Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

MBZUAI
/
Omni-Embed-Mini-2.3B

Feature Extraction
Transformers
Safetensors
English
omni_embed
embeddings
multimodal
omni-modal
retrieval
sentence-similarity
audio
speech
image
video
visual-document-retrieval
matryoshka
custom_code
Model card Files Files and versions
xet
Community

Instructions to use MBZUAI/Omni-Embed-Mini-2.3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use MBZUAI/Omni-Embed-Mini-2.3B with Transformers:

    # Use a pipeline as a high-level helper
    from transformers import pipeline
    
    pipe = pipeline("feature-extraction", model="MBZUAI/Omni-Embed-Mini-2.3B", trust_remote_code=True)
    # pip install -U transformers accelerate
    # Load model directly
    from transformers import AutoModel
    model = AutoModel.from_pretrained("MBZUAI/Omni-Embed-Mini-2.3B", trust_remote_code=True, device_map="auto")
  • Notebooks
  • Google Colab
  • Kaggle

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

Gated model
You can list files but not access them

Preview of files found in this repository
  • backbone
    v1: paper release about 1 month ago
  • .gitattributes
    1.57 kB
    v1: paper release about 1 month ago
  • README.md
    5.81 kB
    Clean remote-code comments, update model card and citation 5 days ago
  • chat_template.jinja
    5.52 kB
    v1: paper release about 1 month ago
  • config.json
    677 Bytes
    v1: paper release about 1 month ago
  • configuration_omni_embed.py
    1.24 kB
    v1: paper release about 1 month ago
  • dasheng_encoder.pt
    342 MB
    xet
    v1: paper release about 1 month ago
  • modeling_omni_embed.py
    38.7 kB
    Clean remote-code comments, update model card and citation 5 days ago
  • processing_omni_embed.py
    24.4 kB
    Clean remote-code comments, update model card and citation 5 days ago
  • processor_config.json
    334 Bytes
    v1: paper release about 1 month ago
  • projector_weights.pt
    558 MB
    xet
    v1: paper release about 1 month ago
  • tokenizer.json
    11.4 MB
    xet
    v1: paper release about 1 month ago
  • tokenizer_config.json
    446 Bytes
    v1: paper release about 1 month ago
  • whisper_encoder.pt
    353 MB
    xet
    v1: paper release about 1 month ago