Instructions to use mrfoxv/snowflake_model2vec with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Model2Vec
How to use mrfoxv/snowflake_model2vec with Model2Vec:
from model2vec import StaticModel model = StaticModel.from_pretrained("mrfoxv/snowflake_model2vec") - sentence-transformers
How to use mrfoxv/snowflake_model2vec with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("mrfoxv/snowflake_model2vec") 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
| # script.py | |
| from model2vec.distill import distill | |
| import os | |
| # Set local base model path (already cloned) | |
| LOCAL_MODEL_PATH = os.path.join(os.path.dirname(__file__), "snowflake-arctic-embed-xs") | |
| OUTPUT_PATH = os.path.dirname(os.path.abspath(__file__)) | |
| PCA_DIMS = 256 # You can tweak this | |
| print("Distilling Model2Vec from local model...") | |
| # Distill model | |
| model = distill(model_name=LOCAL_MODEL_PATH, pca_dims=PCA_DIMS) | |
| print("Saving distilled model to:", OUTPUT_PATH) | |
| model.save_pretrained(OUTPUT_PATH) | |
| print("✅ Done. Distilled model saved to", OUTPUT_PATH) |