turkish-embedding-model

This is a sentence-transformers model finetuned from dbmdz/bert-base-turkish-uncased on the cleaned_turkish_embedding_model_training_data_colab dataset. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more. - **Model Type:** Sentence Transformer - **Base model:** dbmdz/bert-base-turkish-uncased - **Maximum Sequence Length:** 512 tokens - **Output Dimensionality:** 768 dimensions - **Similarity Function:** Cosine Similarity - **Training Dataset:** - cleaned_turkish_embedding_model_training_data_colab - **Documentation:** Sentence Transformers Documentation - **Repository:** Sentence Transformers on GitHub - **Hugging Face:** Sentence Transformers on Hugging Face

번역 준비 중입니다. 원문을 표시합니다.