Sentence Similarity
Model2Vec
Safetensors
sentence-transformers
Ukrainian
static-embeddings
embeddings
retrieval
ukrainian
Instructions to use SyntaxSpirits/ukr-static-m3-64k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Model2Vec
How to use SyntaxSpirits/ukr-static-m3-64k with Model2Vec:
from model2vec import StaticModel model = StaticModel.from_pretrained("SyntaxSpirits/ukr-static-m3-64k") embeddings = model.encode(["It's dangerous to go alone!", "It's a secret to everybody."]) print(embeddings.shape) - sentence-transformers
How to use SyntaxSpirits/ukr-static-m3-64k with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("SyntaxSpirits/ukr-static-m3-64k") 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
Download config.json from SyntaxSpirits/ukr-static-m3-64k: direct link, hf CLI and curl.
- Browser
- Download file 508 Bytes
-
https://huggingface.co/SyntaxSpirits/ukr-static-m3-64k/resolve/main/config.json
- Command line
-
hf download hf://SyntaxSpirits/ukr-static-m3-64k/config.json
-
curl -L -o config.json https://huggingface.co/SyntaxSpirits/ukr-static-m3-64k/resolve/main/config.json
508 Bytes
| { | |
| "model_type": "model2vec", | |
| "architectures": [ | |
| "StaticModel" | |
| ], | |
| "tokenizer_name": "BAAI/bge-m3", | |
| "apply_pca": 256, | |
| "sif_coefficient": 0.0001, | |
| "hidden_dim": 256, | |
| "seq_length": 1000000, | |
| "normalize": true, | |
| "pooling": "mean", | |
| "n_words": 32000, | |
| "max_length": 512, | |
| "embedding_dtype": "float16", | |
| "tokenlearn": { | |
| "samples": 119430, | |
| "val": 10000, | |
| "lr": 0.001, | |
| "batch": 256, | |
| "best_val": 0.2401214860379696 | |
| } | |
| } |