC2012 | Image Classification |
| ResNet152 | ILSVRC2012 | Image Classification |
| ResNet101V2 | ILSVRC2012 | Image Classification |
| ResNet152V2 | ILSVRC2012 | Image Classification |
| VGG11 | ILSVRC2012 | Image Classification |
| VGG11_BN | ILSVRC2012 | Image Classification |
| VGG13 | ILSVRC2012 | Image Classification |
| VGG13_BN | ILSVRC2012 | Image Classification |
| VGG16 | ILSVRC2012 | Image Classification |
| VGG16_BN | ILSVRC2012 | Image Classification |
| VGG19 | ILSVRC2012 | Image Classification |
| VGG19_BN | ILSVRC2012 | Image Classification |
| SqueezeNet1_0 | ILSVRC2012 | Image Classification |
| SqueezeNet1_1 | ILSVRC2012 | Image Classification |
| ShuffleNet_V2_X0_5 | ILSVRC2012 | Image Classification |
| ShuffleNet_V2_X1_0 | ILSVRC2012 | Image Classification |
| ShuffleNet_V2_X1_5 | ILSVRC2012 | Image Classification |
| ShuffleNet_V2_X2_0 | ILSVRC2012 | Image Classification |
| DenseNet121 | ILSVRC2012 | Image Classification |
| DenseNet161 | ILSVRC2012 | Image Classification |
| DenseNet169 | ILSVRC2012 | Image Classification |
| DenseNet201 | ILSVRC2012 | Image Classification |
| RegNet_X_400MF | ILSVRC2012 | Image Classification |
| RegNet_X_800MF | ILSVRC2012 | Image Classification |
| RegNet_X_1_6GF | ILSVRC2012 | Image Classification |
| RegNet_X_3_2GF | ILSVRC2012 | Image Classification |
| RegNet_X_8GF | ILSVRC2012 | Image Classification |
| RegNet_X_16GF | ILSVRC2012 | Image Classification |
| RegNet_X_32GF | ILSVRC2012 | Image Classification |
| RegNet_Y_400MF | ILSVRC2012 | Image Classification |
| RegNet_Y_800MF | ILSVRC2012 | Image Classification |
| RegNet_Y_1_6GF | ILSVRC2012 | Image Classification |
| RegNet_Y_3_2GF | ILSVRC2012 | Image Classification |
| RegNet_Y_8GF | ILSVRC2012 | Image Classification |
| RegNet_Y_16GF | ILSVRC2012 | Image Classification |
| RegNet_Y_32GF | ILSVRC2012 | Image Classification |
| RegNet_Y_128GF | ILSVRC2012 | Image Classification |
| ResNeXt50_32x4D | ILSVRC2012 | Image Classification |
| ResNeXt101_32x8D | ILSVRC2012 | Image Classification |
| ResNeXt101_64x4D | ILSVRC2012 | Image Classification |
| AlexNet | ILSVRC2012 | Image Classification |
| GoogLeNet | ILSVRC2012 | Image Classification |
| Inception_V3 | ILSVRC2012 | Image Classification |