Update README.md
Browse files
README.md
CHANGED
|
@@ -37,7 +37,6 @@ The successors of [German_Semantic_STS_V2](https://huggingface.co/aari1995/Germa
|
|
| 37 |
- **Sequence length:** Embed up to 8192 tokens (16 times more than V2 and other models)
|
| 38 |
- **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.
|
| 39 |
- **German only:** This model is German-only, it has rich cultural knowledge about Germany and German topics. Therefore, also the model to learn more efficient thanks to its tokenizer, deal better with shorter queries and generally be more nuanced in many scenarios.
|
| 40 |
-
- **Updated knowledge and quality data:** The backbone of this model is gbert-large by deepset. With Stage-2 pretraining on 1 Billion tokens of German fineweb by occiglot, up-to-date knowledge is ensured.
|
| 41 |
- **Typo and Casing**: This model was trained to be robust against minor typos and casing, leading to slightly weaker benchmark performance and learning during training, but higher robustness of the embeddings.
|
| 42 |
- **Pooling Function:** Moving away from mean pooling towards using the CLS token. Generally seems to learn better after the stage-2 pretraining and allows for more flexibility.
|
| 43 |
- **License:** Apache 2.0
|
|
|
|
| 37 |
- **Sequence length:** Embed up to 8192 tokens (16 times more than V2 and other models)
|
| 38 |
- **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.
|
| 39 |
- **German only:** This model is German-only, it has rich cultural knowledge about Germany and German topics. Therefore, also the model to learn more efficient thanks to its tokenizer, deal better with shorter queries and generally be more nuanced in many scenarios.
|
|
|
|
| 40 |
- **Typo and Casing**: This model was trained to be robust against minor typos and casing, leading to slightly weaker benchmark performance and learning during training, but higher robustness of the embeddings.
|
| 41 |
- **Pooling Function:** Moving away from mean pooling towards using the CLS token. Generally seems to learn better after the stage-2 pretraining and allows for more flexibility.
|
| 42 |
- **License:** Apache 2.0
|