How to use jfkback/hypencoder.8_layer with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="jfkback/hypencoder.8_layer")
# pip install -U transformers accelerate # Load model directly from transformers import HypencoderDualEncoder model = HypencoderDualEncoder.from_pretrained("jfkback/hypencoder.8_layer", device_map="auto")
https://huggingface.co/jfkback/hypencoder.8_layer/resolve/main/tokenizer.json
hf download hf://jfkback/hypencoder.8_layer/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/jfkback/hypencoder.8_layer/resolve/main/tokenizer.json
