Model Details
Full Model IDcross-encoder/ms-marco-MiniLM-L4-v2
Pipeline / Tasktext-ranking
Librarysentence-transformers
Downloads (all-time)4.9M
Likes31
Last Modified8/29/2025
Author / Orgcross-encoder
PrivateNo — public
⚡ Quick Usage (Python)
Using the 🤗 Transformers library. Install with pip install transformers
from transformers import pipeline
# Load the model
pipe = pipeline("text-ranking", model="cross-encoder/ms-marco-MiniLM-L4-v2")
# Run inference
result = pipe("Your input here")
print(result)🏷️ Tags
sentence-transformerspytorchjaxonnxsafetensorsopenvinoberttext-classificationtransformerstext-rankingendataset:sentence-transformers/msmarcobase_model:cross-encoder/ms-marco-MiniLM-L12-v2base_model:quantized:cross-encoder/ms-marco-MiniLM-L12-v2license:apache-2.0text-embeddings-inferenceendpoints_compatibleregion:us
More text-ranking Models
See all →🚀 Use This Model
Access model files, inference API, and full documentation on Hugging Face.
Open on Hugging Face →Browse Model Files ↗← Browse All Models🤖 Task: text-ranking
This model is designed for the text-ranking task. Explore more models for this use case.
All text-ranking Models →📊 Popularity
⬇ Downloads4.9M
❤️ Community Likes31
🛠️ Requirements
- →Install: pip install sentence-transformers
- →Python 3.8+ recommended for Transformers.
- →GPU (CUDA) speeds up inference significantly.
- →Use model.half() for fp16 on limited VRAM.