Sentence Similarity
sentence-transformers
Safetensors
bert
feature-extraction
dense
Generated from Trainer
dataset_size:110575
loss:MultipleNegativesRankingLoss
Eval Results (legacy)
text-embeddings-inference
Instructions to use dboyker-code/all-MiniLM-L6-v2-nfcorpus with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use dboyker-code/all-MiniLM-L6-v2-nfcorpus with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("dboyker-code/all-MiniLM-L6-v2-nfcorpus") sentences = [ "colon health because of the fiber content , plant-based diets may produce healthier stools and lead to larger bowel movements , which is important for the prevention of a number of medical conditions . interestingly , antioxidant-rich fruits and vegetables appear to increase stool size independent of fiber . furthermore", "Abstract BACKGROUND: The aging process can lead to a decline in cellular immunity. Therefore, the elderly could benefit from safe and effective interventions that restore cellular immune functions. OBJECTIVE: We determined whether dietary supplementation", "Abstract OBJECTIVES: Standard therapies for antibiotic-associated diarrhea (AAD) and Clostridium difficile-associated diarrhea (CDAD) have limited efficacy. Probiotic prophylaxis is a promising alternative for reduction of AAD and CDAD incidence.", "Abstract BACKGROUND: Heterocyclic amines, mutagens formed in meats cooked at high temperatures, have been demonstrated as mammary carcinogens in animals. We conducted a nested, case-control study among 41836 cohort members of the Iowa" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -174,8 +174,6 @@ It is specialised for Information retrieval (IR). Here is the relative improveme
|
|
| 174 |
|
| 175 |
More information on training and dev can be found below.
|
| 176 |
|
| 177 |
-
|
| 178 |
-
'dev_cosine_ndcg@10': 0.2596277626513332, 'dev_cosine_mrr@10': 0.46781182637664115, 'dev_cosine_map@100': 0.12158349529658409
|
| 179 |
## Model Details
|
| 180 |
|
| 181 |
### Model Description
|
|
|
|
| 174 |
|
| 175 |
More information on training and dev can be found below.
|
| 176 |
|
|
|
|
|
|
|
| 177 |
## Model Details
|
| 178 |
|
| 179 |
### Model Description
|