Hugging Face's logo

vllm-sr
/
multi-modal-embed-small

Sentence Similarity
Transformers
ONNX
Safetensors
sentence-transformers
English
multimodal
embeddings
image-text
audio-text
retrieval
2DMSE
matryoshka
Eval Results (legacy)
Model card Files
xet
 Community
multi-modal-embed-small / README.md

Commit History

  1. Update Hugging Face org references: llm-semantic-router → vllm-sr

    Xunzhuo
    Verified signature
    cba24df

  1. Fix standalone model loading code - verified to work

    HuaminChen
    Verified signature
    82e6778

  2. Make README fully standalone - no external repo needed

    HuaminChen
    Verified signature
    e737256

  3. Add standalone loading option using only transformers

    HuaminChen
    Verified signature
    6445452

  4. Fix usage instructions with proper installation steps

    HuaminChen
    Verified signature
    56f3801

  5. Fix total parameter count: ~120M not ~250M

    HuaminChen
    Verified signature
    4817d62

  6. Document both model.pt and model.safetensors formats

    HuaminChen
    Verified signature
    818f7d0

  7. Fix loading example to match checkpoint format

    HuaminChen
    Verified signature
    75eae3f

  8. Fix Whisper-tiny encoder param count (8M, not 39M)

    HuaminChen
    Verified signature
    b4136e7

  9. Update model with audio-text alignment (Stage 5: R@1=36.38%)

    HuaminChen
    Verified signature
    e6b2249

  10. Add verified dataset sources with paper citations

    HuaminChen
    Verified signature
    f241f4b

  11. Add audio training roadmap to model card

    HuaminChen
    Verified signature
    f2cea71

  12. Upload multi-modal-embed-small Stage 2 model

    HuaminChen
    Verified signature
    a82f367