Sentence Similarity
sentence-transformers
Safetensors
English
qwen3
mathematics
mathlib
lean4
retrieval
contrastive-learning
feature-extraction
loss:CachedMultipleNegativesRankingLoss
text-embeddings-inference
Instructions to use uw-math-ai/MathLeap-Octen-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use uw-math-ai/MathLeap-Octen-8B with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("uw-math-ai/MathLeap-Octen-8B") 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
|
@@ -25,9 +25,6 @@ concepts via multi-view contrastive learning. The goal is to embed
|
|
| 25 |
mathematically equivalent statements close together regardless of the surface
|
| 26 |
language they are written in.
|
| 27 |
|
| 28 |
-
A companion model fine-tuned from the original Qwen3-Embedding-8B under the
|
| 29 |
-
same recipe, [MathLeap-Qwen-8B](https://anonymous-hf.up.railway.app/a/pv25ongyl2qb/ )
|
| 30 |
-
is also released.
|
| 31 |
|
| 32 |
## Usage
|
| 33 |
|
|
|
|
| 25 |
mathematically equivalent statements close together regardless of the surface
|
| 26 |
language they are written in.
|
| 27 |
|
|
|
|
|
|
|
|
|
|
| 28 |
|
| 29 |
## Usage
|
| 30 |
|