How to use ironbcc/Qwen3-Embedding-4B-NVFP4 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="ironbcc/Qwen3-Embedding-4B-NVFP4")
# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("ironbcc/Qwen3-Embedding-4B-NVFP4") model = AutoModelForCausalLM.from_pretrained("ironbcc/Qwen3-Embedding-4B-NVFP4", device_map="auto")
