Update README.md
Browse files
README.md
CHANGED
|
@@ -95,10 +95,6 @@ SentenceTransformer(
|
|
| 95 |
```
|
| 96 |
|
| 97 |
|
| 98 |
-
## Evaluation
|
| 99 |
-
|
| 100 |
-
Evaluation to come.
|
| 101 |
-
|
| 102 |
## FAQ
|
| 103 |
|
| 104 |
**Q: Is this Model better than V2?**
|
|
@@ -125,6 +121,13 @@ If you are fine with sacrificing a few points on benchmarks and want the model t
|
|
| 125 |
**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.
|
| 126 |
|
| 127 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 128 |
## Up next:
|
| 129 |
German_Semantic_V3_Instruct: Guiding your embeddings towards self-selected aspects
|
| 130 |
|
|
|
|
| 95 |
```
|
| 96 |
|
| 97 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 98 |
## FAQ
|
| 99 |
|
| 100 |
**Q: Is this Model better than V2?**
|
|
|
|
| 121 |
**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.
|
| 122 |
|
| 123 |
|
| 124 |
+
## Evaluation
|
| 125 |
+
|
| 126 |
+
Storage comparison:
|
| 127 |
+

|
| 128 |
+
|
| 129 |
+
Benchmarks: soon.
|
| 130 |
+
|
| 131 |
## Up next:
|
| 132 |
German_Semantic_V3_Instruct: Guiding your embeddings towards self-selected aspects
|
| 133 |
|