Instructions to use kuleshov-group/mdlm-owt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kuleshov-group/mdlm-owt with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="kuleshov-group/mdlm-owt", trust_remote_code=True)# Load model directly from transformers import AutoModelForMaskedLM model = AutoModelForMaskedLM.from_pretrained("kuleshov-group/mdlm-owt", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
updated modeling code
#4
by avgJo3 - opened
I created a bucket based on this model repo- it contains updated files (modeling, config) and is now compatible with MPS and CPU-only setups. It does not require to install any dependencies (besides transformers). The modeling.py file is a soft rewrite of the original model but it is still fully compatible with the weights you published, the behavior is identical. LMK if this is useful.