Sentence Similarity
sentence-transformers
Safetensors
Turkish
xlm-roberta
feature-extraction
semantic-search
information-retrieval
turkish
matryoshka-embeddings
variable-dimensions
hard-negatives
mrl
Eval Results (legacy)
text-embeddings-inference
Instructions to use GoktugD/DUSUNEN-Atlas-278M-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use GoktugD/DUSUNEN-Atlas-278M-v1 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("GoktugD/DUSUNEN-Atlas-278M-v1") 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
| project_name: DUSUNEN-Atlas-278M-v1 | |
| base_model: intfloat/multilingual-e5-base | |
| base_model_revision: d128750597153bb5987e10b1c3493a34e5a4502a | |
| dataset_id: GoktugD/DUSUNEN-HardNegatives-50K-v1 | |
| seed: 3407 | |
| max_seq_length: 256 | |
| train_rows: 50000 | |
| validation_rows: 2000 | |
| epochs: 1 | |
| learning_rate: 1.0e-5 | |
| warmup_ratio: 0.05 | |
| per_device_batch_size: 8 | |
| gradient_accumulation_steps: 8 | |
| loss_mini_batch_size: 4 | |
| matryoshka_dims: [768, 512, 384, 256, 128, 64] | |
| matryoshka_dims_per_step: 4 | |
| gradient_checkpointing: true | |
| bf16: true | |
| cuda_memory_fraction: 0.50 | |
| step_pause_seconds: 0.75 | |
| eval_steps: 250 | |
| save_steps: 250 | |
| logging_steps: 5 | |