metadata
library_name: zip2zip
license: mit
pipeline_tag: text-generation
base_model: microsoft/Phi-3-medium-4k-instruct
tags:
- zip2zip
- zip2zip++
- adaptive-tokenization
zip2zip-pp-Phi-3-medium-4k-instruct
Zip2Zip++ checkpoint based on microsoft/Phi-3-medium-4k-instruct (training step
8000). The repository keeps the original training checkpoint on main and
the user-facing, self-contained inference export on hf.
Usage
pip install "zip2zip>=0.2.0"
from zip2zip import Zip2ZipModel, Zip2ZipTokenizer
repo_id = "epfl-dlab/zip2zip-pp-Phi-3-medium-4k-instruct"
tokenizer = Zip2ZipTokenizer.from_pretrained(
repo_id, revision="hf"
)
model = Zip2ZipModel.from_pretrained(
repo_id, revision="hf", device_map="auto", dtype="auto"
)
inputs = tokenizer("Hello", return_tensors="pt").to(model.device)
output = model.generate(**inputs, max_new_tokens=100)
print(tokenizer.decode(output[0], skip_special_tokens=True))
Use main only with zip2zip-plus-plus
when resuming training or reproducing the export. It is not a Transformers/zip2zip inference revision.