Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets
  • 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

YCF-AI
/
bge-m3-8bit-MLX

Sentence Similarity
MLX
Safetensors
multilingual
English
Chinese
xlm-roberta
mlx-embeddings
omlx
apple-silicon
m1
bge-m3
embeddings
feature-extraction
retrieval
rag
8-bit precision
Model card Files Files and versions
xet
Community

Instructions to use YCF-AI/bge-m3-8bit-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • MLX

    How to use YCF-AI/bge-m3-8bit-MLX with MLX:

    # Download the model from the Hub
    pip install huggingface_hub[hf_xet]
    
    hf download YCF-AI/bge-m3-8bit-MLX --local-dir bge-m3-8bit-MLX
  • Notebooks
  • Google Colab
  • Kaggle
  • Local Apps Settings
  • LM Studio
  • Atomic Chat
bge-m3-8bit-MLX / recipe
6.16 kB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 1 commit
YCF-AI's picture
YCF-AI
BAAI/bge-m3 in 8-bit (gs64), tuned for oMLX: weights, config, tokenizer, recipe (byte-reproducible), settings entry, bilingual card with figures
de4cdde verified 19 days ago
  • bin2st.py
    3.43 kB
    BAAI/bge-m3 in 8-bit (gs64), tuned for oMLX: weights, config, tokenizer, recipe (byte-reproducible), settings entry, bilingual card with figures 19 days ago
  • make_bgem3_q8.py
    2.73 kB
    BAAI/bge-m3 in 8-bit (gs64), tuned for oMLX: weights, config, tokenizer, recipe (byte-reproducible), settings entry, bilingual card with figures 19 days ago