aari1995 commited on
Commit
ed87d6c
·
verified ·
1 Parent(s): 8a06dec

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -284,16 +284,16 @@ license: apache-2.0
284
 
285
  # German Semantic V3
286
 
287
- The successor of German_Semantic_STS_V2 is here!
288
 
289
  ## Major updates and USPs:
290
 
291
  - **Sequence length:** 8192, (16 times more than V2 and other models) -> thanks to the ALiBi implementation of Jina-Team!
292
  - **Matryoshka Embeddings:** The model is trained for embedding sizes from 1024 down to 64, allowing you to store much smaller embeddings with little quality loss.
293
- - **License:** Apache 2.0
294
  - **German only:** This model is German-only, causing the model to learn more efficient thanks to its tokenizer, deal better with shorter queries and generally be more nuanced.
295
  - **Updated knowledge and quality data:** The backbone of this model is gbert-large by deepset. With Stage-2 pretraining on German fineweb by occiglot (newest only), up-to-date knowledge is ensured.
296
- - **Flexibility:** Trained with flexible sequence-length and embedding truncation, flexibility is a core feature of the model, while improving on V2-performance.
 
297
 
298
  ## Usage:
299
 
 
284
 
285
  # German Semantic V3
286
 
287
+ Finally, a new version! The successor of German_Semantic_STS_V2 is here and comes with loads of cool new features!
288
 
289
  ## Major updates and USPs:
290
 
291
  - **Sequence length:** 8192, (16 times more than V2 and other models) -> thanks to the ALiBi implementation of Jina-Team!
292
  - **Matryoshka Embeddings:** The model is trained for embedding sizes from 1024 down to 64, allowing you to store much smaller embeddings with little quality loss.
 
293
  - **German only:** This model is German-only, causing the model to learn more efficient thanks to its tokenizer, deal better with shorter queries and generally be more nuanced.
294
  - **Updated knowledge and quality data:** The backbone of this model is gbert-large by deepset. With Stage-2 pretraining on German fineweb by occiglot (newest only), up-to-date knowledge is ensured.
295
+ - **Flexibility:** Trained with flexible sequence-length and embedding truncation, flexibility is a core feature of the model, while improving on V2-performance.
296
+ - **License:** Apache 2.0
297
 
298
  ## Usage:
299