Sentence Similarity
ONNX
Safetensors
sentence-transformers
English
code
PyLate
modernbert
ColBERT
feature-extraction
Generated from Trainer
dataset_size:21502474
loss:CachedContrastive
embeddings
retrieval
code search
Eval Results (legacy)
text-embeddings-inference
🇪🇺 Region: EU
Instructions to use lightonai/LateOn-Code-pretrain with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use lightonai/LateOn-Code-pretrain 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="lightonai/LateOn-Code-pretrain") queries_emb = model.encode(queries, is_query=True) docs_emb = model.encode(documents, is_query=False) - Notebooks
- Google Colab
- Kaggle
Download model.onnx from lightonai/LateOn-Code-pretrain: direct link, hf CLI and curl.
- Browser
- Download file 597 MB
-
https://huggingface.co/lightonai/LateOn-Code-pretrain/resolve/main/model.onnx
- Command line
-
hf download hf://lightonai/LateOn-Code-pretrain/model.onnx
-
curl -L -o model.onnx https://huggingface.co/lightonai/LateOn-Code-pretrain/resolve/main/model.onnx
597 MB
- Xet hash:
- 213228d214699d1360239e90ec69a03cf5a90ca933954589bdd2fbb731396f9b
- Size of remote file:
- 597 MB
- SHA256:
- 5ff754ace77c6919ef2bff3bd81d630b61c909a4d5247ac369edec065293b8b0
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.