Below, we list all presets available in the KerasHub library. For more detailed usage, browse the docstring for a particular class. For an in depth introduction to our API, see the getting started guide.
The following preset names correspond to a config and weights for a pretrained
model. Any task, preprocessor, backbone, or tokenizer from_preset() can be used
to create a model from the saved preset.
backbone = keras_hub.models.Backbone.from_preset("bert_base_en")
tokenizer = keras_hub.models.Tokenizer.from_preset("bert_base_en")
classifier = keras_hub.models.TextClassifier.from_preset("bert_base_en", num_classes=2)
preprocessor = keras_hub.models.TextClassifierPreprocessor.from_preset("bert_base_en")
| Preset | Model API | Parameters | Description |
|---|---|---|---|
| albert_base_en_uncased | Albert | 11.68M | 12-layer ALBERT model where all input is lowercased. Trained on English Wikipedia + BooksCorpus. |
| albert_large_en_uncased | Albert | 17.68M | 24-layer ALBERT model where all input is lowercased. Trained on English Wikipedia + BooksCorpus. |
| albert_extra_large_en_uncased | Albert | 58.72M | 24-layer ALBERT model where all input is lowercased. Trained on English Wikipedia + BooksCorpus. |
| albert_extra_extra_large_en_uncased | Albert | 222.60M | 12-layer ALBERT model where all input is lowercased. Trained on English Wikipedia + BooksCorpus. |
| bart_base_en | Bart | 139.42M | 6-layer BART model where case is maintained. Trained on BookCorpus, English Wikipedia and CommonCrawl. |
| bart_large_en | Bart | 406.29M | 12-layer BART model where case is maintained. Trained on BookCorpus, English Wikipedia and CommonCrawl. |
| bart_large_en_cnn | Bart | 406.29M | The bart_large_en backbone model fine-tuned on the CNN+DM summarization dataset. |
| basnet_duts | BASNet | 108.89M | BASNet model with a 34-layer ResNet backbone, pre-trained on the DUTS image dataset at a 288x288 resolution. Model training was performed by Hamid Ali (https://github.com/hamidriasat/BASNet). |
| bert_tiny_en_uncased | Bert | 4.39M | 2-layer BERT model where all input is lowercased. Trained on English Wikipedia + BooksCorpus. |
| bert_tiny_en_uncased_sst2 | Bert | 4.39M | The bert_tiny_en_uncased backbone model fine-tuned on the SST-2 sentiment analysis dataset. |
| bert_small_en_uncased | Bert | 28.76M | 4-layer BERT model where all input is lowercased. Trained on English Wikipedia + BooksCorpus. |
| bert_medium_en_uncased | Bert | 41.37M | 8-layer BERT model where all input is lowercased. Trained on English Wikipedia + BooksCorpus. |
| bert_base_zh | Bert | 102.27M | 12-layer BERT model. Trained on Chinese Wikipedia. |
| bert_base_en | Bert | 108.31M | 12-layer BERT model where case is maintained. Trained on English Wikipedia + BooksCorpus. |
| bert_base_en_uncased | Bert | 109.48M | 12-layer BERT model where all input is lowercased. Trained on English Wikipedia + BooksCorpus. |
| bert_base_multi | Bert | 177.85M | 12-layer BERT model where case is maintained. Trained on trained on Wikipedias of 104 languages |
| bert_large_en | Bert | 333.58M | 24-layer BERT model where case is maintained. Trained on English Wikipedia + BooksCorpus. |
| bert_large_en_uncased | Bert | 335.14M | 24-layer BERT model where all input is lowercased. Trained on English Wikipedia + BooksCorpus. |
| bloom_560m_multi | Bloom | 559.21M | 24-layer Bloom model with hidden dimension of 1024. trained on 45 natural languages and 12 programming languages. |
| bloomz_560m_multi | Bloom | 559.21M | 24-layer Bloom model with hidden dimension of 1024. finetuned on crosslingual task mixture (xP3) dataset. |
| bloom_1.1b_multi | Bloom | 1.07B | 24-layer Bloom model with hidden dimension of 1536. trained on 45 natural languages and 12 programming languages. |
| bloomz_1.1b_multi | Bloom | 1.07B | 24-layer Bloom model with hidden dimension of 1536. finetuned on crosslingual task mixture (xP3) dataset. |
| bloom_1.7b_multi | Bloom | 1.72B | 24-layer Bloom model with hidden dimension of 2048. trained on 45 natural languages and 12 programming languages. |
| bloomz_1.7b_multi | Bloom | 1.72B | 24-layer Bloom model with hidden dimension of 2048. finetuned on crosslingual task mixture (xP3) dataset. |
| bloom_3b_multi | Bloom | 3.00B | 30-layer Bloom model with hidden dimension of 2560. trained on 45 natural languages and 12 programming languages. |
| bloomz_3b_multi | Bloom | 3.00B | 30-layer Bloom model with hidden dimension of 2560. finetuned on crosslingual task mixture (xP3) dataset. |
| clip_vit_base_patch16 | CLIP | 149.62M | 150 million parameter, 12-layer for vision and 12-layer for text, patch size of 16, CLIP model. |
| clip_vit_base_patch32 | CLIP | 151.28M | 151 million parameter, 12-layer for vision and 12-layer for text, patch size of 32, CLIP model. |
| clip_vit_b_32_laion2b_s34b_b79k | CLIP | 151.28M | 151 million parameter, 12-layer for vision and 12-layer for text, patch size of 32, Open CLIP model. |
| clip_vit_large_patch14 | CLIP | 427.62M | 428 million parameter, 24-layer for vision and 12-layer for text, patch size of 14, CLIP model. |
| clip_vit_large_patch14_336 | CLIP | 427.94M | 428 million parameter, 24-layer for vision and 12-layer for text, patch size of 14, image size of 336, CLIP model. |
| clip_vit_h_14_laion2b_s32b_b79k | CLIP | 986.11M | 986 million parameter, 32-layer for vision and 24-layer for text, patch size of 14, Open CLIP model. |
| clip_vit_g_14_laion2b_s12b_b42k | CLIP | 1.37B | 1.4 billion parameter, 40-layer for vision and 24-layer for text, patch size of 14, Open CLIP model. |
| clip_vit_bigg_14_laion2b_39b_b160k | CLIP | 2.54B | 2.5 billion parameter, 48-layer for vision and 32-layer for text, patch size of 14, Open CLIP model. |
| csp_resnext_50_ra_imagenet | CSPNet | 20.57M | A CSP-ResNeXt (Cross-Stage-Partial) image classification model pre-trained on the Randomly Augmented ImageNet 1k dataset at a 256x256 resolution. |
| csp_resnet_50_ra_imagenet | CSPNet | 21.62M | A CSP-ResNet (Cross-Stage-Partial) image classification model pre-trained on the Randomly Augmented ImageNet 1k dataset at a 256x256 resolution. |
| csp_darknet_53_ra_imagenet | CSPNet | 27.64M | A CSP-DarkNet (Cross-Stage-Partial) image classification model pre-trained on the Randomly Augmented ImageNet 1k dataset at a 256x256 resolution. |
| darknet_53_imagenet | CSPNet | 41.61M | A DarkNet image classification model pre-trained on theImageNet 1k dataset at a 256x256 resolution. |
| dfine_nano_coco | D-FINE | 3.79M | D-FINE Nano model, the smallest variant in the family, pretrained on the COCO dataset. Ideal for applications where computational resources are limited. |
| dfine_small_coco | D-FINE | 10.33M | D-FINE Small model pretrained on the COCO dataset. Offers a balance between performance and computational efficiency. |
| dfine_small_obj2coco | D-FINE | 10.33M | D-FINE Small model first pretrained on Objects365 and then fine-tuned on COCO, combining broad feature learning with benchmark-specific adaptation. |
| dfine_small_obj365 | D-FINE | 10.62M | D-FINE Small model pretrained on the large-scale Objects365 dataset, enhancing its ability to recognize a wider variety of objects. |
| dfine_medium_coco | D-FINE | 19.62M | D-FINE Medium model pretrained on the COCO dataset. A solid baseline with strong performance for general-purpose object detection. |
| dfine_medium_obj2coco | D-FINE | 19.62M | D-FINE Medium model using a two-stage training process: pretraining on Objects365 followed by fine-tuning on COCO. |
| dfine_medium_obj365 | D-FINE | 19.99M | D-FINE Medium model pretrained on the Objects365 dataset. Benefits from a larger and more diverse pretraining corpus. |
| dfine_large_coco | D-FINE | 31.34M | D-FINE Large model pretrained on the COCO dataset. Provides high accuracy and is suitable for more demanding tasks. |
| dfine_large_obj2coco_e25 | D-FINE | 31.34M | D-FINE Large model pretrained on Objects365 and then fine-tuned on COCO for 25 epochs. A high-performance model with specialized tuning. |
| dfine_large_obj365 | D-FINE | 31.86M | D-FINE Large model pretrained on the Objects365 dataset for improved generalization and performance on diverse object categories. |
| dfine_xlarge_coco | D-FINE | 62.83M | D-FINE X-Large model, the largest COCO-pretrained variant, designed for state-of-the-art performance where accuracy is the top priority. |
| dfine_xlarge_obj2coco | D-FINE | 62.83M | D-FINE X-Large model, pretrained on Objects365 and fine-tuned on COCO, representing the most powerful model in this series for COCO-style tasks. |
| dfine_xlarge_obj365 | D-FINE | 63.35M | D-FINE X-Large model pretrained on the Objects365 dataset, offering maximum performance by leveraging a vast number of object categories during pretraining. |
| deberta_v3_extra_small_en | DebertaV3 | 70.68M | 12-layer DeBERTaV3 model where case is maintained. Trained on English Wikipedia, BookCorpus and OpenWebText. |
| deberta_v3_small_en | DebertaV3 | 141.30M | 6-layer DeBERTaV3 model where case is maintained. Trained on English Wikipedia, BookCorpus and OpenWebText. |
| deberta_v3_base_en | DebertaV3 | 183.83M | 12-layer DeBERTaV3 model where case is maintained. Trained on English Wikipedia, BookCorpus and OpenWebText. |
| deberta_v3_base_multi | DebertaV3 | 278.22M | 12-layer DeBERTaV3 model where case is maintained. Trained on the 2.5TB multilingual CC100 dataset. |
| deberta_v3_large_en | DebertaV3 | 434.01M | 24-layer DeBERTaV3 model where case is maintained. Trained on English Wikipedia, BookCorpus and OpenWebText. |
| deeplab_v3_plus_resnet50_pascalvoc | DeepLabV3 | 39.19M | DeepLabV3+ model with ResNet50 as image encoder and trained on augmented Pascal VOC dataset by Semantic Boundaries Dataset(SBD) which is having categorical accuracy of 90.01 and 0.63 Mean IoU. |
| deit_tiny_distilled_patch16_224_imagenet | DeiT | 5.52M | DeiT-T16 model pre-trained on the ImageNet 1k dataset with image resolution of 224x224 |
| deit_small_distilled_patch16_224_imagenet | DeiT | 21.67M | DeiT-S16 model pre-trained on the ImageNet 1k dataset with image resolution of 224x224 |
| deit_base_distilled_patch16_224_imagenet | DeiT | 85.80M | DeiT-B16 model pre-trained on the ImageNet 1k dataset with image resolution of 224x224 |
| deit_base_distilled_patch16_384_imagenet | DeiT | 86.09M | DeiT-B16 model pre-trained on the ImageNet 1k dataset with image resolution of 384x384 |
| densenet_121_imagenet | DenseNet | 7.04M | 121-layer DenseNet model pre-trained on the ImageNet 1k dataset at a 224x224 resolution. |
| densenet_169_imagenet | DenseNet | 12.64M | 169-layer DenseNet model pre-trained on the ImageNet 1k dataset at a 224x224 resolution. |
| densenet_201_imagenet | DenseNet | 18.32M | 201-layer DenseNet model pre-trained on the ImageNet 1k dataset at a 224x224 resolution. |
| depth_anything_v2_small | - | 25.31M | Small variant of Depth Anything V2 monocular depth estimation (MDE) model trained on synthetic labeled images and real unlabeled images. |
| depth_anything_v2_base | - | 98.52M | Base variant of Depth Anything V2 monocular depth estimation (MDE) model trained on synthetic labeled images and real unlabeled images. |
| depth_anything_v2_large | - | 336.72M | Large variant of Depth Anything V2 monocular depth estimation (MDE) model trained on synthetic labeled images and real unlabeled images. |
| dinov2_small | DINOV2 | 22.58M | Vision Transformer (small-sized model) trained using DINOv2. |
| dinov2_with_registers_small | DINOV2 | 22.58M | Vision Transformer (small-sized model) trained using DINOv2, with registers. |
| dinov2_base | DINOV2 | 87.63M | Vision Transformer (base-sized model) trained using DINOv2. |
| dinov2_with_registers_base | DINOV2 | 87.64M | Vision Transformer (base-sized model) trained using DINOv2, with registers. |
| dinov2_large | DINOV2 | 305.77M | Vision Transformer (large-sized model) trained using DINOv2. |
| dinov2_with_registers_large | DINOV2 | 305.78M | Vision Transformer (large-sized model) trained using DINOv2, with registers. |
| dinov2_giant | DINOV2 | 1.14B | Vision Transformer (giant-sized model) trained using DINOv2. |
| dinov2_with_registers_giant | DINOV2 | 1.14B | Vision Transformer (giant-sized model) trained using DINOv2, with registers. |
| distil_bert_base_en | DistilBert | 65.19M | 6-layer DistilBERT model where case is maintained. Trained on English Wikipedia + BooksCorpus using BERT as the teacher model. |
| distil_bert_base_en_uncased | DistilBert | 66.36M | 6-layer DistilBERT model where all input is lowercased. Trained on English Wikipedia + BooksCorpus using BERT as the teacher model. |
| distil_bert_base_multi | DistilBert | 134.73M | 6-layer DistilBERT model where case is maintained. Trained on Wikipedias of 104 languages |
| efficientnet_lite0_ra_imagenet | EfficientNet | 4.65M | EfficientNet-Lite model fine-trained on the ImageNet 1k dataset with RandAugment recipe. |
| efficientnet_b0_ra_imagenet | EfficientNet | 5.29M | EfficientNet B0 model pre-trained on the ImageNet 1k dataset with RandAugment recipe. |
| efficientnet_b0_ra4_e3600_r224_imagenet | EfficientNet | 5.29M | EfficientNet B0 model pre-trained on the ImageNet 1k dataset by Ross Wightman. Trained with timm scripts using hyper-parameters inspired by the MobileNet-V4 small, mixed with go-to hparams from timm and 'ResNet Strikes Back'. |
| efficientnet_es_ra_imagenet | EfficientNet | 5.44M | EfficientNet-EdgeTPU Small model trained on the ImageNet 1k dataset with RandAugment recipe. |
| efficientnet_em_ra2_imagenet | EfficientNet | 6.90M | EfficientNet-EdgeTPU Medium model trained on the ImageNet 1k dataset with RandAugment2 recipe. |
| efficientnet_b1_ft_imagenet | EfficientNet | 7.79M | EfficientNet B1 model fine-tuned on the ImageNet 1k dataset. |
| efficientnet_b1_ra4_e3600_r240_imagenet | EfficientNet | 7.79M | EfficientNet B1 model pre-trained on the ImageNet 1k dataset by Ross Wightman. Trained with timm scripts using hyper-parameters inspired by the MobileNet-V4 small, mixed with go-to hparams from timm and 'ResNet Strikes Back'. |
| efficientnet_b2_ra_imagenet | EfficientNet | 9.11M | EfficientNet B2 model pre-trained on the ImageNet 1k dataset with RandAugment recipe. |
| efficientnet_el_ra_imagenet | EfficientNet | 10.59M | EfficientNet-EdgeTPU Large model trained on the ImageNet 1k dataset with RandAugment recipe. |
| efficientnet_b3_ra2_imagenet | EfficientNet | 12.23M | EfficientNet B3 model pre-trained on the ImageNet 1k dataset with RandAugment2 recipe. |
| efficientnet2_rw_t_ra2_imagenet | EfficientNet | 13.65M | EfficientNet-v2 Tiny model trained on the ImageNet 1k dataset with RandAugment2 recipe. |
| efficientnet_b4_ra2_imagenet | EfficientNet | 19.34M | EfficientNet B4 model pre-trained on the ImageNet 1k dataset with RandAugment2 recipe. |
| efficientnet2_rw_s_ra2_imagenet | EfficientNet | 23.94M | EfficientNet-v2 Small model trained on the ImageNet 1k dataset with RandAugment2 recipe. |
| efficientnet_b5_sw_imagenet | EfficientNet | 30.39M | EfficientNet B5 model pre-trained on the ImageNet 12k dataset by Ross Wightman. Based on Swin Transformer train / pretrain recipe with modifications (related to both DeiT and ConvNeXt recipes). |
| efficientnet_b5_sw_ft_imagenet | EfficientNet | 30.39M | EfficientNet B5 model pre-trained on the ImageNet 12k dataset and fine-tuned on ImageNet-1k by Ross Wightman. Based on Swin Transformer train / pretrain recipe with modifications (related to both DeiT and ConvNeXt recipes). |
| efficientnet2_rw_m_agc_imagenet | EfficientNet | 53.24M | EfficientNet-v2 Medium model trained on the ImageNet 1k dataset with adaptive gradient clipping. |
| electra_small_discriminator_uncased_en | Electra | 13.55M | 12-layer small ELECTRA discriminator model. All inputs are lowercased. Trained on English Wikipedia + BooksCorpus. |
| electra_small_generator_uncased_en | Electra | 13.55M | 12-layer small ELECTRA generator model. All inputs are lowercased. Trained on English Wikipedia + BooksCorpus. |
| electra_base_generator_uncased_en | Electra | 33.58M | 12-layer base ELECTRA generator model. All inputs are lowercased. Trained on English Wikipedia + BooksCorpus. |
| electra_large_generator_uncased_en | Electra | 51.07M | 24-layer large ELECTRA generator model. All inputs are lowercased. Trained on English Wikipedia + BooksCorpus. |
| electra_base_discriminator_uncased_en | Electra | 109.48M | 12-layer base ELECTRA discriminator model. All inputs are lowercased. Trained on English Wikipedia + BooksCorpus. |
| electra_large_discriminator_uncased_en | Electra | 335.14M | 24-layer large ELECTRA discriminator model. All inputs are lowercased. Trained on English Wikipedia + BooksCorpus. |
| esm2_t6_8M | ESM | 7.41M | 6 transformer layers version of the ESM-2 protein language model, trained on the UniRef50 clustered protein sequence dataset. |
| esm2_t12_35M | ESM | 33.27M | 12 transformer layers version of the ESM-2 protein language model, trained on the UniRef50 clustered protein sequence dataset. |
| esm2_t30_150M | ESM | 147.73M | 30 transformer layers version of the ESM-2 protein language model, trained on the UniRef50 clustered protein sequence dataset. |
| esm2_t33_650M | ESM | 649.40M | 33 transformer layers version of the ESM-2 protein language model, trained on the UniRef50 clustered protein sequence dataset. |
| f_net_base_en | FNet | 82.86M | 12-layer FNet model where case is maintained. Trained on the C4 dataset. |
| f_net_large_en | FNet | 236.95M | 24-layer FNet model where case is maintained. Trained on the C4 dataset. |
| falcon_refinedweb_1b_en | Falcon | 1.31B | 24-layer Falcon model (Falcon with 1B parameters), trained on 350B tokens of RefinedWeb dataset. |
| vault_gemma_1b_en | Gemma | 1.04B | 1 billion parameter, 26-layer, VaultGemma model. |
| gemma_2b_en | Gemma | 2.51B | 2 billion parameter, 18-layer, base Gemma model. |
| gemma_instruct_2b_en | Gemma | 2.51B | 2 billion parameter, 18-layer, instruction tuned Gemma model. |
| gemma_1.1_instruct_2b_en | Gemma | 2.51B | 2 billion parameter, 18-layer, instruction tuned Gemma model. The 1.1 update improves model quality. |
| code_gemma_1.1_2b_en | Gemma | 2.51B | 2 billion parameter, 18-layer, CodeGemma model. This model has been trained on a fill-in-the-middle (FIM) task for code completion. The 1.1 update improves model quality. |
| code_gemma_2b_en | Gemma | 2.51B | 2 billion parameter, 18-layer, CodeGemma model. This model has been trained on a fill-in-the-middle (FIM) task for code completion. |
| gemma2_2b_en | Gemma | 2.61B | 2 billion parameter, 26-layer, base Gemma model. |
| gemma2_instruct_2b_en | Gemma | 2.61B | 2 billion parameter, 26-layer, instruction tuned Gemma model. |
| shieldgemma_2b_en | Gemma | 2.61B | 2 billion parameter, 26-layer, ShieldGemma model. |
| c2s_scale_gemma_2_2b_en | Gemma | 2.61B | A 2 billion parameter, single-cell biology-aware model built on the Gemma-2 architecture. |
| gemma_7b_en | Gemma | 8.54B | 7 billion parameter, 28-layer, base Gemma model. |
| gemma_instruct_7b_en | Gemma | 8.54B | 7 billion parameter, 28-layer, instruction tuned Gemma model. |
| gemma_1.1_instruct_7b_en | Gemma | 8.54B | 7 billion parameter, 28-layer, instruction tuned Gemma model. The 1.1 update improves model quality. |
| code_gemma_7b_en | Gemma | 8.54B | 7 billion parameter, 28-layer, CodeGemma model. This model has been trained on a fill-in-the-middle (FIM) task for code completion. |
| code_gemma_instruct_7b_en | Gemma | 8.54B | 7 billion parameter, 28-layer, instruction tuned CodeGemma model. This model has been trained for chat use cases related to code. |
| code_gemma_1.1_instruct_7b_en | Gemma | 8.54B | 7 billion parameter, 28-layer, instruction tuned CodeGemma model. This model has been trained for chat use cases related to code. The 1.1 update improves model quality. |
| gemma2_9b_en | Gemma | 9.24B | 9 billion parameter, 42-layer, base Gemma model. |
| gemma2_instruct_9b_en | Gemma | 9.24B | 9 billion parameter, 42-layer, instruction tuned Gemma model. |
| shieldgemma_9b_en | Gemma | 9.24B | 9 billion parameter, 42-layer, ShieldGemma model. |
| gemma2_27b_en | Gemma | 27.23B | 27 billion parameter, 42-layer, base Gemma model. |
| gemma2_instruct_27b_en | Gemma | 27.23B | 27 billion parameter, 42-layer, instruction tuned Gemma model. |
| shieldgemma_27b_en | Gemma | 27.23B | 27 billion parameter, 42-layer, ShieldGemma model. |
| c2s_scale_gemma_2_27b_en | Gemma | 27.23B | A 27 billion parameter, single-cell biology-aware model built on the Gemma-2 architecture. |
| gemma3_270m | Gemma3 | 268.10M | 270-million parameter(170m embedding,100m transformer params) model, 18-layer, text-only designed for hyper-efficient AI, particularly for task-specific fine-tuning. |
| gemma3_instruct_270m | Gemma3 | 268.10M | 270-million parameter(170m embedding,100m transformer params) model, 18-layer, text-only,instruction-tuned model designed for hyper-efficient AI, particularly for task-specific fine-tuning. |
| gemma3_1b | Gemma3 | 999.89M | 1 billion parameter, 26-layer, text-only pretrained Gemma3 model. |
| gemma3_instruct_1b | Gemma3 | 999.89M | 1 billion parameter, 26-layer, text-only instruction-tuned Gemma3 model. |
| gemma3_4b_text | Gemma3 | 3.88B | 4 billion parameter, 34-layer, text-only pretrained Gemma3 model. |
| gemma3_instruct_4b_text | Gemma3 | 3.88B | 4 billion parameter, 34-layer, text-only instruction-tuned Gemma3 model. |
| gemma3_4b | Gemma3 | 4.30B | 4 billion parameter, 34-layer, vision+text pretrained Gemma3 model. |
| gemma3_instruct_4b | Gemma3 | 4.30B | 4 billion parameter, 34-layer, vision+text instruction-tuned Gemma3 model. |
| gemma3_12b_text | Gemma3 | 11.77B | 12 billion parameter, 48-layer, text-only pretrained Gemma3 model. |
| gemma3_instruct_12b_text | Gemma3 | 11.77B | 12 billion parameter, 48-layer, text-only instruction-tuned Gemma3 model. |
| gemma3_12b | Gemma3 | 12.19B | 12 billion parameter, 48-layer, vision+text pretrained Gemma3 model. |
| gemma3_instruct_12b | Gemma3 | 12.19B | 12 billion parameter, 48-layer, vision+text instruction-tuned Gemma3 model. |
| gemma3_27b_text | Gemma3 | 27.01B | 27 billion parameter, 62-layer, text-only pretrained Gemma3 model. |
| gemma3_instruct_27b_text | Gemma3 | 27.01B | 27 billion parameter, 62-layer, text-only instruction-tuned Gemma3 model. |
| gemma3_27b | Gemma3 | 27.43B | 27 billion parameter, 62-layer, vision+text pretrained Gemma3 model. |
| gemma3_instruct_27b | Gemma3 | 27.43B | 27 billion parameter, 62-layer, vision+text instruction-tuned Gemma3 model. |
| gpt2_base_en | GPT2 | 124.44M | 12-layer GPT-2 model where case is maintained. Trained on WebText. |
| gpt2_base_en_cnn_dailymail | GPT2 | 124.44M | 12-layer GPT-2 model where case is maintained. Finetuned on the CNN/DailyMail summarization dataset. |
| gpt2_medium_en | GPT2 | 354.82M | 24-layer GPT-2 model where case is maintained. Trained on WebText. |
| gpt2_large_en | GPT2 | 774.03M | 36-layer GPT-2 model where case is maintained. Trained on WebText. |
| gpt2_extra_large_en | GPT2 | 1.56B | 48-layer GPT-2 model where case is maintained. Trained on WebText. |
| hgnetv2_b4_ssld_stage2_ft_in1k | HGNetV2 | 13.60M | HGNetV2 B4 model with 2-stage SSLD training, fine-tuned on ImageNet-1K. |
| hgnetv2_b5_ssld_stage1_in22k_in1k | HGNetV2 | 33.42M | HGNetV2 B5 model with 1-stage SSLD training, pre-trained on ImageNet-22K and fine-tuned on ImageNet-1K. |
| hgnetv2_b5_ssld_stage2_ft_in1k | HGNetV2 | 33.42M | HGNetV2 B5 model with 2-stage SSLD training, fine-tuned on ImageNet-1K. |
| hgnetv2_b6_ssld_stage1_in22k_in1k | HGNetV2 | 69.18M | HGNetV2 B6 model with 1-stage SSLD training, pre-trained on ImageNet-22K and fine-tuned on ImageNet-1K. |
| hgnetv2_b6_ssld_stage2_ft_in1k | HGNetV2 | 69.18M | HGNetV2 B6 model with 2-stage SSLD training, fine-tuned on ImageNet-1K. |
| llama2_7b_en | Llama | 6.74B | 7 billion parameter, 32-layer, base LLaMA 2 model. |
| llama2_instruct_7b_en | Llama | 6.74B | 7 billion parameter, 32-layer, instruction tuned LLaMA 2 model. |
| vicuna_1.5_7b_en | Llama | 6.74B | 7 billion parameter, 32-layer, instruction tuned Vicuna v1.5 model. |
| llama2_7b_en_int8 | Llama | 6.74B | 7 billion parameter, 32-layer, base LLaMA 2 model with activation and weights quantized to int8. |
| llama2_instruct_7b_en_int8 | Llama | 6.74B | 7 billion parameter, 32-layer, instruction tuned LLaMA 2 model with activation and weights quantized to int8. |
| llama3.2_1b | Llama3 | 1.50B | 1 billion parameter, 16-layer, based LLaMA 3.2 model. |
| llama3.2_instruct_1b | Llama3 | 1.50B | 1 billion parameter, 16-layer, instruction tuned LLaMA 3.2. |
| llama3.2_guard_1b | Llama3 | 1.50B | 1 billion parameter, 16-layer, based LLaMA 3.2 model fine-tuned for consent safety classification. |
| llama3.2_3b | Llama3 | 3.61B | 3 billion parameter, 26-layer, based LLaMA 3.2 model. |
| llama3.2_instruct_3b | Llama3 | 3.61B | 3 billion parameter, 28-layer, instruction tuned LLaMA 3.2. |
| llama3_8b_en | Llama3 | 8.03B | 8 billion parameter, 32-layer, base LLaMA 3 model. |
| llama3_instruct_8b_en | Llama3 | 8.03B | 8 billion parameter, 32-layer, instruction tuned LLaMA 3 model. |
| llama3.1_8b | Llama3 | 8.03B | 8 billion parameter, 32-layer, based LLaMA 3.1 model. |
| llama3.1_instruct_8b | Llama3 | 8.03B | 8 billion parameter, 32-layer, instruction tuned LLaMA 3.1. |
| llama3.1_guard_8b | Llama3 | 8.03B | 8 billion parameter, 32-layer, LLaMA 3.1 fine-tuned for consent safety classification. |
| llama3_8b_en_int8 | Llama3 | 8.03B | 8 billion parameter, 32-layer, base LLaMA 3 model with activation and weights quantized to int8. |
| llama3_instruct_8b_en_int8 | Llama3 | 8.03B | 8 billion parameter, 32-layer, instruction tuned LLaMA 3 model with activation and weights quantized to int8. |
| mistral_7b_en | Mistral | 7.24B | Mistral 7B base model |
| mistral_instruct_7b_en | Mistral | 7.24B | Mistral 7B instruct model |
| mistral_0.2_instruct_7b_en | Mistral | 7.24B | Mistral 7B instruct version 0.2 model |
| mistral_0.3_7b_en | Mistral | 7.25B | Mistral 7B base version 0.3 model |
| mistral_0.3_instruct_7b_en | Mistral | 7.25B | Mistral 7B instruct version 0.3 model |
| mit_b0_ade20k_512 | MiT | 3.32M | MiT (MixTransformer) model with 8 transformer blocks. |
| mit_b0_cityscapes_1024 | MiT | 3.32M | MiT (MixTransformer) model with 8 transformer blocks. |
| mit_b1_ade20k_512 | MiT | 13.16M | MiT (MixTransformer) model with 8 transformer blocks. |
| mit_b1_cityscapes_1024 | MiT | 13.16M | MiT (MixTransformer) model with 8 transformer blocks. |
| mit_b2_ade20k_512 | MiT | 24.20M | MiT (MixTransformer) model with 16 transformer blocks. |
| mit_b2_cityscapes_1024 | MiT | 24.20M | MiT (MixTransformer) model with 16 transformer blocks. |
| mit_b3_ade20k_512 | MiT | 44.08M | MiT (MixTransformer) model with 28 transformer blocks. |
| mit_b3_cityscapes_1024 | MiT | 44.08M | MiT (MixTransformer) model with 28 transformer blocks. |
| mit_b4_ade20k_512 | MiT | 60.85M | MiT (MixTransformer) model with 41 transformer blocks. |
| mit_b4_cityscapes_1024 | MiT | 60.85M | MiT (MixTransformer) model with 41 transformer blocks. |
| mit_b5_ade20k_640 | MiT | 81.45M | MiT (MixTransformer) model with 52 transformer blocks. |
| mit_b5_cityscapes_1024 | MiT | 81.45M | MiT (MixTransformer) model with 52 transformer blocks. |
| mixtral_8_7b_en | Mixtral | 46.70B | 32-layer Mixtral MoE model with 7 billionactive parameters and 8 experts per MoE layer. |
| mixtral_8_instruct_7b_en | Mixtral | 46.70B | Instruction fine-tuned 32-layer Mixtral MoE modelwith 7 billion active parameters and 8 experts per MoE layer. |
| mobilenet_v3_small_050_imagenet | MobileNet | 278.78K | Small Mobilenet V3 model pre-trained on the ImageNet 1k dataset at a 224x224 resolution. Has half channel multiplier. |
| mobilenet_v3_small_100_imagenet | MobileNet | 939.12K | Small Mobilenet V3 model pre-trained on the ImageNet 1k dataset at a 224x224 resolution. Has baseline channel multiplier. |
| mobilenet_v3_large_100_imagenet | MobileNet | 3.00M | Large Mobilenet V3 model pre-trained on the ImageNet 1k dataset at a 224x224 resolution. Has baseline channel multiplier. |
| mobilenet_v3_large_100_imagenet_21k | MobileNet | 3.00M | Large Mobilenet V3 model pre-trained on the ImageNet 21k dataset at a 224x224 resolution. Has baseline channel multiplier. |
| mobilenetv5_300m_enc_gemma3n | - | 294.28M | Lightweight 300M-parameter convolutional vision encoder used as the image backbone for Gemma 3n |
| moonshine_tiny_en | Moonshine | 27.09M | Moonshine tiny model for English speech recognition. Developed by Useful Sensors for real-time transcription. |
| moonshine_base_en | Moonshine | 61.51M | Moonshine base model for English speech recognition. Developed by Useful Sensors for real-time transcription. |
| opt_125m_en | OPT | 125.24M | 12-layer OPT model where case in maintained. Trained on BookCorpus, CommonCrawl, Pile, and PushShift.io corpora. |
| opt_1.3b_en | OPT | 1.32B | 24-layer OPT model where case in maintained. Trained on BookCorpus, CommonCrawl, Pile, and PushShift.io corpora. |
| opt_2.7b_en | OPT | 2.70B | 32-layer OPT model where case in maintained. Trained on BookCorpus, CommonCrawl, Pile, and PushShift.io corpora. |
| opt_6.7b_en | OPT | 6.70B | 32-layer OPT model where case in maintained. Trained on BookCorpus, CommonCrawl, Pile, and PushShift.io corpora. |
| pali_gemma_3b_mix_224 | PaliGemma | 2.92B | image size 224, mix fine tuned, text sequence length is 256 |
| pali_gemma_3b_224 | PaliGemma | 2.92B | image size 224, pre trained, text sequence length is 128 |
| pali_gemma_3b_mix_448 | PaliGemma | 2.92B | image size 448, mix fine tuned, text sequence length is 512 |
| pali_gemma_3b_448 | PaliGemma | 2.92B | image size 448, pre trained, text sequence length is 512 |
| pali_gemma_3b_896 | PaliGemma | 2.93B | image size 896, pre trained, text sequence length is 512 |
| pali_gemma2_mix_3b_224 | PaliGemma | 3.03B | 3 billion parameter, image size 224, 27-layer for SigLIP-So400m vision encoder and 26-layer Gemma2 2B lanuage model. This model has been fine-tuned on a wide range of vision-language tasks and domains. |
| pali_gemma2_pt_3b_224 | PaliGemma | 3.03B | 3 billion parameter, image size 224, 27-layer for SigLIP-So400m vision encoder and 26-layer Gemma2 2B lanuage model. This model has been pre-trained on a mixture of datasets. |
| pali_gemma_2_ft_docci_3b_448 | PaliGemma | 3.03B | 3 billion parameter, image size 448, 27-layer for SigLIP-So400m vision encoder and 26-layer Gemma2 2B lanuage model. This model has been fine-tuned on the DOCCI dataset for improved descriptions with fine-grained details. |
| pali_gemma2_mix_3b_448 | PaliGemma | 3.03B | 3 billion parameter, image size 448, 27-layer for SigLIP-So400m vision encoder and 26-layer Gemma2 2B lanuage model. This model has been fine-tuned on a wide range of vision-language tasks and domains. |
| pali_gemma2_pt_3b_448 | PaliGemma | 3.03B | 3 billion parameter, image size 448, 27-layer for SigLIP-So400m vision encoder and 26-layer Gemma2 2B lanuage model. This model has been pre-trained on a mixture of datasets. |
| pali_gemma2_pt_3b_896 | PaliGemma | 3.04B | 3 billion parameter, image size 896, 27-layer for SigLIP-So400m vision encoder and 26-layer Gemma2 2B lanuage model. This model has been pre-trained on a mixture of datasets. |
| pali_gemma2_mix_10b_224 | PaliGemma | 9.66B | 10 billion parameter, image size 224, 27-layer for SigLIP-So400m vision encoder and 42-layer Gemma2 9B lanuage model. This model has been fine-tuned on a wide range of vision-language tasks and domains. |
| pali_gemma2_pt_10b_224 | PaliGemma | 9.66B | 10 billion parameter, image size 224, 27-layer for SigLIP-So400m vision encoder and 42-layer Gemma2 9B lanuage model. This model has been pre-trained on a mixture of datasets. |
| pali_gemma2_ft_docci_10b_448 | PaliGemma | 9.66B | 10 billion parameter, 27-layer for SigLIP-So400m vision encoder and 42-layer Gemma2 9B lanuage model. This model has been fine-tuned on the DOCCI dataset for improved descriptions with fine-grained details. |
| pali_gemma2_mix_10b_448 | PaliGemma | 9.66B | 10 billion parameter, image size 448, 27-layer for SigLIP-So400m vision encoder and 42-layer Gemma2 9B lanuage model. This model has been fine-tuned on a wide range of vision-language tasks and domains. |
| pali_gemma2_pt_10b_448 | PaliGemma | 9.66B | 10 billion parameter, image size 448, 27-layer for SigLIP-So400m vision encoder and 42-layer Gemma2 9B lanuage model. This model has been pre-trained on a mixture of datasets. |
| pali_gemma2_pt_10b_896 | PaliGemma | 9.67B | 10 billion parameter, image size 896, 27-layer for SigLIP-So400m vision encoder and 42-layer Gemma2 9B lanuage model. This model has been pre-trained on a mixture of datasets. |
| pali_gemma2_mix_28b_224 | PaliGemma | 27.65B | 28 billion parameter, image size 224, 27-layer for SigLIP-So400m vision encoder and 46-layer Gemma2 27B lanuage model. This model has been fine-tuned on a wide range of vision-language tasks and domains. |
| pali_gemma2_mix_28b_448 | PaliGemma | 27.65B | 28 billion parameter, image size 448, 27-layer for SigLIP-So400m vision encoder and 46-layer Gemma2 27B lanuage model. This model has been fine-tuned on a wide range of vision-language tasks and domains. |
| pali_gemma2_pt_28b_224 | PaliGemma | 27.65B | 28 billion parameter, image size 224, 27-layer for SigLIP-So400m vision encoder and 46-layer Gemma2 27B lanuage model. This model has been pre-trained on a mixture of datasets. |
| pali_gemma2_pt_28b_448 | PaliGemma | 27.65B | 28 billion parameter, image size 448, 27-layer for SigLIP-So400m vision encoder and 46-layer Gemma2 27B lanuage model. This model has been pre-trained on a mixture of datasets. |
| pali_gemma2_pt_28b_896 | PaliGemma | 27.65B | 28 billion parameter, image size 896, 27-layer for SigLIP-So400m vision encoder and 46-layer Gemma2 27B lanuage model. This model has been pre-trained on a mixture of datasets. |
| parseq | - | 23.83M | Permuted autoregressive sequence (PARSeq) base model for scene text recognition |
| phi3_mini_4k_instruct_en | Phi3 | 3.82B | 3.8 billion parameters, 32 layers, 4k context length, Phi-3 model. The model was trained using the Phi-3 datasets. This dataset includes both synthetic data and filtered publicly available website data, with an emphasis on high-quality and reasoning-dense properties. |
| phi3_mini_128k_instruct_en | Phi3 | 3.82B | 3.8 billion parameters, 32 layers, 128k context length, Phi-3 model. The model was trained using the Phi-3 datasets. This dataset includes both synthetic data and filtered publicly available website data, with an emphasis on high-quality and reasoning-dense properties. |
| qwen2.5_0.5b_en | Qwen | 494.03M | 24-layer Qwen model with 0.5 billion parameters. |
| qwen2.5_instruct_0.5b_en | Qwen | 494.03M | Instruction fine-tuned 24-layer Qwen model with 0.5 billion parameters. |
| qwen2.5_3b_en | Qwen | 3.09B | 36-layer Qwen model with 3.1 billion parameters. |
| qwen2.5_7b_en | Qwen | 6.99B | 48-layer Qwen model with 7 billion parameters. |
| qwen2.5_instruct_32b_en | Qwen | 32.76B | Instruction fine-tuned 64-layer Qwen model with 32 billion parameters. |
| qwen2.5_instruct_72b_en | Qwen | 72.71B | Instruction fine-tuned 80-layer Qwen model with 72 billion parameters. |
| qwen3_0.6b_en | Qwen3 | 596.05M | 28-layer Qwen3 model with 596M parameters, optimized for efficiency and fast inference on resource-constrained devices. |
| qwen3_1.7b_en | Qwen3 | 1.72B | 28-layer Qwen3 model with 1.72B parameters, offering a good balance between performance and resource usage. |
| qwen3_4b_en | Qwen3 | 4.02B | 36-layer Qwen3 model with 4.02B parameters, offering improved reasoning capabilities and better performance than smaller variants. |
| qwen3_8b_en | Qwen3 | 8.19B | 36-layer Qwen3 model with 8.19B parameters, featuring enhanced reasoning, coding, and instruction-following capabilities. |
| qwen3_14b_en | Qwen3 | 14.77B | 40-layer Qwen3 model with 14.77B parameters, featuring advanced reasoning, coding, and multilingual capabilities. |
| qwen3_32b_en | Qwen3 | 32.76B | 64-layer Qwen3 model with 32.76B parameters, featuring state-of-the-art performance across reasoning, coding, and general language tasks. |
| qwen3_moe_30b_a3b_en | - | 30.53B | Mixture-of-Experts (MoE) model has 30.5 billion total parameters with 3.3 billion activated, built on 48 layers and utilizes 32 query and 4 key/value attention heads with 128 experts (8 active). |
| qwen3_moe_235b_a22b_en | - | 235.09B | Mixture-of-Experts (MoE) model has 235 billion total parameters with 22 billion activated, built on 94 layers and utilizes 64 query and 4 key/value attention heads with 128 experts (8 active). |
| qwen1.5_moe_2.7b_en | QwenMoe | 14.32B | 24-layer Qwen MoE model with 2.7 billion active parameters and 8 experts per MoE layer. |
| resnet_18_imagenet | ResNet | 11.19M | 18-layer ResNet model pre-trained on the ImageNet 1k dataset at a 224x224 resolution. |
| resnet_vd_18_imagenet | ResNet | 11.72M | 18-layer ResNetVD (ResNet with bag of tricks) model pre-trained on the ImageNet 1k dataset at a 224x224 resolution. |
| resnet_vd_34_imagenet | ResNet | 21.84M | 34-layer ResNetVD (ResNet with bag of tricks) model pre-trained on the ImageNet 1k dataset at a 224x224 resolution. |
| resnet_50_imagenet | ResNet | 23.56M | 50-layer ResNet model pre-trained on the ImageNet 1k dataset at a 224x224 resolution. |
| resnet_v2_50_imagenet | ResNet | 23.56M | 50-layer ResNetV2 model pre-trained on the ImageNet 1k dataset at a 224x224 resolution. |
| resnet_vd_50_imagenet | ResNet | 25.63M | 50-layer ResNetVD (ResNet with bag of tricks) model pre-trained on the ImageNet 1k dataset at a 224x224 resolution. |
| resnet_vd_50_ssld_imagenet | ResNet | 25.63M | 50-layer ResNetVD (ResNet with bag of tricks) model pre-trained on the ImageNet 1k dataset at a 224x224 resolution with knowledge distillation. |
| resnet_vd_50_ssld_v2_imagenet | ResNet | 25.63M | 50-layer ResNetVD (ResNet with bag of tricks) model pre-trained on the ImageNet 1k dataset at a 224x224 resolution with knowledge distillation and AutoAugment. |
| resnet_vd_50_ssld_v2_fix_imagenet | ResNet | 25.63M | 50-layer ResNetVD (ResNet with bag of tricks) model pre-trained on the ImageNet 1k dataset at a 224x224 resolution with knowledge distillation, AutoAugment and additional fine-tuning of the classification head. |
| resnet_101_imagenet | ResNet | 42.61M | 101-layer ResNet model pre-trained on the ImageNet 1k dataset at a 224x224 resolution. |
| resnet_v2_101_imagenet | ResNet | 42.61M | 101-layer ResNetV2 model pre-trained on the ImageNet 1k dataset at a 224x224 resolution. |
| resnet_vd_101_imagenet | ResNet | 44.67M | 101-layer ResNetVD (ResNet with bag of tricks) model pre-trained on the ImageNet 1k dataset at a 224x224 resolution. |
| resnet_vd_101_ssld_imagenet | ResNet | 44.67M | 101-layer ResNetVD (ResNet with bag of tricks) model pre-trained on the ImageNet 1k dataset at a 224x224 resolution with knowledge distillation. |
| resnet_152_imagenet | ResNet | 58.30M | 152-layer ResNet model pre-trained on the ImageNet 1k dataset at a 224x224 resolution. |
| resnet_vd_152_imagenet | ResNet | 60.36M | 152-layer ResNetVD (ResNet with bag of tricks) model pre-trained on the ImageNet 1k dataset at a 224x224 resolution. |
| resnet_vd_200_imagenet | ResNet | 74.93M | 200-layer ResNetVD (ResNet with bag of tricks) model pre-trained on the ImageNet 1k dataset at a 224x224 resolution. |
| retinanet_resnet50_fpn_v2_coco | RetinaNet | 31.56M | RetinaNet model with ResNet50 backbone fine-tuned on COCO in 800x800 resolution with FPN features created from P5 level. |
| retinanet_resnet50_fpn_coco | RetinaNet | 34.12M | RetinaNet model with ResNet50 backbone fine-tuned on COCO in 800x800 resolution. |
| roberta_base_en | Roberta | 124.05M | 12-layer RoBERTa model where case is maintained.Trained on English Wikipedia, BooksCorpus, CommonCraw, and OpenWebText. |
| roberta_large_en | Roberta | 354.31M | 24-layer RoBERTa model where case is maintained.Trained on English Wikipedia, BooksCorpus, CommonCraw, and OpenWebText. |
| sam_base_sa1b | Segment Anything Model | 93.74M | The base SAM model trained on the SA1B dataset. |
| sam_huge_sa1b | Segment Anything Model | 312.34M | The huge SAM model trained on the SA1B dataset. |
| sam_large_sa1b | Segment Anything Model | 641.09M | The large SAM model trained on the SA1B dataset. |
| siglip_base_patch16_224 | SigLIP | 203.16M | 200 million parameter, image size 224, pre-trained on WebLi. |
| siglip_base_patch16_256 | SigLIP | 203.20M | 200 million parameter, image size 256, pre-trained on WebLi. |
| siglip_base_patch16_384 | SigLIP | 203.45M | 200 million parameter, image size 384, pre-trained on WebLi. |
| siglip_base_patch16_512 | SigLIP | 203.79M | 200 million parameter, image size 512, pre-trained on WebLi. |
| siglip_base_patch16_256_multilingual | SigLIP | 370.63M | 370 million parameter, image size 256, pre-trained on WebLi. |
| siglip2_base_patch16_224 | SigLIP | 375.19M | 375 million parameter, patch size 16, image size 224, pre-trained on WebLi. |
| siglip2_base_patch16_256 | SigLIP | 375.23M | 375 million parameter, patch size 16, image size 256, pre-trained on WebLi. |
| siglip2_base_patch32_256 | SigLIP | 376.86M | 376 million parameter, patch size 32, image size 256, pre-trained on WebLi. |
| siglip2_base_patch16_384 | SigLIP | 376.86M | 376 million parameter, patch size 16, image size 384, pre-trained on WebLi. |
| siglip_large_patch16_256 | SigLIP | 652.15M | 652 million parameter, image size 256, pre-trained on WebLi. |
| siglip_large_patch16_384 | SigLIP | 652.48M | 652 million parameter, image size 384, pre-trained on WebLi. |
| siglip_so400m_patch14_224 | SigLIP | 877.36M | 877 million parameter, image size 224, shape-optimized version, pre-trained on WebLi. |
| siglip_so400m_patch14_384 | SigLIP | 877.96M | 877 million parameter, image size 384, shape-optimized version, pre-trained on WebLi. |
| siglip2_large_patch16_256 | SigLIP | 881.53M | 881 million parameter, patch size 16, image size 256, pre-trained on WebLi. |
| siglip2_large_patch16_384 | SigLIP | 881.86M | 881 million parameter, patch size 16, image size 384, pre-trained on WebLi. |
| siglip2_large_patch16_512 | SigLIP | 882.31M | 882 million parameter, patch size 16, image size 512, pre-trained on WebLi. |
| siglip_so400m_patch16_256_i18n | SigLIP | 1.13B | 1.1 billion parameter, image size 256, shape-optimized version, pre-trained on WebLi. |
| siglip2_so400m_patch14_224 | SigLIP | 1.14B | 1.1 billion parameter, patch size 14, image size 224, shape-optimized version, pre-trained on WebLi. |
| siglip2_so400m_patch16_256 | SigLIP | 1.14B | 1.1 billion parameter, patch size 16, image size 256, shape-optimized version, pre-trained on WebLi. |
| siglip2_so400m_patch14_384 | SigLIP | 1.14B | 1.1 billion parameter, patch size 14, image size 224, shape-optimized version, pre-trained on WebLi. |
| siglip2_so400m_patch16_384 | SigLIP | 1.14B | 1.1 billion parameter, patch size 16, image size 384, shape-optimized version, pre-trained on WebLi. |
| siglip2_so400m_patch16_512 | SigLIP | 1.14B | 1.1 billion parameter, patch size 16, image size 512, shape-optimized version, pre-trained on WebLi. |
| siglip2_giant_opt_patch16_256 | SigLIP | 1.87B | 1.8 billion parameter, patch size 16, image size 256, pre-trained on WebLi. |
| siglip2_giant_opt_patch16_384 | SigLIP | 1.87B | 1.8 billion parameter, patch size 16, image size 384, pre-trained on WebLi. |
| stable_diffusion_3_medium | Stable Diffusion 3 | 2.99B | 3 billion parameter, including CLIP L and CLIP G text encoders, MMDiT generative model, and VAE autoencoder. Developed by Stability AI. |
| stable_diffusion_3.5_medium | Stable Diffusion 3 | 3.37B | 3 billion parameter, including CLIP L and CLIP G text encoders, MMDiT-X generative model, and VAE autoencoder. Developed by Stability AI. |
| stable_diffusion_3.5_large | Stable Diffusion 3 | 9.05B | 9 billion parameter, including CLIP L and CLIP G text encoders, MMDiT generative model, and VAE autoencoder. Developed by Stability AI. |
| stable_diffusion_3.5_large_turbo | Stable Diffusion 3 | 9.05B | 9 billion parameter, including CLIP L and CLIP G text encoders, MMDiT generative model, and VAE autoencoder. A timestep-distilled version that eliminates classifier-free guidance and uses fewer steps for generation. Developed by Stability AI. |
| t5_small_multi | T5 | 0 | 8-layer T5 model. Trained on the Colossal Clean Crawled Corpus (C4). |
| t5_base_multi | T5 | 0 | 12-layer T5 model. Trained on the Colossal Clean Crawled Corpus (C4). |
| t5_large_multi | T5 | 0 | 24-layer T5 model. Trained on the Colossal Clean Crawled Corpus (C4). |
| flan_small_multi | T5 | 0 | 8-layer T5 model. Trained on the Colossal Clean Crawled Corpus (C4). |
| flan_base_multi | T5 | 0 | 12-layer T5 model. Trained on the Colossal Clean Crawled Corpus (C4). |
| flan_large_multi | T5 | 0 | 24-layer T5 model. Trained on the Colossal Clean Crawled Corpus (C4). |
| t5_1.1_small | T5 | 60.51M | |
| t5_1.1_base | T5 | 247.58M | |
| t5_1.1_large | T5 | 750.25M | |
| t5_1.1_xl | T5 | 2.85B | |
| t5_1.1_xxl | T5 | 11.14B | |
| t5gemma_s_s_ul2 | T5Gemma | 312.52M | T5Gemma S/S model with a small encoder and small decoder, adapted as a UL2 model. |
| t5gemma_s_s_prefixlm | T5Gemma | 312.52M | T5Gemma S/S model with a small encoder and small decoder, adapted as a prefix language model. |
| t5gemma_s_s_ul2_it | T5Gemma | 312.52M | T5Gemma S/S model with a small encoder and small decoder, adapted as a UL2 model and fine-tuned for instruction following. |
| t5gemma_s_s_prefixlm_it | T5Gemma | 312.52M | T5Gemma S/S model with a small encoder and small decoder, adapted as a prefix language model and fine-tuned for instruction following. |
| t5gemma_b_b_ul2 | T5Gemma | 591.49M | T5Gemma B/B model with a base encoder and base decoder, adapted as a UL2 model. |
| t5gemma_b_b_prefixlm | T5Gemma | 591.49M | T5Gemma B/B model with a base encoder and base decoder, adapted as a prefix language model. |
| t5gemma_b_b_ul2_it | T5Gemma | 591.49M | T5Gemma B/B model with a base encoder and base decoder, adapted as a UL2 model and fine-tuned for instruction following. |
| t5gemma_b_b_prefixlm_it | T5Gemma | 591.49M | T5Gemma B/B model with a base encoder and base decoder, adapted as a prefix language model and fine-tuned for instruction following. |
| t5gemma_l_l_ul2 | T5Gemma | 1.24B | T5Gemma L/L model with a large encoder and large decoder, adapted as a UL2 model. |
| t5gemma_l_l_prefixlm | T5Gemma | 1.24B | T5Gemma L/L model with a large encoder and large decoder, adapted as a prefix language model. |
| t5gemma_l_l_ul2_it | T5Gemma | 1.24B | T5Gemma L/L model with a large encoder and large decoder, adapted as a UL2 model and fine-tuned for instruction following. |
| t5gemma_l_l_prefixlm_it | T5Gemma | 1.24B | T5Gemma L/L model with a large encoder and large decoder, adapted as a prefix language model and fine-tuned for instruction following. |
| t5gemma_ml_ml_ul2 | T5Gemma | 2.20B | T5Gemma ML/ML model with a medium-large encoder and medium-large decoder, adapted as a UL2 model. |
| t5gemma_ml_ml_prefixlm | T5Gemma | 2.20B | T5Gemma ML/ML model with a medium-large encoder and medium-large decoder, adapted as a prefix language model. |
| t5gemma_ml_ml_ul2_it | T5Gemma | 2.20B | T5Gemma ML/ML model with a medium-large encoder and medium-large decoder, adapted as a UL2 model and fine-tuned for instruction following. |
| t5gemma_ml_ml_prefixlm_it | T5Gemma | 2.20B | T5Gemma ML/ML model with a medium-large encoder and medium-large decoder, adapted as a prefix language model and fine-tuned for instruction following. |
| t5gemma_xl_xl_ul2 | T5Gemma | 3.77B | T5Gemma XL/XL model with an extra-large encoder and extra-large decoder, adapted as a UL2 model. |
| t5gemma_xl_xl_prefixlm | T5Gemma | 3.77B | T5Gemma XL/XL model with an extra-large encoder and extra-large decoder, adapted as a prefix language model. |
| t5gemma_xl_xl_ul2_it | T5Gemma | 3.77B | T5Gemma XL/XL model with an extra-large encoder and extra-large decoder, adapted as a UL2 model and fine-tuned for instruction following. |
| t5gemma_xl_xl_prefixlm_it | T5Gemma | 3.77B | T5Gemma XL/XL model with an extra-large encoder and extra-large decoder, adapted as a prefix language model and fine-tuned for instruction following. |
| t5gemma_2b_2b_ul2 | T5Gemma | 5.60B | T5Gemma 2B/2B model with a 2-billion-parameter encoder and 2-billion-parameter decoder, adapted as a UL2 model. |
| t5gemma_2b_2b_prefixlm | T5Gemma | 5.60B | T5Gemma 2B/2B model with a 2-billion-parameter encoder and 2-billion-parameter decoder, adapted as a prefix language model. |
| t5gemma_2b_2b_ul2_it | T5Gemma | 5.60B | T5Gemma 2B/2B model with a 2-billion-parameter encoder and 2-billion-parameter decoder, adapted as a UL2 model and fine-tuned for instruction following. |
| t5gemma_2b_2b_prefixlm_it | T5Gemma | 5.60B | T5Gemma 2B/2B model with a 2-billion-parameter encoder and 2-billion-parameter decoder, adapted as a prefix language model and fine-tuned for instruction following. |
| t5gemma_9b_2b_ul2 | T5Gemma | 12.29B | T5Gemma 9B/2B model with a 9-billion-parameter encoder and 2-billion-parameter decoder, adapted as a UL2 model. |
| t5gemma_9b_2b_prefixlm | T5Gemma | 12.29B | T5Gemma 9B/2B model with a 9-billion-parameter encoder and 2-billion-parameter decoder, adapted as a prefix language model. |
| t5gemma_9b_2b_ul2_it | T5Gemma | 12.29B | T5Gemma 9B/2B model with a 9-billion-parameter encoder and 2-billion-parameter decoder, adapted as a UL2 model and fine-tuned for instruction following. |
| t5gemma_9b_2b_prefixlm_it | T5Gemma | 12.29B | T5Gemma 9B/2B model with a 9-billion-parameter encoder and 2-billion-parameter decoder, adapted as a prefix language model and fine-tuned for instruction following. |
| t5gemma_9b_9b_ul2 | T5Gemma | 20.33B | T5Gemma 9B/9B model with a 9-billion-parameter encoder and 9-billion-parameter decoder, adapted as a UL2 model. |
| t5gemma_9b_9b_prefixlm | T5Gemma | 20.33B | T5Gemma 9B/9B model with a 9-billion-parameter encoder and 9-billion-parameter decoder, adapted as a prefix language model. |
| t5gemma_9b_9b_ul2_it | T5Gemma | 20.33B | T5Gemma 9B/9B model with a 9-billion-parameter encoder and 9-billion-parameter decoder, adapted as a UL2 model and fine-tuned for instruction following. |
| t5gemma_9b_9b_prefixlm_it | T5Gemma | 20.33B | T5Gemma 9B/9B model with a 9-billion-parameter encoder and 9-billion-parameter decoder, adapted as a prefix language model and fine-tuned for instruction following. |
| vgg_11_imagenet | VGG | 9.22M | 11-layer vgg model pre-trained on the ImageNet 1k dataset at a 224x224 resolution. |
| vgg_13_imagenet | VGG | 9.40M | 13-layer vgg model pre-trained on the ImageNet 1k dataset at a 224x224 resolution. |
| vgg_16_imagenet | VGG | 14.71M | 16-layer vgg model pre-trained on the ImageNet 1k dataset at a 224x224 resolution. |
| vgg_19_imagenet | VGG | 20.02M | 19-layer vgg model pre-trained on the ImageNet 1k dataset at a 224x224 resolution. |
| vit_base_patch16_224_imagenet | ViT | 85.80M | ViT-B16 model pre-trained on the ImageNet 1k dataset with image resolution of 224x224 |
| vit_base_patch16_224_imagenet21k | ViT | 85.80M | ViT-B16 backbone pre-trained on the ImageNet 21k dataset with image resolution of 224x224 |
| vit_base_patch16_384_imagenet | ViT | 86.09M | ViT-B16 model pre-trained on the ImageNet 1k dataset with image resolution of 384x384 |
| vit_base_patch32_224_imagenet21k | ViT | 87.46M | ViT-B32 backbone pre-trained on the ImageNet 21k dataset with image resolution of 224x224 |
| vit_base_patch32_384_imagenet | ViT | 87.53M | ViT-B32 model pre-trained on the ImageNet 1k dataset with image resolution of 384x384 |
| vit_large_patch16_224_imagenet | ViT | 303.30M | ViT-L16 model pre-trained on the ImageNet 1k dataset with image resolution of 224x224 |
| vit_large_patch16_224_imagenet21k | ViT | 303.30M | ViT-L16 backbone pre-trained on the ImageNet 21k dataset with image resolution of 224x224 |
| vit_large_patch16_384_imagenet | ViT | 303.69M | ViT-L16 model pre-trained on the ImageNet 1k dataset with image resolution of 384x384 |
| vit_large_patch32_224_imagenet21k | ViT | 305.51M | ViT-L32 backbone pre-trained on the ImageNet 21k dataset with image resolution of 224x224 |
| vit_large_patch32_384_imagenet | ViT | 305.61M | ViT-L32 model pre-trained on the ImageNet 1k dataset with image resolution of 384x384 |
| vit_huge_patch14_224_imagenet21k | ViT | 630.76M | ViT-H14 backbone pre-trained on the ImageNet 21k dataset with image resolution of 224x224 |
| whisper_tiny_en | Whisper | 37.18M | 4-layer Whisper model. Trained on 438,000 hours of labelled English speech data. |
| whisper_tiny_multi | Whisper | 37.76M | 4-layer Whisper model. Trained on 680,000 hours of labelled multilingual speech data. |
| whisper_base_multi | Whisper | 72.59M | 6-layer Whisper model. Trained on 680,000 hours of labelled multilingual speech data. |
| whisper_base_en | Whisper | 124.44M | 6-layer Whisper model. Trained on 438,000 hours of labelled English speech data. |
| whisper_small_en | Whisper | 241.73M | 12-layer Whisper model. Trained on 438,000 hours of labelled English speech data. |
| whisper_small_multi | Whisper | 241.73M | 12-layer Whisper model. Trained on 680,000 hours of labelled multilingual speech data. |
| whisper_medium_en | Whisper | 763.86M | 24-layer Whisper model. Trained on 438,000 hours of labelled English speech data. |
| whisper_medium_multi | Whisper | 763.86M | 24-layer Whisper model. Trained on 680,000 hours of labelled multilingual speech data. |
| whisper_large_multi | Whisper | 1.54B | 32-layer Whisper model. Trained on 680,000 hours of labelled multilingual speech data. |
| whisper_large_multi_v2 | Whisper | 1.54B | 32-layer Whisper model. Trained for 2.5 epochs on 680,000 hours of labelled multilingual speech data. An improved of whisper_large_multi. |
| xception_41_imagenet | Xception | 20.86M | 41-layer Xception model pre-trained on ImageNet 1k. |
| xlm_roberta_base_multi | XLMRoberta | 277.45M | 12-layer XLM-RoBERTa model where case is maintained. Trained on CommonCrawl in 100 languages. |
| xlm_roberta_large_multi | XLMRoberta | 558.84M | 24-layer XLM-RoBERTa model where case is maintained. Trained on CommonCrawl in 100 languages. |