Sentence Similarity
sentence-transformers
Safetensors
Turkish
gemma3_text
feature-extraction
semantic-search
information-retrieval
turkish
retrieval
distillation
werea
text-embeddings-inference
Instructions to use Werea-co/DUSUNEN-Rota-270M-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use Werea-co/DUSUNEN-Rota-270M-v3 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("Werea-co/DUSUNEN-Rota-270M-v3") 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] - Notebooks
- Google Colab
- Kaggle
Download train-manifest.json from Werea-co/DUSUNEN-Rota-270M-v3: direct link, hf CLI and curl.
- Browser
- Download file 218 Bytes
-
https://huggingface.co/Werea-co/DUSUNEN-Rota-270M-v3/resolve/main/train-manifest.json
- Command line
-
hf download hf://Werea-co/DUSUNEN-Rota-270M-v3/train-manifest.json
-
curl -L -o train-manifest.json https://huggingface.co/Werea-co/DUSUNEN-Rota-270M-v3/resolve/main/train-manifest.json
218 Bytes
| { | |
| "base": "microsoft/harrier-oss-v1-270m", | |
| "records": 308487, | |
| "steps": 30848, | |
| "epochs": 2, | |
| "lr": 3e-05, | |
| "batch": 20, | |
| "neg_per": 4, | |
| "loss": "in-batch InfoNCE + 0.1*marginMSE(E5-large)", | |
| "data": "NATURAL only" | |
| } |