Sentence Similarity
sentence-transformers
Safetensors
xlm-roberta
feature-extraction
dense
Generated from Trainer
dataset_size:295188
loss:WeightedMultiPositiveCachedLoss
loss:MultipleNegativesRankingLoss
Eval Results (legacy)
text-embeddings-inference
Instructions to use Ehsanl/cncpt_e5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use Ehsanl/cncpt_e5 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("Ehsanl/cncpt_e5") 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
Download dev_by_kind.json from Ehsanl/cncpt_e5: direct link, hf CLI and curl.
- Browser
- Download file 1.98 kB
-
https://huggingface.co/Ehsanl/cncpt_e5/resolve/main/dev_by_kind.json
- Command line
-
hf download hf://Ehsanl/cncpt_e5/dev_by_kind.json
-
curl -L -o dev_by_kind.json https://huggingface.co/Ehsanl/cncpt_e5/resolve/main/dev_by_kind.json
1.98 kB
| { | |
| "summary": { | |
| "dev-summary_cosine_accuracy@1": 0.458, | |
| "dev-summary_cosine_accuracy@5": 0.798, | |
| "dev-summary_cosine_accuracy@10": 0.877, | |
| "dev-summary_cosine_precision@1": 0.458, | |
| "dev-summary_cosine_precision@10": 0.15610000000000002, | |
| "dev-summary_cosine_precision@25": 0.08628000000000001, | |
| "dev-summary_cosine_recall@1": 0.05152065295815296, | |
| "dev-summary_cosine_recall@10": 0.173055395992896, | |
| "dev-summary_cosine_recall@25": 0.23789036102786104, | |
| "dev-summary_cosine_ndcg@10": 0.23113588599657442, | |
| "dev-summary_cosine_mrr@10": 0.5988781746031744, | |
| "dev-summary_cosine_map@100": 0.12377712614452646 | |
| }, | |
| "question": { | |
| "dev-question_cosine_accuracy@1": 0.312, | |
| "dev-question_cosine_accuracy@5": 0.584, | |
| "dev-question_cosine_accuracy@10": 0.669, | |
| "dev-question_cosine_precision@1": 0.312, | |
| "dev-question_cosine_precision@10": 0.09659999999999999, | |
| "dev-question_cosine_precision@25": 0.051879999999999996, | |
| "dev-question_cosine_recall@1": 0.06280153735153735, | |
| "dev-question_cosine_recall@10": 0.1758062826062826, | |
| "dev-question_cosine_recall@25": 0.23278918026418027, | |
| "dev-question_cosine_ndcg@10": 0.19077156506634219, | |
| "dev-question_cosine_mrr@10": 0.4223615079365074, | |
| "dev-question_cosine_map@100": 0.11703775434440343 | |
| }, | |
| "article_question": { | |
| "dev-article_question_cosine_accuracy@1": 0.227, | |
| "dev-article_question_cosine_accuracy@5": 0.494, | |
| "dev-article_question_cosine_accuracy@10": 0.608, | |
| "dev-article_question_cosine_precision@1": 0.227, | |
| "dev-article_question_cosine_precision@10": 0.0834, | |
| "dev-article_question_cosine_precision@25": 0.04748, | |
| "dev-article_question_cosine_recall@1": 0.05320595238095238, | |
| "dev-article_question_cosine_recall@10": 0.1930401154401154, | |
| "dev-article_question_cosine_recall@25": 0.27011396103896107, | |
| "dev-article_question_cosine_ndcg@10": 0.18361063568884123, | |
| "dev-article_question_cosine_mrr@10": 0.34262301587301586, | |
| "dev-article_question_cosine_map@100": 0.1191213852280308 | |
| } | |
| } |