Sentence Similarity
sentence-transformers
Safetensors
feature-extraction
dense
Generated from Trainer
dataset_size:40374
loss:MultipleNegativesRankingLoss
Eval Results (legacy)
Instructions to use vrnP66/finetuned-embedding-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use vrnP66/finetuned-embedding-model with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("vrnP66/finetuned-embedding-model") sentences = [ "यथोवाच भगवान् धन्वन्तरिः ||२||", "**Ashtanga Hridayam, Uttara Sthana, chapter 22, sutra 106**\n\n**Sutra**:\nपटोल-निम्ब-यष्ट्य्-आह्व-वासा-जात्य्-अरिमेदसाम् । खदिरस्य वरायाश् च पृथग् एवं प्रकल्पना ॥ १०६ ॥\n\n**English Transliteration**:\npaṭola-nimba-yaṣṭy-āhva-vāsā-jāty-arimedasām | khadirasya varāyāś ca pṛthag evaṁ prakalpanā || 106 ||\n\n**English Translation**:\nThus, a separate preparation should be made from patola, nimba, licorice, vasa, jati, arimedasa, khadira, and vara.", "**Susrut Samhita, Sharira Sthana, chapter 9, sutra 2**\n\n**Sutra**:\nयथोवाच भगवान् धन्वन्तरिः ||२||\n\n**English Transliteration**:\nyathovāca bhagavān dhanvantariḥ ||2||\n\n**English Translation**:\nThus spoke the venerable Dhanvantari.", "**Susrut Samhita, Chikitsa Sthana, chapter 24, sutra 85**\n\n**Sutra**:\nसुखं वातं प्रसेवेत ग्रीष्मे शरदि मानवः | निवातं ह्यायुषे सेव्यमारोग्याय च सर्वदा ||८५||\n\n**English Transliteration**:\nsukhaṃ vātaṃ praseveta grīṣme śaradi mānavaḥ | nivātaṃ hyāyuṣe sevyamārogyāya ca sarvadā ||85||\n\n**English Translation**:\nA person should enjoy pleasant wind in summer and autumn. Absence of wind is always beneficial for longevity and health." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
File size: 313 Bytes
c4bbc52 | 1 2 3 4 5 6 7 8 9 10 | {
"word_embedding_dimension": 1024,
"pooling_mode_cls_token": false,
"pooling_mode_mean_tokens": true,
"pooling_mode_max_tokens": false,
"pooling_mode_mean_sqrt_len_tokens": false,
"pooling_mode_weightedmean_tokens": false,
"pooling_mode_lasttoken": false,
"include_prompt": true
} |