Feature Extraction
sentence-transformers
Safetensors
Transformers
English
luxical-one
sentence-similarity
luxical
custom_code
Instructions to use DatologyAI/luxical-one with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use DatologyAI/luxical-one with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("DatologyAI/luxical-one", trust_remote_code=True) 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] - Transformers
How to use DatologyAI/luxical-one with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="DatologyAI/luxical-one", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("DatologyAI/luxical-one", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse filesAdd blog post and github links
README.md
CHANGED
|
@@ -10,6 +10,10 @@ license: apache-2.0
|
|
| 10 |
|
| 11 |
Luxical-One is a small lexical-dense text embedding model distilled from [`Snowflake/snowflake-arctic-embed-m-v2.0`](https://huggingface.co/Snowflake/snowflake-arctic-embed-m-v2.0). It is optimized for high-throughput embedding without GPU acceleration, and it is trained for English-language symmetrical full-document text similarity and classification applications.
|
| 12 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
## Quickstart
|
| 14 |
|
| 15 |
Luxical-One includes a basic HuggingFace integration that supports model inference. GPU-based inference is not supported (GPU "acceleration" would not provide a meaningful boost on most systems due to how fast and small the model is anyhow).
|
|
|
|
| 10 |
|
| 11 |
Luxical-One is a small lexical-dense text embedding model distilled from [`Snowflake/snowflake-arctic-embed-m-v2.0`](https://huggingface.co/Snowflake/snowflake-arctic-embed-m-v2.0). It is optimized for high-throughput embedding without GPU acceleration, and it is trained for English-language symmetrical full-document text similarity and classification applications.
|
| 12 |
|
| 13 |
+
Read the full story of Luxical in our [blog post](https://www.datologyai.com/blog/introducing-luxical-embeddings).
|
| 14 |
+
|
| 15 |
+
Want to go deeper with Luxical models? Check out the [repo](https://github.com/datologyai/luxical).
|
| 16 |
+
|
| 17 |
## Quickstart
|
| 18 |
|
| 19 |
Luxical-One includes a basic HuggingFace integration that supports model inference. GPU-based inference is not supported (GPU "acceleration" would not provide a meaningful boost on most systems due to how fast and small the model is anyhow).
|