How to use KoliaNik/Qwen3-Reranker-4B-NVFP4 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("KoliaNik/Qwen3-Reranker-4B-NVFP4") model = AutoModelForCausalLM.from_pretrained("KoliaNik/Qwen3-Reranker-4B-NVFP4", device_map="auto")
