Sentence Similarity
sentence-transformers
Safetensors
English
bert
feature-extraction
retrieval
bge
beir
vstash
mnrl
fine-tuned
text-embeddings-inference
Instructions to use Stffens/bge-small-rrf-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use Stffens/bge-small-rrf-v3 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("Stffens/bge-small-rrf-v3") sentences = [ "That is a happy person", "That is a happy dog", "That is a very happy person", "Today is a sunny day" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
| { | |
| "base_model": "BAAI/bge-small-en-v1.5", | |
| "n_pairs": 39852, | |
| "epochs": 2, | |
| "batch_size": 32, | |
| "lr": 3e-06, | |
| "use_amp": true, | |
| "max_seq_length": 256, | |
| "seed": 42, | |
| "training_time_s": 409.6, | |
| "multi_eval": { | |
| "per_dataset_baseline": { | |
| "scifact": { | |
| "ndcg_at_10": 0.7332589505448117, | |
| "mrr": 0.6985621693121693, | |
| "hit_at_10": 0.8666666666666667, | |
| "n_queries": 300, | |
| "ndcg_at_3": 0.6864461358824794, | |
| "recall_at_100": 0.9633333333333334 | |
| }, | |
| "nfcorpus": { | |
| "ndcg_at_10": 0.3537822502011714, | |
| "mrr": 0.5585421888053467, | |
| "hit_at_10": 0.718266253869969, | |
| "n_queries": 323, | |
| "ndcg_at_3": 0.42597599502093686, | |
| "recall_at_100": 0.31346252170704986 | |
| }, | |
| "fiqa": { | |
| "ndcg_at_10": 0.3916405282437908, | |
| "mrr": 0.4678749020184205, | |
| "hit_at_10": 0.6790123456790124, | |
| "n_queries": 648, | |
| "ndcg_at_3": 0.34901243718670777, | |
| "recall_at_100": 0.692446185501741 | |
| } | |
| }, | |
| "per_dataset_final": { | |
| "scifact": { | |
| "ndcg_at_10": 0.781752459899092, | |
| "mrr": 0.7422301587301587, | |
| "hit_at_10": 0.93, | |
| "n_queries": 300, | |
| "ndcg_at_3": 0.7335167753839059, | |
| "recall_at_100": 0.99 | |
| }, | |
| "nfcorpus": { | |
| "ndcg_at_10": 0.37574420884042387, | |
| "mrr": 0.5812288073123986, | |
| "hit_at_10": 0.7306501547987616, | |
| "n_queries": 323, | |
| "ndcg_at_3": 0.4442297150425726, | |
| "recall_at_100": 0.3516690054451889 | |
| }, | |
| "fiqa": { | |
| "ndcg_at_10": 0.48181104416454384, | |
| "mrr": 0.554401822457378, | |
| "hit_at_10": 0.7901234567901234, | |
| "n_queries": 648, | |
| "ndcg_at_3": 0.4284406049379992, | |
| "recall_at_100": 0.8457548067501771 | |
| } | |
| }, | |
| "per_dataset_pairs": { | |
| "scifact": 4291, | |
| "nfcorpus": 9713, | |
| "fiqa": 25848 | |
| }, | |
| "per_dataset_budget": { | |
| "scifact": 11601, | |
| "nfcorpus": 9713, | |
| "fiqa": 38686 | |
| }, | |
| "per_dataset_sizes": { | |
| "scifact": 5183, | |
| "nfcorpus": 3633, | |
| "fiqa": 57638 | |
| }, | |
| "macro_baseline_ndcg": 0.49289, | |
| "macro_final_ndcg": 0.54644, | |
| "macro_delta_ndcg": 0.05354, | |
| "sampling": "temperature", | |
| "temperature": 0.5, | |
| "total_triples_target": 60000, | |
| "gated_out": false, | |
| "per_dataset_gate": false, | |
| "min_gain": -1.0, | |
| "seed": 42 | |
| } | |
| } |