Meta

About Meta

Explore AI at Meta. Meet Muse, our new AI agent that takes tasks off your plate. Use Meta AI for questions and images, plus tools for developers.

Website ↗

Source ↗ · 2026-11-12T02:17:02.456468780Z

Transparency & Governance

  • Foundation Model Transparency Index 2025 · 31 / 100 · Company disclosure assessment Source assessment ↗

632 indexed models

632 matching models

Facebook-DinoV2-Image-Embeddings-ViT-Base · azureml v1

azureFoundry/azureml/Facebook-DinoV2-Image-Embeddings-ViT-Base@1

The Vision Transformer (ViT) is a transformer encoder model (BERT-like) pretrained on a large collection of images in a self-supervised fashion with the DinoV2 method. Images are presented to the model as a sequence of fixed-size patches, which are linearly embedded. One also ad

Input modalities
text
Output modalities
embeddings
Capabilities
embeddings

Facebook-DinoV2-Image-Embeddings-ViT-Base · azureml v2

azureFoundry/azureml/Facebook-DinoV2-Image-Embeddings-ViT-Base@2

The Vision Transformer (ViT) is a transformer encoder model (BERT-like) pretrained on a large collection of images in a self-supervised fashion with the DinoV2 method. Images are presented to the model as a sequence of fixed-size patches, which are linearly embedded. One also ad

Input modalities
text
Output modalities
embeddings
Capabilities
embeddings

Facebook-DinoV2-Image-Embeddings-ViT-Base · azureml v3

azureFoundry/azureml/Facebook-DinoV2-Image-Embeddings-ViT-Base@3

The Vision Transformer (ViT) is a transformer encoder model (BERT-like) pretrained on a large collection of images in a self-supervised fashion with the DinoV2 method. Images are presented to the model as a sequence of fixed-size patches, which are linearly embedded. One also ad

Input modalities
text
Output modalities
embeddings
Capabilities
embeddings

Facebook-DinoV2-Image-Embeddings-ViT-Giant · azureml v1

azureFoundry/azureml/Facebook-DinoV2-Image-Embeddings-ViT-Giant@1

The Vision Transformer (ViT) is a transformer encoder model (BERT-like) pretrained on a large collection of images in a self-supervised fashion with the DinoV2 method. Images are presented to the model as a sequence of fixed-size patches, which are linearly embedded. One also ad

Input modalities
text
Output modalities
embeddings
Capabilities
embeddings

Facebook-DinoV2-Image-Embeddings-ViT-Giant · azureml v2

azureFoundry/azureml/Facebook-DinoV2-Image-Embeddings-ViT-Giant@2

The Vision Transformer (ViT) is a transformer encoder model (BERT-like) pretrained on a large collection of images in a self-supervised fashion with the DinoV2 method. Images are presented to the model as a sequence of fixed-size patches, which are linearly embedded. One also ad

Input modalities
text
Output modalities
embeddings
Capabilities
embeddings

Facebook-DinoV2-Image-Embeddings-ViT-Giant · azureml v3

azureFoundry/azureml/Facebook-DinoV2-Image-Embeddings-ViT-Giant@3

The Vision Transformer (ViT) is a transformer encoder model (BERT-like) pretrained on a large collection of images in a self-supervised fashion with the DinoV2 method. Images are presented to the model as a sequence of fixed-size patches, which are linearly embedded. One also ad

Input modalities
text
Output modalities
embeddings
Capabilities
embeddings

Facebook-DinoV2-Image-Embeddings-ViT-Giant · azureml v4

azureFoundry/azureml/Facebook-DinoV2-Image-Embeddings-ViT-Giant@4

The Vision Transformer (ViT) is a transformer encoder model (BERT-like) pretrained on a large collection of images in a self-supervised fashion with the DinoV2 method. Images are presented to the model as a sequence of fixed-size patches, which are linearly embedded. One also ad

Input modalities
text
Output modalities
embeddings
Capabilities
embeddings

facebook/dinov2-large-imagenet1k-1-layer

azureFoundry/HuggingFace/facebook-dinov2-large-imagenet1k-1-layer@1

`facebook/dinov2-large-imagenet1k-1-layer` powered by Hugging Face Inference Toolkit - [Original Model Card](https://huggingface.co/facebook/dinov2-large-imagenet1k-1-layer) - [`image-classification` Task on Hugging Face](https://huggingface.co/tasks/image-classification) ### S

facebook/dinov2-small-imagenet1k-1-layer

azureFoundry/HuggingFace/facebook-dinov2-small-imagenet1k-1-layer@2

`facebook/dinov2-small-imagenet1k-1-layer` powered by Hugging Face Inference Toolkit - [Original Model Card](https://huggingface.co/facebook/dinov2-small-imagenet1k-1-layer) - [`image-classification` Task on Hugging Face](https://huggingface.co/tasks/image-classification) ### S

facebook/dpr-question_encoder-multiset-base

azureFoundry/HuggingFace/facebook-dpr-question-encoder-multiset-base@1

`facebook/dpr-question_encoder-multiset-base` powered by Hugging Face Inference Toolkit - [Original Model Card](https://huggingface.co/facebook/dpr-question_encoder-multiset-base) - [`feature-extraction` Task on Hugging Face](https://huggingface.co/tasks/feature-extraction) ###

Input modalities
text
Output modalities
embeddings
Capabilities
embeddings

facebook/dpr-question_encoder-single-nq-base

azureFoundry/HuggingFace/facebook-dpr-question-encoder-single-nq-base@1

`facebook/dpr-question_encoder-single-nq-base` powered by Hugging Face Inference Toolkit - [Original Model Card](https://huggingface.co/facebook/dpr-question_encoder-single-nq-base) - [`feature-extraction` Task on Hugging Face](https://huggingface.co/tasks/feature-extraction) #

Input modalities
text
Output modalities
embeddings
Capabilities
embeddings

facebook/dragon-plus-context-encoder

azureFoundry/HuggingFace/facebook-dragon-plus-context-encoder@2

`facebook/dragon-plus-context-encoder` powered by Hugging Face Inference Toolkit - [Original Model Card](https://huggingface.co/facebook/dragon-plus-context-encoder) - [`feature-extraction` Task on Hugging Face](https://huggingface.co/tasks/feature-extraction) ### Send Request

Input modalities
text
Output modalities
embeddings
Capabilities
embeddings

facebook/dragon-plus-query-encoder

azureFoundry/HuggingFace/facebook-dragon-plus-query-encoder@1

`facebook/dragon-plus-query-encoder` powered by Hugging Face Inference Toolkit - [Original Model Card](https://huggingface.co/facebook/dragon-plus-query-encoder) - [`feature-extraction` Task on Hugging Face](https://huggingface.co/tasks/feature-extraction) ### Send Request You

Input modalities
text
Output modalities
embeddings
Capabilities
embeddings

facebook/dragon-roberta-query-encoder

azureFoundry/HuggingFace/facebook-dragon-roberta-query-encoder@1

`facebook/dragon-roberta-query-encoder` powered by Text Embeddings Inference (TEI) - [Original Model Card](https://huggingface.co/facebook/dragon-roberta-query-encoder) - [Text Embeddings Inference Documentation](https://huggingface.co/docs/text-embeddings-inference) ### Send R

Input modalities
text
Output modalities
embeddings
Capabilities
embeddings

facebook/encodec_24khz

azureFoundry/HuggingFace/facebook-encodec-24khz@3

`facebook/encodec_24khz` powered by Hugging Face Inference Toolkit - [Original Model Card](https://huggingface.co/facebook/encodec_24khz) - [`feature-extraction` Task on Hugging Face](https://huggingface.co/tasks/feature-extraction) ### Send Request You can use cURL or any RES

Input modalities
text
Output modalities
embeddings
Capabilities
embeddings

Benchmarks

  • MTEB: 26.315%

facebook/encodec_32khz

azureFoundry/HuggingFace/facebook-encodec-32khz@2

`facebook/encodec_32khz` powered by Hugging Face Inference Toolkit - [Original Model Card](https://huggingface.co/facebook/encodec_32khz) - [`feature-extraction` Task on Hugging Face](https://huggingface.co/tasks/feature-extraction) ### Send Request You can use cURL or any RES

Input modalities
text
Output modalities
embeddings
Capabilities
embeddings

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace