Sentence Similarity
sentence-transformers
PyTorch
English
bert
feature-extraction
text-embeddings-inference
Instructions to use julep-ai/dfe-base-en with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use julep-ai/dfe-base-en with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("julep-ai/dfe-base-en") 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 eval/triplet_evaluation_results.csv from julep-ai/dfe-base-en: direct link, hf CLI and curl.
- Browser
- Download file 1.6 kB
-
https://huggingface.co/julep-ai/dfe-base-en/resolve/main/eval/triplet_evaluation_results.csv
- Command line
-
hf download hf://julep-ai/dfe-base-en/eval/triplet_evaluation_results.csv
-
curl -L -o triplet_evaluation_results.csv https://huggingface.co/julep-ai/dfe-base-en/resolve/main/eval/triplet_evaluation_results.csv
1.6 kB
| epoch,steps,accuracy_cosinus,accuracy_manhattan,accuracy_euclidean | |
| 0,1200,0.9606164840146122,0.9602165160120524,0.9614964136202437 | |
| 0,2400,0.968722502199824,0.9686691731328161,0.968775831266832 | |
| 0,-1,0.9683491987307682,0.968642508599312,0.9684825213982882 | |
| 1,1200,0.9688291603338399,0.968749166733328,0.968882489400848 | |
| 1,2400,0.9700557288750233,0.9699757352745114,0.9700823934085273 | |
| 1,-1,0.9694424446044316,0.9694691091379356,0.9697357544729754 | |
| 2,1200,0.9703490387435671,0.9704556968775832,0.970695677679119 | |
| 2,2400,0.9670159720555689,0.966909313921553,0.9672292883236008 | |
| 2,-1,0.9683758632642722,0.9682158760632483,0.9684291923312802 | |
| 3,1200,0.9681092179292323,0.9682425405967523,0.9683491987307682 | |
| 3,2400,0.9677359144601765,0.9676292563261606,0.9679492307282084 | |
| 3,-1,0.9690958056688799,0.9690691411353758,0.9695491027384476 | |
| 4,1200,0.9691491347358878,0.9691224702023838,0.9692824574034077 | |
| 4,2400,0.9694157800709277,0.9695491027384476,0.9696024318054556 | |
| 4,-1,0.9696557608724635,0.9695757672719516,0.9699224062075034 | |
| 5,1200,0.9695757672719516,0.9693891155374237,0.9692824574034077 | |
| 5,2400,0.9701890515425433,0.9701357224755353,0.9702690451430552 | |
| 5,-1,0.9700023998080154,0.9699224062075034,0.9701623870090392 | |
| 6,1200,0.9713089619497107,0.9713889555502226,0.9713089619497107 | |
| 6,2400,0.9703223742100632,0.9702957096765592,0.9704290323440792 | |
| 6,-1,0.970695677679119,0.9706156840786071,0.9709356584806549 | |
| 7,1200,0.9703757032770711,0.9703223742100632,0.9702690451430552 | |
| 7,2400,0.9703757032770711,0.9705090259445911,0.970749006746127 | |
| 7,-1,0.9703757032770711,0.9705090259445911,0.970749006746127 | |