Instructions to use huggingface-mic/modernbert-embed-base-mic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use huggingface-mic/modernbert-embed-base-mic with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("huggingface-mic/modernbert-embed-base-mic") 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 integrations/sentence_transformers/usage.md from huggingface-mic/modernbert-embed-base-mic: direct link, hf CLI and curl.
- Browser
- Download file 2.59 kB
-
https://huggingface.co/huggingface-mic/modernbert-embed-base-mic/resolve/main/integrations/sentence_transformers/usage.md
- Command line
-
hf download hf://huggingface-mic/modernbert-embed-base-mic/integrations/sentence_transformers/usage.md
-
curl -L -o usage.md https://huggingface.co/huggingface-mic/modernbert-embed-base-mic/resolve/main/integrations/sentence_transformers/usage.md
2.59 kB
| # SentenceTransformer: encoding and scoring | |
| Run the public Sentence Transformers API with a small, fixed retrieval example. | |
| ```py runnable:retrieval | |
| import torch | |
| from sentence_transformers import SentenceTransformer | |
| import json # doc-builder: hide | |
| import os # doc-builder: hide | |
| model_id = 'nomic-ai/modernbert-embed-base' | |
| model_id = os.environ.get('MIC_MODEL', model_id) # doc-builder: hide | |
| revision = os.environ.get('MIC_MODEL_REVISION') or None # doc-builder: hide | |
| variant = json.loads(os.environ.get('MIC_MODEL_KWARGS', '{}')) # doc-builder: hide | |
| torch.manual_seed(0) | |
| device = 'cuda' if torch.cuda.is_available() else 'cpu' | |
| model = SentenceTransformer( | |
| model_id, | |
| device=device, | |
| revision=revision, # doc-builder: hide | |
| model_kwargs=variant, # doc-builder: hide | |
| ) | |
| queries = ['Which planet is known as the Red Planet?', 'Where do penguins live?'] | |
| documents = ["Venus is often called Earth's twin.", 'Mars is known for its reddish appearance and is called the Red Planet.', 'Penguins live in the Southern Hemisphere, including Antarctica.', 'Jupiter is the largest planet in our solar system and has a prominent red spot.'] | |
| query_embeddings = model.encode_query(queries, show_progress_bar=False, convert_to_tensor=True) | |
| document_embeddings = model.encode_document(documents, show_progress_bar=False, convert_to_tensor=True) | |
| scores = model.similarity(query_embeddings, document_embeddings) | |
| assert scores.shape == (2, 4) | |
| assert torch.isfinite(scores).all() | |
| assert torch.isfinite(query_embeddings).all() and torch.isfinite(document_embeddings).all() | |
| assert (query_embeddings[0] - query_embeddings[1]).abs().max() > 0.001 | |
| individual = model.encode_query(queries, batch_size=1, show_progress_bar=False, convert_to_tensor=True) | |
| batch_max_delta = float((query_embeddings - individual).abs().max()) | |
| if query_embeddings.dtype == torch.float32: | |
| torch.testing.assert_close(query_embeddings, individual, atol=1e-4, rtol=1e-4) | |
| if os.environ.get('MIC_RUNNER'): # doc-builder: hide | |
| backbone = next(module for module in model.modules() if isinstance(module, __import__('transformers').PreTrainedModel)) | |
| result = { | |
| 'runtime': {'device': model.device.type, 'dtype': str(next(model.parameters()).dtype).removeprefix('torch.'), 'attn_implementation': backbone.config._attn_implementation}, | |
| 'scores': scores.float().cpu().tolist(), | |
| 'batch_max_delta': batch_max_delta, | |
| 'query_embeddings': query_embeddings.float().cpu().tolist(), | |
| 'document_embeddings': document_embeddings.float().cpu().tolist(), | |
| } | |
| print(json.dumps(result)) | |
| ``` | |