How to use EmbeddedLLM/bge-reranker-large-onnx-o4-gpu with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("EmbeddedLLM/bge-reranker-large-onnx-o4-gpu") model = AutoModelForSequenceClassification.from_pretrained("EmbeddedLLM/bge-reranker-large-onnx-o4-gpu", device_map="auto")
