diff --git a/README.md b/README.md index d3a0c5c48..4f4169302 100644 --- a/README.md +++ b/README.md @@ -318,6 +318,7 @@ You can refine your search by selecting the task you're interested in (e.g., [te 1. **[DETR](https://huggingface.co/docs/transformers/model_doc/detr)** (from Facebook) released with the paper [End-to-End Object Detection with Transformers](https://huggingface.co/papers/2005.12872) by Nicolas Carion, Francisco Massa, Gabriel Synnaeve, Nicolas Usunier, Alexander Kirillov, Sergey Zagoruyko. 1. **[DINOv2](https://huggingface.co/docs/transformers/model_doc/dinov2)** (from Meta AI) released with the paper [DINOv2: Learning Robust Visual Features without Supervision](https://huggingface.co/papers/2304.07193) by Maxime Oquab, Timothée Darcet, Théo Moutakanni, Huy Vo, Marc Szafraniec, Vasil Khalidov, Pierre Fernandez, Daniel Haziza, Francisco Massa, Alaaeldin El-Nouby, Mahmoud Assran, Nicolas Ballas, Wojciech Galuba, Russell Howes, Po-Yao Huang, Shang-Wen Li, Ishan Misra, Michael Rabbat, Vasu Sharma, Gabriel Synnaeve, Hu Xu, Hervé Jegou, Julien Mairal, Patrick Labatut, Armand Joulin, Piotr Bojanowski. 1. **[DINOv2 with Registers](https://huggingface.co/docs/transformers/model_doc/dinov2_with_registers)** (from Meta AI) released with the paper [DINOv2 with Registers](https://huggingface.co/papers/2309.16588) by Timothée Darcet, Maxime Oquab, Julien Mairal, Piotr Bojanowski. +1. **[DINOv3](https://huggingface.co/docs/transformers/model_doc/dinov3)** (from Meta AI) released with the paper [DINOv3](https://huggingface.co/papers/2508.10104) by Oriane Siméoni, Huy V. Vo, Maximilian Seitzer, Federico Baldassarre, Maxime Oquab, Cijo Jose, Vasil Khalidov, Marc Szafraniec, Seungeun Yi, Michaël Ramamonjisoa, Francisco Massa, Daniel Haziza, Luca Wehrstedt, Jianyuan Wang, Timothée Darcet, Théo Moutakanni, Leonel Sentana, Claire Roberts, Andrea Vedaldi, Jamie Tolan, John Brandt, Camille Couprie, Julien Mairal, Hervé Jégou, Patrick Labatut, Piotr Bojanowski. 1. **[DistilBERT](https://huggingface.co/docs/transformers/model_doc/distilbert)** (from HuggingFace), released together with the paper [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://huggingface.co/papers/1910.01108) by Victor Sanh, Lysandre Debut and Thomas Wolf. The same method has been applied to compress GPT2 into [DistilGPT2](https://github.com/huggingface/transformers/tree/main/examples/research_projects/distillation), RoBERTa into [DistilRoBERTa](https://github.com/huggingface/transformers/tree/main/examples/research_projects/distillation), Multilingual BERT into [DistilmBERT](https://github.com/huggingface/transformers/tree/main/examples/research_projects/distillation) and a German version of DistilBERT. 1. **[DiT](https://huggingface.co/docs/transformers/model_doc/dit)** (from Microsoft Research) released with the paper [DiT: Self-supervised Pre-training for Document Image Transformer](https://huggingface.co/papers/2203.02378) by Junlong Li, Yiheng Xu, Tengchao Lv, Lei Cui, Cha Zhang, Furu Wei. 1. **[Donut](https://huggingface.co/docs/transformers/model_doc/donut)** (from NAVER), released together with the paper [OCR-free Document Understanding Transformer](https://huggingface.co/papers/2111.15664) by Geewook Kim, Teakgyu Hong, Moonbin Yim, Jeongyeon Nam, Jinyoung Park, Jinyeong Yim, Wonseok Hwang, Sangdoo Yun, Dongyoon Han, Seunghyun Park. diff --git a/docs/snippets/6_supported-models.snippet b/docs/snippets/6_supported-models.snippet index d0459db74..99dd529b0 100644 --- a/docs/snippets/6_supported-models.snippet +++ b/docs/snippets/6_supported-models.snippet @@ -32,6 +32,7 @@ 1. **[DETR](https://huggingface.co/docs/transformers/model_doc/detr)** (from Facebook) released with the paper [End-to-End Object Detection with Transformers](https://huggingface.co/papers/2005.12872) by Nicolas Carion, Francisco Massa, Gabriel Synnaeve, Nicolas Usunier, Alexander Kirillov, Sergey Zagoruyko. 1. **[DINOv2](https://huggingface.co/docs/transformers/model_doc/dinov2)** (from Meta AI) released with the paper [DINOv2: Learning Robust Visual Features without Supervision](https://huggingface.co/papers/2304.07193) by Maxime Oquab, Timothée Darcet, Théo Moutakanni, Huy Vo, Marc Szafraniec, Vasil Khalidov, Pierre Fernandez, Daniel Haziza, Francisco Massa, Alaaeldin El-Nouby, Mahmoud Assran, Nicolas Ballas, Wojciech Galuba, Russell Howes, Po-Yao Huang, Shang-Wen Li, Ishan Misra, Michael Rabbat, Vasu Sharma, Gabriel Synnaeve, Hu Xu, Hervé Jegou, Julien Mairal, Patrick Labatut, Armand Joulin, Piotr Bojanowski. 1. **[DINOv2 with Registers](https://huggingface.co/docs/transformers/model_doc/dinov2_with_registers)** (from Meta AI) released with the paper [DINOv2 with Registers](https://huggingface.co/papers/2309.16588) by Timothée Darcet, Maxime Oquab, Julien Mairal, Piotr Bojanowski. +1. **[DINOv3](https://huggingface.co/docs/transformers/model_doc/dinov3)** (from Meta AI) released with the paper [DINOv3](https://huggingface.co/papers/2508.10104) by Oriane Siméoni, Huy V. Vo, Maximilian Seitzer, Federico Baldassarre, Maxime Oquab, Cijo Jose, Vasil Khalidov, Marc Szafraniec, Seungeun Yi, Michaël Ramamonjisoa, Francisco Massa, Daniel Haziza, Luca Wehrstedt, Jianyuan Wang, Timothée Darcet, Théo Moutakanni, Leonel Sentana, Claire Roberts, Andrea Vedaldi, Jamie Tolan, John Brandt, Camille Couprie, Julien Mairal, Hervé Jégou, Patrick Labatut, Piotr Bojanowski. 1. **[DistilBERT](https://huggingface.co/docs/transformers/model_doc/distilbert)** (from HuggingFace), released together with the paper [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://huggingface.co/papers/1910.01108) by Victor Sanh, Lysandre Debut and Thomas Wolf. The same method has been applied to compress GPT2 into [DistilGPT2](https://github.com/huggingface/transformers/tree/main/examples/research_projects/distillation), RoBERTa into [DistilRoBERTa](https://github.com/huggingface/transformers/tree/main/examples/research_projects/distillation), Multilingual BERT into [DistilmBERT](https://github.com/huggingface/transformers/tree/main/examples/research_projects/distillation) and a German version of DistilBERT. 1. **[DiT](https://huggingface.co/docs/transformers/model_doc/dit)** (from Microsoft Research) released with the paper [DiT: Self-supervised Pre-training for Document Image Transformer](https://huggingface.co/papers/2203.02378) by Junlong Li, Yiheng Xu, Tengchao Lv, Lei Cui, Cha Zhang, Furu Wei. 1. **[Donut](https://huggingface.co/docs/transformers/model_doc/donut)** (from NAVER), released together with the paper [OCR-free Document Understanding Transformer](https://huggingface.co/papers/2111.15664) by Geewook Kim, Teakgyu Hong, Moonbin Yim, Jeongyeon Nam, Jinyoung Park, Jinyeong Yim, Wonseok Hwang, Sangdoo Yun, Dongyoon Han, Seunghyun Park. diff --git a/src/models.js b/src/models.js index 98e6b796f..528c2fb58 100644 --- a/src/models.js +++ b/src/models.js @@ -5867,6 +5867,18 @@ export class Dinov2WithRegistersForImageClassification extends Dinov2WithRegiste return new SequenceClassifierOutput(await super._call(model_inputs)); } } +////////////////////////////////////////////////// + +////////////////////////////////////////////////// +export class DINOv3ViTPreTrainedModel extends PreTrainedModel { } +export class DINOv3ViTModel extends DINOv3ViTPreTrainedModel { } +////////////////////////////////////////////////// + +////////////////////////////////////////////////// +export class DINOv3ConvNextPreTrainedModel extends PreTrainedModel { } +export class DINOv3ConvNextModel extends DINOv3ConvNextPreTrainedModel { } +////////////////////////////////////////////////// + ////////////////////////////////////////////////// export class GroundingDinoPreTrainedModel extends PreTrainedModel { } export class GroundingDinoForObjectDetection extends GroundingDinoPreTrainedModel { } @@ -7772,6 +7784,8 @@ const MODEL_MAPPING_NAMES_ENCODER_ONLY = new Map([ ['convnextv2', ['ConvNextV2Model', ConvNextV2Model]], ['dinov2', ['Dinov2Model', Dinov2Model]], ['dinov2_with_registers', ['Dinov2WithRegistersModel', Dinov2WithRegistersModel]], + ['dinov3_vit', ['DINOv3ViTModel', DINOv3ViTModel]], + ['dinov3_convnext', ['DINOv3ConvNextModel', DINOv3ConvNextModel]], ['resnet', ['ResNetModel', ResNetModel]], ['swin', ['SwinModel', SwinModel]], ['swin2sr', ['Swin2SRModel', Swin2SRModel]], diff --git a/src/models/dinov3_vit/image_processing_dinov3_vit.js b/src/models/dinov3_vit/image_processing_dinov3_vit.js new file mode 100644 index 000000000..d907f810b --- /dev/null +++ b/src/models/dinov3_vit/image_processing_dinov3_vit.js @@ -0,0 +1,6 @@ + +import { + ImageProcessor, +} from "../../base/image_processors_utils.js"; + +export class DINOv3ViTImageProcessor extends ImageProcessor { } diff --git a/src/models/image_processors.js b/src/models/image_processors.js index 95f275893..57c4b158a 100644 --- a/src/models/image_processors.js +++ b/src/models/image_processors.js @@ -6,6 +6,7 @@ export * from './clip/image_processing_clip.js' export * from './convnext/image_processing_convnext.js' export * from './deit/image_processing_deit.js' export * from './detr/image_processing_detr.js' +export * from './dinov3_vit/image_processing_dinov3_vit.js' export * from './donut/image_processing_donut.js' export * from './dpt/image_processing_dpt.js' export * from './efficientnet/image_processing_efficientnet.js'