Sentence Similarity
sentence-transformers
ONNX
Safetensors
embedding_gemma2
feature-extraction
dense
Generated from Trainer
dataset_size:50
loss:MultipleNegativesRankingLoss
Instructions to use Erog0291/stew-embedding-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use Erog0291/stew-embedding-v2 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("Erog0291/stew-embedding-v2") sentences = [ "task: search result | query: Upscale this image for me", "title: code_app | text: Write and run code in a sandbox; build simple apps and games. Best for building a game or writing a script.", "title: image_edit | text: Edit, upscale or restyle images. Best for cleaning up a photo or removing a background.", "title: code_app | text: Write and run code in a sandbox; build simple apps and games. Best for building a game or writing a script." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
Download 2_Normalize/config.json from Erog0291/stew-embedding-v2: direct link, hf CLI and curl.
- Browser
- Download file 97 Bytes
-
https://huggingface.co/Erog0291/stew-embedding-v2/resolve/main/2_Normalize/config.json
- Command line
-
hf download hf://Erog0291/stew-embedding-v2/2_Normalize/config.json
-
curl -L -o config.json https://huggingface.co/Erog0291/stew-embedding-v2/resolve/main/2_Normalize/config.json
97 Bytes
| { | |
| "module_input_name": "sentence_embedding", | |
| "module_output_name": "sentence_embedding" | |
| } |