How to use Lipdog/Qwen3-Reranker-4B-mlx-fp16 with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Lipdog/Qwen3-Reranker-4B-mlx-fp16") model = AutoModelForCausalLM.from_pretrained("Lipdog/Qwen3-Reranker-4B-mlx-fp16")
How to use Lipdog/Qwen3-Reranker-4B-mlx-fp16 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Qwen3-Reranker-4B-mlx-fp16 Lipdog/Qwen3-Reranker-4B-mlx-fp16
