How to use EmbeddedLLM/bge-reranker-base-onnx-o3-cpu with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("EmbeddedLLM/bge-reranker-base-onnx-o3-cpu") model = AutoModelForSequenceClassification.from_pretrained("EmbeddedLLM/bge-reranker-base-onnx-o3-cpu")
