How to use gsjang/kepri-embedding with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="gsjang/kepri-embedding")
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("gsjang/kepri-embedding") model = AutoModel.from_pretrained("gsjang/kepri-embedding", device_map="auto")
https://huggingface.co/gsjang/kepri-embedding/resolve/main/tokenizer.json
hf download hf://gsjang/kepri-embedding/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/gsjang/kepri-embedding/resolve/main/tokenizer.json
