Instructions to use McGill-NLP/bge-small-dmr with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use McGill-NLP/bge-small-dmr with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("McGill-NLP/bge-small-dmr") sentences = [ "That is a happy person", "That is a happy dog", "That is a very happy person", "Today is a sunny day" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Transformers
How to use McGill-NLP/bge-small-dmr with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("McGill-NLP/bge-small-dmr", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download 1_Pooling/config.json from McGill-NLP/bge-small-dmr: direct link, hf CLI and curl.
- Browser
- Download file 190 Bytes
-
https://huggingface.co/McGill-NLP/bge-small-dmr/resolve/main/1_Pooling/config.json
- Command line
-
hf download hf://McGill-NLP/bge-small-dmr/1_Pooling/config.json
-
curl -L -o config.json https://huggingface.co/McGill-NLP/bge-small-dmr/resolve/main/1_Pooling/config.json
190 Bytes
- Xet hash:
- 223391095ce06bafe73fead17f4d25e3994eded16a532ff1d3b8bedebea7178f
- Size of remote file:
- 190 Bytes
- SHA256:
- 4be450dde3b0273bb9787637cfbd28fe04a7ba6ab9d36ac48e92b11e350ffc23
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.