Sentence Similarity
sentence-transformers
Safetensors
xlm-roberta
feature-extraction
Generated from Trainer
dataset_size:1814
loss:MatryoshkaLoss
loss:MultipleNegativesRankingLoss
Eval Results (legacy)
text-embeddings-inference
Instructions to use FareedKhan/mixedbread-ai_deepset-mxbai-embed-de-large-v1_FareedKhan_prime_synthetic_data_2k_3_8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use FareedKhan/mixedbread-ai_deepset-mxbai-embed-de-large-v1_FareedKhan_prime_synthetic_data_2k_3_8 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("FareedKhan/mixedbread-ai_deepset-mxbai-embed-de-large-v1_FareedKhan_prime_synthetic_data_2k_3_8") sentences = [ "\nThe document you provided seems to be a list of compounds, some of which are well-known drugs or drugs used in experimental contexts, and others that don't appear to have recognized applications in medicine or science. The list includes substances like cortisol, a hormone, and filopram, which is related to anesthetics or possibly a misprint or misclassification. The side effects listed are also a mix, with some being plausible reactions to certain medication (like Edema, dysphagia) and others being quite unusual for commonly recognized drug interactions (like retinal vein occlusion, which is not a typical side effect of most medications).\n\nIt would be useful to have labels or references indicating which of these compounds are actually drugs and which are other chemical substances. For instance, cortisol, if given its correct context, would typically have side effects associated with cortisol therapy such as fluid retention or electrolyte imbalances.\n\nIf you need detailed information on how these substances work or what their possible side effects might be, you'll likely need to refer to a medical compendium or a pharmacology resource for accurate data. It's also important to clarify the intended use for this list, whether for educational purposes, research, or another context; the provided list appears to be a jumbled amalgamation, which might not have clear clinical relevance without additional detail.", "Can you suggest medications targeting the GC gene/protein with a proven synergy with AVE9633?", "Could you help identify the gene or protein that facilitates sodium-dependent transportation and elimination of organic anions, with a particular emphasis on those implicated in the cellular efflux of potentially hazardous organic anions? Additionally, I'm interested in understanding if this gene or protein also mediates the transport of drugs known to exhibit synergistic pharmacological interactions with Ractopamine.", "Can you list the medications suitable for benign prostatic hyperplasia and tell me if any are linked to dysphagia as a side effect?" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle