Sentence Similarity
sentence-transformers
Safetensors
Turkish
xlm-roberta
turkish
embeddings
retrieval
distillation
text-embeddings-inference
Instructions to use fredoline005/ajan-embed-q with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use fredoline005/ajan-embed-q with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("fredoline005/ajan-embed-q") 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
Commit History
26 days ago
-
Ajanlar is available for acquisition
Verified signatureDomain, model, recipe and brand offered together. Placed below the technical content, not as a banner, and states explicitly that the weights stay Apache-2.0, up and free regardless of ownership, so current users are not driven off.8097882 -
Limitations: the undistilled-e5-base ablation has been run, it is in the table
Verified signatureThe limitations section still said the ablation was not yet run while the benchmark table above it reported that ablation. Corrected, and states plainly that the ablation beats this model on the 4-task average and loses on retrieval.6bf7ea8
27 days ago
-
Add maker, Ajanlar link and contact
Verified signature76a8dc6
-
Honest 4-task benchmark + ablation
Verified signaturedbe3c5a -
Link GitHub repo
Verified signature09fa1d4
-
Add model card with measured Turkish benchmark
Verified signatureb99f456 -
Add ajan-embed-q: bge-m3-distilled Turkish embeddings
Verified signature4b39d55 -
initial commit
Verified signature264c4ad