Text Classification
Safetensors
MLX
multilingual
mlx-embeddings
qwen3
reranker
apple-silicon
fp16
cross-encoder
Instructions to use bsisduck/Qwen3-Reranker-8B-fp16-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use bsisduck/Qwen3-Reranker-8B-fp16-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Qwen3-Reranker-8B-fp16-mlx bsisduck/Qwen3-Reranker-8B-fp16-mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
File size: 294 Bytes
71f07c4 | 1 2 3 4 5 6 7 8 9 10 11 | {
"__version__": {
"sentence_transformers": "5.4.0"
},
"activation_fn": "torch.nn.modules.linear.Identity",
"default_prompt_name": "query",
"model_type": "CrossEncoder",
"prompts": {
"query": "Given a web search query, retrieve relevant passages that answer the query"
}
} |