timm
/

vit_pe_lang_gigantic_patch14_448.fb

Image Feature Extraction

Model card Files Files and versions

nielsr HF Staff commited on Jun 28

Commit

b184e6c

·

verified ·

1 Parent(s): 41539e3

Add project page link

This PR adds a link to the project page.

Files changed (1) hide show

README.md +5 -2

README.md CHANGED Viewed

@@ -1,11 +1,12 @@
 ---
 tags:
 - image-feature-extraction
 - timm
 - transformers
-library_name: timm
-license: apache-2.0
 ---
 # Model Details
 This is a `timm` remapped, image encoder only variant of the original weights.
@@ -13,6 +14,8 @@ This is a `timm` remapped, image encoder only variant of the original weights.
 [\[📃 Tech Report\]](https://arxiv.org/abs/2504.13181)
 [\[📂 Github\]](https://github.com/facebookresearch/perception_models/)
 Perception Encoder (PE) is a state-of-the-art encoder for image and video understanding trained via simple vision-language learning. It was introduced in "[Perception Encoder: The best visual embeddings
 are not at the output of the network](https://ai.meta.com/research/publications/perception-encoder-the-best-visual-embeddings-are-not-at-the-output-of-the-network/)".

 ---
+library_name: timm
+license: apache-2.0
 tags:
 - image-feature-extraction
 - timm
 - transformers
 ---
 # Model Details
 This is a `timm` remapped, image encoder only variant of the original weights.
 [\[📃 Tech Report\]](https://arxiv.org/abs/2504.13181)
 [\[📂 Github\]](https://github.com/facebookresearch/perception_models/)
+Project page: https://ai.meta.com/datasets/plm-data/
 Perception Encoder (PE) is a state-of-the-art encoder for image and video understanding trained via simple vision-language learning. It was introduced in "[Perception Encoder: The best visual embeddings
 are not at the output of the network](https://ai.meta.com/research/publications/perception-encoder-the-best-visual-embeddings-are-not-at-the-output-of-the-network/)".