Sentence Similarity
sentence-transformers
Safetensors
bert
feature-extraction
fitness
retrieval
text-embeddings-inference
Instructions to use OrDora/coachtwin-embedder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use OrDora/coachtwin-embedder with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("OrDora/coachtwin-embedder") 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
| { | |
| "embedding_model": "BAAI/bge-small-en-v1.5", | |
| "dim": 384, | |
| "n_vectors": 10393, | |
| "normalized": true, | |
| "metric": "inner_product (== cosine on normalised vectors)", | |
| "doc_text_template": "{title}. Goal: {goal}. Equipment: {equipment}. Duration: {duration_minutes} minutes. Difficulty: {difficulty}. Body focus: {body_focus}. Exercises: {names}.", | |
| "query_text_template": "I want a {difficulty} {goal} workout for {body_focus}, {duration} minutes, using {equipment}.", | |
| "needs_query_prefix": true, | |
| "evaluation": { | |
| "all-MiniLM-L6-v2": { | |
| "precision_at_3_strict": 0.4733, | |
| "precision_at_3_loose": 0.6667, | |
| "mrr_at_10": 0.6686, | |
| "params_M": 22, | |
| "dim": 384, | |
| "encode_corpus_s": 7.0 | |
| }, | |
| "all-mpnet-base-v2": { | |
| "precision_at_3_strict": 0.5047, | |
| "precision_at_3_loose": 0.7453, | |
| "mrr_at_10": 0.6866, | |
| "params_M": 110, | |
| "dim": 768, | |
| "encode_corpus_s": 31.2 | |
| }, | |
| "bge-small-en-v1.5": { | |
| "precision_at_3_strict": 0.6687, | |
| "precision_at_3_loose": 0.8273, | |
| "mrr_at_10": 0.802, | |
| "params_M": 33, | |
| "dim": 384, | |
| "encode_corpus_s": 10.4 | |
| } | |
| }, | |
| "random_baseline": { | |
| "precision_at_3_strict": 0.021999999999999995, | |
| "precision_at_3_loose": 0.12, | |
| "mrr_at_10": 0.06852301587301587 | |
| } | |
| } |