# Load model directly
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("ellenhp/osm2vec-bert-v1")
model = AutoModel.from_pretrained("ellenhp/osm2vec-bert-v1", device_map="auto")Quick Links
osm2vec-bert-v1
This is my first attempt at creating a model to generate vector embeddings of OpenStreetMap elements. It works reasonably well. More info to come probably. :)
Licensing
This model has memorized OpenStreetMap tags and data, and in my opinion as a non-lawyer computer science practitioner, it should be considered a derivative work of OpenStreetMap, so I'm releasing it as ODbL.
This osm2vec weights data is made available under the Open Database License: http://opendatacommons.org/licenses/odbl/1.0/. Any rights in individual contents of the database are licensed under the Database Contents License: http://opendatacommons.org/licenses/dbcl/1.0/
- Downloads last month
- 11
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="ellenhp/osm2vec-bert-v1")