zip2zip: Inference-Time Adaptive Vocabularies for Language Models via Token Compression
Paper โข 2506.01084 โข Published โข 6
How to use nathanrchn/zip2zip-test with Transformers:
# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("nathanrchn/zip2zip-test", device_map="auto")Base model
microsoft/Phi-3.5-mini-instruct