전체 검색

AI 모델 76

• dgmr↗

  openclimatefix

• ViT-L-16-SigLIP2-512↗

  timm

  This model has been converted for use in OpenCLIP from the original JAX checkpoints in Big Vision. - **Model Type:** Contrastive Image-Text, Zero-Shot Image Classification. - **Original:** https://github.com/google-research/big_vision - **Dataset:** WebLI - **Papers:** - SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features: https://arxiv.org/abs/2502.14786 - Sigmoid loss for language image pre-training: https://arxiv.org/abs/2303.15343

• convnext_large_mlp.clip_laion2b_soup_ft_in12k_in1k_384↗

  timm

  A ConvNeXt image classification model. CLIP image tower weights pretrained in OpenCLIP on LAION and fine-tuned on ImageNet-12k followed by ImageNet-1k in `timm` bby Ross Wightman. Please see related OpenCLIP model cards for more details on pretrain: * https://huggingface.co/laion/CLIP-convnext_xxlarge-laion2B-s34B-b82K-augreg-soup * https://huggingface.co/laion/CLIP-convnext_large_d.laion2B-s26B-b102K-augreg * https://huggingface.co/laion/CLIP-convnext_base_w-laion2B-s13B-b82K-augreg * https://huggingface.co/laion/CLIP-convnext_base_w_320-laion_aesthetic-s13B-b82K - **Model Type:** Image classification / feature backbone - **Model Stats:** - Params (M): 200.1 - GMACs: 101.1 - Activations (M): 126.7 - Image size: 384 x 384 - **Papers:** - LAION-5B: An open large-scale dataset for training next generation image-text models: https://arxiv.org/abs/2210.08402 - A ConvNet for the 2020s: https://arxiv.org/abs/2201.03545 - Learning Transferable Visual Models From Natural Language Supervision: https://arxiv.org/abs/2103.00020 - **Original:** https://github.com/mlfoundations/open_clip - **Pretrain Dataset:** LAION-2B - **Dataset:** ImageNet-1k

• CLIP-ViT-B-16-laion2B-s34B-b88K↗

  laion

  1. Model Details 2. Uses 3. Training Details 4. Evaluation 5. Acknowledgements 6. Citation A CLIP ViT-B/16 model trained with the LAION-2B English subset of LAION-5B (https://laion.ai/blog/laion-5b/) using OpenCLIP (https://github.com/mlfoundations/open_clip). Model training done by Mehdi Cherti on the JUWELS Booster supercomputer. See acknowledgements below.

• vit_large_patch14_clip_224.laion400m_e32↗

  timm

  This model is a dual use `open_clip` and `timm` model. Model name in OpenCLIP is `ViT-L-14`, and timm name is `vit_large_patch14_clip_224.laion400m_e32`.

• CLIP-ViT-L-14-laion2B-s32B-b82K↗

  laion

  1. Model Details 2. Uses 3. Training Details 4. Evaluation 5. Acknowledgements 6. Citation 7. How To Get Started With the Model A CLIP ViT L/14 model trained with the LAION-2B English subset of LAION-5B (https://laion.ai/blog/laion-5b/) using OpenCLIP (https://github.com/mlfoundations/open_clip). Model training ('babysitting') done by Ross Wightman on the JUWELS Booster supercomputer. See acknowledgements below.

• vit_base_patch16_clip_224.laion400m_e32↗

  timm

  This model is a dual use `open_clip` and `timm` model. Model name in OpenCLIP is `ViT-B-16`, and timm name is `vit_base_patch16_clip_224.laion400m_e32`.

• MobileCLIP2-L-14-OpenCLIP↗

  timm

• ViT-SO400M-14-SigLIP2-378↗

  timm

  This model has been converted for use in OpenCLIP from the original JAX checkpoints in Big Vision. - **Model Type:** Contrastive Image-Text, Zero-Shot Image Classification. - **Original:** https://github.com/google-research/big_vision - **Dataset:** WebLI - **Papers:** - SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features: https://arxiv.org/abs/2502.14786 - Sigmoid loss for language image pre-training: https://arxiv.org/abs/2303.15343

• metnet↗

  openclimatefix