Instructions to use AutoDataBench/Retrieval-resources with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use AutoDataBench/Retrieval-resources with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("AutoDataBench/Retrieval-resources") sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Notebooks
- Google Colab
- Kaggle
Download data/retrieval_v1/train.jsonl from AutoDataBench/Retrieval-resources: direct link, hf CLI and curl.
- Browser
- Download file 527 MB
-
https://huggingface.co/AutoDataBench/Retrieval-resources/resolve/main/data/retrieval_v1/train.jsonl
- Command line
-
hf download hf://AutoDataBench/Retrieval-resources/data/retrieval_v1/train.jsonl
-
curl -L -o train.jsonl https://huggingface.co/AutoDataBench/Retrieval-resources/resolve/main/data/retrieval_v1/train.jsonl
527 MB
- Xet hash:
- 3fd718beca3e4a7643a6f92956e3cee6505cf415df9587087ec43ffec864e725
- Size of remote file:
- 527 MB
- SHA256:
- 193d85660e80ed266376378655192a86655977bc46aaaf0980f7d28b1f29a3ab
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.