Sentence Similarity
sentence-transformers
Safetensors
Transformers
English
atto
feature-extraction
ColBERT
PyLate
custom_code
Instructions to use NeuML/colbert-atto-25m-384d with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use NeuML/colbert-atto-25m-384d with sentence-transformers:
from pylate import models queries = [ "Which planet is known as the Red Planet?", "What is the largest planet in our solar system?", ] documents = [ ["Mars is the Red Planet.", "Venus is Earth's twin."], ["Jupiter is the largest planet.", "Saturn has rings."], ] model = models.ColBERT(model_name_or_path="NeuML/colbert-atto-25m-384d") queries_emb = model.encode(queries, is_query=True) docs_emb = model.encode(documents, is_query=False) - Transformers
How to use NeuML/colbert-atto-25m-384d with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("NeuML/colbert-atto-25m-384d", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer.json from NeuML/colbert-atto-25m-384d: direct link, hf CLI and curl.
- Browser
- Download file 701 kB
-
https://huggingface.co/NeuML/colbert-atto-25m-384d/resolve/main/tokenizer.json
- Command line
-
hf download hf://NeuML/colbert-atto-25m-384d/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/NeuML/colbert-atto-25m-384d/resolve/main/tokenizer.json
701 kB
File too large to display, you can check the raw version instead.