Text Ranking
Transformers
Safetensors
MLX
multilingual
qwen3
feature-extraction
reranker
custom_code
Instructions to use mlx-community/jina-reranker-v3-4bit-mxfp4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mlx-community/jina-reranker-v3-4bit-mxfp4 with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("mlx-community/jina-reranker-v3-4bit-mxfp4", trust_remote_code=True) model = AutoModel.from_pretrained("mlx-community/jina-reranker-v3-4bit-mxfp4", trust_remote_code=True) - MLX
How to use mlx-community/jina-reranker-v3-4bit-mxfp4 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir jina-reranker-v3-4bit-mxfp4 mlx-community/jina-reranker-v3-4bit-mxfp4
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
mlx-community/jina-reranker-v3-4bit-mxfp4
The Model mlx-community/jina-reranker-v3-4bit-mxfp4 was converted to MLX format from jinaai/jina-reranker-v3 using mlx-embeddings version 0.0.3.
Use with mlx
pip install mlx-embeddings
from mlx_embeddings import load, generate
import mlx.core as mx
model, tokenizer = load("mlx-community/jina-reranker-v3-4bit-mxfp4")
# For text embeddings
output = generate(model, processor, texts=["I like grapes", "I like fruits"])
embeddings = output.text_embeds # Normalized embeddings
# Compute dot product between normalized embeddings
similarity_matrix = mx.matmul(embeddings, embeddings.T)
print("Similarity matrix between texts:")
print(similarity_matrix)
- Downloads last month
- 153
Hardware compatibility
Log In to add your hardware
Quantized
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐ Ask for provider support