Sentence Similarity
sentence-transformers
Safetensors
Turkish
new
feature-extraction
Generated from Trainer
dataset_size:482091
loss:MatryoshkaLoss
loss:MultipleNegativesRankingLoss
loss:CoSENTLoss
custom_code
Eval Results (legacy)
text-embeddings-inference
Instructions to use newmindai/TurkEmbed4STS with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use newmindai/TurkEmbed4STS with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("newmindai/TurkEmbed4STS", trust_remote_code=True) sentences = [ "Ya da dışarı çıkıp yürü ya da biraz koşun. Bunu düzenli olarak yapmıyorum ama Washington bunu yapmak için harika bir yer.", "“Washington's yürüyüş ya da koşu için harika bir yer.”", "H-2A uzaylılar Amerika Birleşik Devletleri'nde zaman kısa süreleri var.", "“Washington'da düzenli olarak yürüyüşe ya da koşuya çıkıyorum.”" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
| { | |
| "added_tokens_decoder": { | |
| "0": { | |
| "content": "<s>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "1": { | |
| "content": "<pad>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "2": { | |
| "content": "</s>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "3": { | |
| "content": "<unk>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "250001": { | |
| "content": "<mask>", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| } | |
| }, | |
| "bos_token": "<s>", | |
| "clean_up_tokenization_spaces": true, | |
| "cls_token": "<s>", | |
| "eos_token": "</s>", | |
| "extra_special_tokens": {}, | |
| "mask_token": "<mask>", | |
| "model_max_length": 8192, | |
| "pad_token": "<pad>", | |
| "sep_token": "</s>", | |
| "tokenizer_class": "XLMRobertaTokenizer", | |
| "unk_token": "<unk>" | |
| } | |