aari1995
/

German_Semantic_V3

Sentence Similarity

sentence-transformers

feature-extraction

loss:MatryoshkaLoss

text-embeddings-inference

Model card Files Files and versions Community

aari1995 commited on Jun 25, 2024

Commit

a2c1e06

·

verified ·

1 Parent(s): 214ddb5

Update README.md

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -86,7 +86,7 @@ similarities = model.similarity(embeddings, embeddings)
 ```
-# Full Model Architecture
 ```
 SentenceTransformer(
@@ -122,7 +122,7 @@ Another noticable difference is that V3 has a broader cosine_similarity spectrum
 **A:** Broadly speaking, when going from 1024 to 512 dimensions, there is very little trade-off (1 percent). When going down to 64 dimensions, you may face a decrease of up to 3 percent.
-## Evaluation
 Storage comparison:
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3801ab7e583543386217ac/Aa5WzHanj-DXc86AKxpEz.png)
@@ -130,7 +130,7 @@ Storage comparison:
 Benchmarks: soon.
 # Up next:
-German_Semantic_V3_Instruct: Guiding your embeddings towards self-selected aspects
 # Thank You and Credits

 ```
+## Full Model Architecture
 ```
 SentenceTransformer(
 **A:** Broadly speaking, when going from 1024 to 512 dimensions, there is very little trade-off (1 percent). When going down to 64 dimensions, you may face a decrease of up to 3 percent.
+# Evaluation
 Storage comparison:
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3801ab7e583543386217ac/Aa5WzHanj-DXc86AKxpEz.png)
 Benchmarks: soon.
 # Up next:
+German_Semantic_V3_Instruct: Guiding your embeddings towards self-selected aspects. - planned: 2024.
 # Thank You and Credits