Fix typo
Browse files
README.md
CHANGED
|
@@ -22,7 +22,7 @@ All quants made using imatrix option with dataset from [here](https://gist.githu
|
|
| 22 |
|
| 23 |
## What's new
|
| 24 |
|
| 25 |
-
- June
|
| 26 |
- July 3 2024: Updated the experimental quants to newer method, Q8 for embed/output, yields higher quality at much lower size than f16 (left Q8_0_L since Q8_0 is already Q8 embed/output)
|
| 27 |
|
| 28 |
## Prompt format
|
|
|
|
| 22 |
|
| 23 |
## What's new
|
| 24 |
|
| 25 |
+
- June 31 2024: Contains latest tokenizer fixes, which addressed a few oddities from the original fix, should be closest to correct performance yet. Also has metadata for SWA and logit softcapping.
|
| 26 |
- July 3 2024: Updated the experimental quants to newer method, Q8 for embed/output, yields higher quality at much lower size than f16 (left Q8_0_L since Q8_0 is already Q8 embed/output)
|
| 27 |
|
| 28 |
## Prompt format
|