Transformers How to use EmbeddedLLM/bge-large-en-v1.5-onnx-o4-gpu with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("feature-extraction", model="EmbeddedLLM/bge-large-en-v1.5-onnx-o4-gpu") # Load model directly
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("EmbeddedLLM/bge-large-en-v1.5-onnx-o4-gpu")
model = AutoModel.from_pretrained("EmbeddedLLM/bge-large-en-v1.5-onnx-o4-gpu", device_map="auto") 
