Sentence Similarity
sentence-transformers
Safetensors
English
bert
biencoder
text-classification
sentence-pair-classification
semantic-similarity
semantic-search
retrieval
reranking
Generated from Trainer
dataset_size:8000000
loss:ArcFaceInBatchLoss
Eval Results (legacy)
text-embeddings-inference
Instructions to use redis/langcache-embed-v3-small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use redis/langcache-embed-v3-small with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("redis/langcache-embed-v3-small") sentences = [ "\"How much would I need to narrate a \"\"Let's Play\"\" video in order to make money from it on YouTube?\"", "How much money do people make from YouTube videos with 1 million views?", "\"How much would I need to narrate a \"\"Let's Play\"\" video in order to make money from it on YouTube?\"", "\"Does the sentence, \"\"I expect to be disappointed,\"\" make sense?\"" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
| { | |
| "test_cosine_accuracy@1": 0.5955802603036876, | |
| "test_cosine_precision@1": 0.5955802603036876, | |
| "test_cosine_recall@1": 0.5780913232288468, | |
| "test_cosine_ndcg@10": 0.777639866271746, | |
| "test_cosine_mrr@1": 0.5955802603036876, | |
| "test_cosine_map@100": 0.7275779687157514, | |
| "test_cosine_auc_precision_cache_hit_ratio": 0.3639683124583609, | |
| "test_cosine_auc_similarity_distribution": 0.15401896350374616 | |
| } |