Sentence Similarity
sentence-transformers
Safetensors
English
modernbert
colbert
late-interaction
retrieval
pylate
multi-vector
text-embeddings-inference
Instructions to use chungimungi/GLInt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use chungimungi/GLInt with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("chungimungi/GLInt") 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] - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -15,7 +15,7 @@ pipeline_tag: sentence-similarity
|
|
| 15 |
|
| 16 |
# GLInt
|
| 17 |
|
| 18 |
-
GLINT is a 149M-parameter English late-interaction retriever built from
|
| 19 |
[LateOn-unsupervised](https://huggingface.co/lightonai/LateOn-unsupervised). It retains
|
| 20 |
128-dimensional token embeddings and uses MaxSim retrieval with 32 query tokens and 300
|
| 21 |
document tokens.
|
|
|
|
| 15 |
|
| 16 |
# GLInt
|
| 17 |
|
| 18 |
+
GLINT is a SOTA 149M-parameter English late-interaction retriever built from
|
| 19 |
[LateOn-unsupervised](https://huggingface.co/lightonai/LateOn-unsupervised). It retains
|
| 20 |
128-dimensional token embeddings and uses MaxSim retrieval with 32 query tokens and 300
|
| 21 |
document tokens.
|