Sentence Similarity
sentence-transformers
PyTorch
Safetensors
Transformers
new
feature-extraction
mteb
custom_code
Eval Results (legacy)
text-embeddings-inference
Instructions to use NovaSearch/stella_en_400M_v5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use NovaSearch/stella_en_400M_v5 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("NovaSearch/stella_en_400M_v5", trust_remote_code=True) 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] - Transformers
How to use NovaSearch/stella_en_400M_v5 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("NovaSearch/stella_en_400M_v5", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md (#13)
Browse files- Update README.md (577dc280bd0e9626df83c7a6d895d247adf6d7dc)
Co-authored-by: Jiahuan Luo <jiahaunluo@users.noreply.huggingface.co>
README.md
CHANGED
|
@@ -5455,7 +5455,7 @@ Prompt of s2s task(e.g. semantic textual similarity task):
|
|
| 5455 |
Instruct: Retrieve semantically similar text.\nQuery: {query}
|
| 5456 |
```
|
| 5457 |
|
| 5458 |
-
The models are finally trained by [MRL](
|
| 5459 |
1024, 2048, 4096, 6144 and 8192.
|
| 5460 |
|
| 5461 |
The higher the dimension, the better the performance.
|
|
|
|
| 5455 |
Instruct: Retrieve semantically similar text.\nQuery: {query}
|
| 5456 |
```
|
| 5457 |
|
| 5458 |
+
The models are finally trained by [MRL](https://arxiv.org/abs/2205.13147), so they have multiple dimensions: 512, 768,
|
| 5459 |
1024, 2048, 4096, 6144 and 8192.
|
| 5460 |
|
| 5461 |
The higher the dimension, the better the performance.
|