Instructions to use DKYoon/mt5-base-lm-adapt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DKYoon/mt5-base-lm-adapt with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("DKYoon/mt5-base-lm-adapt") model = AutoModelForSeq2SeqLM.from_pretrained("DKYoon/mt5-base-lm-adapt", device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from DKYoon/mt5-base-lm-adapt: direct link, hf CLI and curl.
- Browser
- Download file 468 Bytes
-
https://huggingface.co/DKYoon/mt5-base-lm-adapt/resolve/main/README.md
- Command line
-
hf download hf://DKYoon/mt5-base-lm-adapt/README.md
-
curl -L -o README.md https://huggingface.co/DKYoon/mt5-base-lm-adapt/resolve/main/README.md
468 Bytes
metadata
license: apache-2.0
🤗 Language model initialized from mT5 and trained for an additional 100K steps on the Prefix LM objective using mC4 data.
Paper: Overcoming Catastrophic Forgetting in Zero-Shot Cross-Lingual Generation
Authors: Tu Vu, Aditya Barua, Brian Lester, Daniel Cer, Mohit Iyyer, Noah Constant
PyTorch port of the original Flax checkpoint at Google/T5X repository.