Sentence Similarity
sentence-transformers
Safetensors
Spanish
bert
public-procurement
semantic-search
cpv
text-embeddings-inference
Instructions to use hsilvosa/openplacsp-e5-small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use hsilvosa/openplacsp-e5-small with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("hsilvosa/openplacsp-e5-small") sentences = [ "Esa es una persona feliz", "Ese es un perro feliz", "Esa es una persona muy feliz", "Hoy es un día soleado" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
| language: | |
| - es | |
| license: mit | |
| datasets: | |
| - hsilvosa/openplacsp | |
| library_name: sentence-transformers | |
| pipeline_tag: sentence-similarity | |
| tags: | |
| - public-procurement | |
| - semantic-search | |
| - cpv | |
| base_model: intfloat/multilingual-e5-small | |
| # Embeddings for Spanish public procurement | |
| A semantic encoder fine-tuned on historical versions of Spanish procurement notices and | |
| text-to-CPV-description pairs. It is intended for search, related-notice retrieval, | |
| version matching, and CPV division retrieval. | |
| It was trained from the | |
| [hsilvosa/openplacsp](https://huggingface.co/datasets/hsilvosa/openplacsp). | |
| ## Temporal evaluation on 2024 | |
| | Task | Metric | Base | Fine-tuned | | |
| |---|---|---:|---:| | |
| | Retrieve another version | Recall@1 | 0.9984 | 0.9982 | | |
| | Retrieve another version | Recall@10 | 1.0000 | 0.9998 | | |
| | Retrieve a CPV division | Recall@1 | 0.1920 | 0.6846 | | |
| | Retrieve a CPV division | Recall@3 | 0.3672 | 0.8550 | | |
| Training only uses notices whose first publication date is no later than 2022. The years | |
| 2023 and 2024 are reserved for validation and testing. Training uses | |
| 150,000 version pairs and | |
| 50,000 text-to-CPV pairs with seed | |
| 20260817. The source snapshot fingerprint is | |
| `fad46713c99abcaa500c7cef9323ae173f8f75c5aca02b299db2d4e96c3ca934` and the model checksum is `e89f3596034c54b46d3959d2c7a33e378c9d67019405c9b6d26e56f207ec01ed`. | |
| ## Usage | |
| ```python | |
| from sentence_transformers import SentenceTransformer | |
| model = SentenceTransformer(".") | |
| queries = model.encode(["query: mantenimiento de aplicaciones"], normalize_embeddings=True) | |
| documents = model.encode(["passage: servicios de desarrollo de software"], normalize_embeddings=True) | |
| similarity = model.similarity(queries, documents) | |
| ``` | |
| ## Limitations | |
| The model reflects Spanish administrative language and data published through December | |
| 2024. Similarity does not imply legal identity, irregularity, or contractual equivalence. | |
| CPV descriptions are short and some divisions have relatively few examples. | |