Instructions to use bertin-project/bertin-base-stepwise with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bertin-project/bertin-base-stepwise with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="bertin-project/bertin-base-stepwise")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("bertin-project/bertin-base-stepwise") model = AutoModelForMaskedLM.from_pretrained("bertin-project/bertin-base-stepwise", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download outputs/optimizer_state.msgpack from bertin-project/bertin-base-stepwise: direct link, hf CLI and curl.
- Browser
- Download file 500 MB
-
https://huggingface.co/bertin-project/bertin-base-stepwise/resolve/main/outputs/optimizer_state.msgpack
- Command line
-
hf download hf://bertin-project/bertin-base-stepwise/outputs/optimizer_state.msgpack
-
curl -L -o optimizer_state.msgpack https://huggingface.co/bertin-project/bertin-base-stepwise/resolve/main/outputs/optimizer_state.msgpack
500 MB
- Xet hash:
- f0cf14d226c86f822878335b562070c7261144f1f9c1b7e0b576c217b4dffc77
- Size of remote file:
- 500 MB
- SHA256:
- 1169479fbf819cbca67bb8fbef0922b31789415f0580a4c19ea192da62b69d63
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.