Update README.md
Browse files
README.md
CHANGED
|
@@ -94,12 +94,15 @@ Evaluation to come.
|
|
| 94 |
## FAQ
|
| 95 |
|
| 96 |
**Q: Is this Model better than V2?**
|
|
|
|
| 97 |
**A:** In terms of flexibility-definitely. In terms of data-yes as well, as it is more up-to-date. In terms of benchmark they differ, while V3 is better for longer texts, V2 works very well for shorter texts.
|
| 98 |
|
| 99 |
**Q: How does the model perform vs. multilingual models?**
|
|
|
|
| 100 |
**A:** There are really great multilingual models that will be very useful for many use-cases. This model shines with its cultural knowledge.
|
| 101 |
|
| 102 |
**Q: What is the trade-off when reducing the embedding size?**
|
|
|
|
| 103 |
**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.
|
| 104 |
|
| 105 |
## Up next:
|
|
|
|
| 94 |
## FAQ
|
| 95 |
|
| 96 |
**Q: Is this Model better than V2?**
|
| 97 |
+
|
| 98 |
**A:** In terms of flexibility-definitely. In terms of data-yes as well, as it is more up-to-date. In terms of benchmark they differ, while V3 is better for longer texts, V2 works very well for shorter texts.
|
| 99 |
|
| 100 |
**Q: How does the model perform vs. multilingual models?**
|
| 101 |
+
|
| 102 |
**A:** There are really great multilingual models that will be very useful for many use-cases. This model shines with its cultural knowledge.
|
| 103 |
|
| 104 |
**Q: What is the trade-off when reducing the embedding size?**
|
| 105 |
+
|
| 106 |
**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.
|
| 107 |
|
| 108 |
## Up next:
|