Feature Extraction
sentence-transformers
Safetensors
English
text-embeddings-inference
embeddings
retrieval
matryoshka
lattice
cilow
db-native
claim-aware
Instructions to use GeneralizedLabs/Vinci with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use GeneralizedLabs/Vinci with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("GeneralizedLabs/Vinci") 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
| [ | |
| { | |
| "dataset_id": "vinci-v0-synthetic", | |
| "model_id": "Cilow/Vinci", | |
| "backend": "deterministic", | |
| "dim": 256, | |
| "metrics": { | |
| "recall_at_5": 0.14285714285714285, | |
| "recall_at_10": 0.7142857142857143, | |
| "mrr_at_10": 0.11604308390022676, | |
| "ndcg_at_10": 0.24841329030013304 | |
| }, | |
| "query_count": 7, | |
| "claim_count": 16, | |
| "category_metrics": { | |
| "code": { | |
| "recall_at_5": 0.0, | |
| "recall_at_10": 0.0, | |
| "mrr_at_10": 0.0, | |
| "ndcg_at_10": 0.0 | |
| }, | |
| "correction": { | |
| "recall_at_5": 0.0, | |
| "recall_at_10": 1.0, | |
| "mrr_at_10": 0.125, | |
| "ndcg_at_10": 0.31546487678572877 | |
| }, | |
| "knowledge-update": { | |
| "recall_at_5": 0.0, | |
| "recall_at_10": 1.0, | |
| "mrr_at_10": 0.1, | |
| "ndcg_at_10": 0.2890648263178879 | |
| }, | |
| "numeric-precision": { | |
| "recall_at_5": 0.0, | |
| "recall_at_10": 1.0, | |
| "mrr_at_10": 0.14285714285714285, | |
| "ndcg_at_10": 0.3333333333333333 | |
| }, | |
| "semantic-neighbor": { | |
| "recall_at_5": 1.0, | |
| "recall_at_10": 1.0, | |
| "mrr_at_10": 0.3333333333333333, | |
| "ndcg_at_10": 0.5 | |
| }, | |
| "structured-db-row": { | |
| "recall_at_5": 0.0, | |
| "recall_at_10": 1.0, | |
| "mrr_at_10": 0.1111111111111111, | |
| "ndcg_at_10": 0.3010299956639812 | |
| }, | |
| "tool-trace": { | |
| "recall_at_5": 0.0, | |
| "recall_at_10": 0.0, | |
| "mrr_at_10": 0.0, | |
| "ndcg_at_10": 0.0 | |
| } | |
| }, | |
| "model_family": "vinci", | |
| "pipeline": "Lattice", | |
| "promotion_gate": { | |
| "shadow_only": true, | |
| "requires_voyage_baseline_comparison": true, | |
| "min_stephen_longitudinal_passes": 8, | |
| "eligible_without_baseline": false | |
| } | |
| }, | |
| { | |
| "dataset_id": "vinci-v0-synthetic", | |
| "model_id": "Cilow/Vinci", | |
| "backend": "deterministic", | |
| "dim": 1024, | |
| "metrics": { | |
| "recall_at_5": 0.2857142857142857, | |
| "recall_at_10": 0.7142857142857143, | |
| "mrr_at_10": 0.1261904761904762, | |
| "ndcg_at_10": 0.25812105530341245 | |
| }, | |
| "query_count": 7, | |
| "claim_count": 16, | |
| "category_metrics": { | |
| "code": { | |
| "recall_at_5": 0.0, | |
| "recall_at_10": 0.0, | |
| "mrr_at_10": 0.0, | |
| "ndcg_at_10": 0.0 | |
| }, | |
| "correction": { | |
| "recall_at_5": 1.0, | |
| "recall_at_10": 1.0, | |
| "mrr_at_10": 0.2, | |
| "ndcg_at_10": 0.38685280723454163 | |
| }, | |
| "knowledge-update": { | |
| "recall_at_5": 0.0, | |
| "recall_at_10": 0.0, | |
| "mrr_at_10": 0.0, | |
| "ndcg_at_10": 0.0 | |
| }, | |
| "numeric-precision": { | |
| "recall_at_5": 1.0, | |
| "recall_at_10": 1.0, | |
| "mrr_at_10": 0.3333333333333333, | |
| "ndcg_at_10": 0.5 | |
| }, | |
| "semantic-neighbor": { | |
| "recall_at_5": 0.0, | |
| "recall_at_10": 1.0, | |
| "mrr_at_10": 0.125, | |
| "ndcg_at_10": 0.31546487678572877 | |
| }, | |
| "structured-db-row": { | |
| "recall_at_5": 0.0, | |
| "recall_at_10": 1.0, | |
| "mrr_at_10": 0.125, | |
| "ndcg_at_10": 0.31546487678572877 | |
| }, | |
| "tool-trace": { | |
| "recall_at_5": 0.0, | |
| "recall_at_10": 1.0, | |
| "mrr_at_10": 0.1, | |
| "ndcg_at_10": 0.2890648263178879 | |
| } | |
| }, | |
| "model_family": "vinci", | |
| "pipeline": "Lattice", | |
| "promotion_gate": { | |
| "shadow_only": true, | |
| "requires_voyage_baseline_comparison": true, | |
| "min_stephen_longitudinal_passes": 8, | |
| "eligible_without_baseline": false | |
| } | |
| } | |
| ] |