Update README.md

README.md

@@ -35,13 +35,13 @@ pipeline_tag: sentence-similarity
 ---
 
 # German Semantic V3 
-## and [**German_Semantic_V3b**](https://huggingface.co/aari1995/German_Semantic_V3b)
+### and [**German_Semantic_V3b**](https://huggingface.co/aari1995/German_Semantic_V3b)
 
 The successor ofs [German_Semantic_STS_V2](https://huggingface.co/aari1995/German_Semantic_STS_V2) are here and come with loads of cool new features! While V3 is really knowledge-heavy, V3b is more focused on performance. Feel free to provide feedback on the model and what you would like to see next.
 
 **Note:** To run this model properly, see "Usage".
 
-## Major updates and USPs:
+# Major updates and USPs:
 
 - **Flexibility:** Trained with flexible sequence-length and embedding truncation, flexibility is a core feature of the model. Yet, smaller dimensions bring a minor trade-off in quality. 
 - **Sequence length:** Embed up to 8192 tokens (16 times more than V2 and other models)
@@ -54,7 +54,7 @@ The successor ofs [German_Semantic_STS_V2](https://huggingface.co/aari1995/Germa
 
 (If you are looking for even better performance on tasks, but with a German knowledge-cutoff around 2020, check out [German_Semantic_V3b](https://huggingface.co/aari1995/German_Semantic_V3))
 
-## Usage:
+# Usage:
 
 This model has some build-in functionality that is rather hidden. To profit from it, use this code:
 
@@ -86,7 +86,7 @@ similarities = model.similarity(embeddings, embeddings)
 
 ```
 
-### Full Model Architecture
+# Full Model Architecture
 
 ```
 SentenceTransformer(
@@ -96,11 +96,11 @@ SentenceTransformer(
 ```
 
 
-## Evaluation
+# Evaluation
 
 Evaluation to come.
 
-## FAQ
+# FAQ
 
 **Q: Is this Model better than V2?**
 
@@ -126,10 +126,10 @@ Also, V3 uses cls_pooling while V3buses mean_pooling.
 
 **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.
 
-## Up next:
+# Up next:
 German_Semantic_V3_Instruct: Guiding your embeddings towards self-selected aspects
 
-## Thank You and Credits
+# Thank You and Credits
 
 - To [jinaAI](https://huggingface.co/jinaai) for their BERT implementation that is used, especially ALiBi
 - To [deepset](https://huggingface.co/deepset) for the gbert-large, which is a really great model