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
| { | |
| "_name_or_path": "Alibaba-NLP/gte-multilingual-base", | |
| "architectures": [ | |
| "NewModel" | |
| ], | |
| "attention_probs_dropout_prob": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "Alibaba-NLP/new-impl--configuration.NewConfig", | |
| "AutoModel": "Alibaba-NLP/new-impl--modeling.NewModel", | |
| "AutoModelForMaskedLM": "Alibaba-NLP/new-impl--modeling.NewForMaskedLM", | |
| "AutoModelForMultipleChoice": "Alibaba-NLP/new-impl--modeling.NewForMultipleChoice", | |
| "AutoModelForQuestionAnswering": "Alibaba-NLP/new-impl--modeling.NewForQuestionAnswering", | |
| "AutoModelForSequenceClassification": "Alibaba-NLP/new-impl--modeling.NewForSequenceClassification", | |
| "AutoModelForTokenClassification": "Alibaba-NLP/new-impl--modeling.NewForTokenClassification" | |
| }, | |
| "classifier_dropout": 0.0, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "id2label": { | |
| "0": "LABEL_0" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "label2id": { | |
| "LABEL_0": 0 | |
| }, | |
| "layer_norm_eps": 1e-12, | |
| "layer_norm_type": "layer_norm", | |
| "logn_attention_clip1": false, | |
| "logn_attention_scale": false, | |
| "max_position_embeddings": 8192, | |
| "model_type": "new", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "pack_qkv": true, | |
| "pad_token_id": 1, | |
| "position_embedding_type": "rope", | |
| "rope_scaling": { | |
| "factor": 8.0, | |
| "type": "ntk" | |
| }, | |
| "rope_theta": 20000, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.49.0.dev0", | |
| "type_vocab_size": 1, | |
| "unpad_inputs": false, | |
| "use_memory_efficient_attention": false, | |
| "vocab_size": 250048 | |
| } | |