Spaces:
Running
Running
Update README.md
Browse files
README.md
CHANGED
|
@@ -7,7 +7,8 @@ sdk: static
|
|
| 7 |
pinned: true
|
| 8 |
---
|
| 9 |
|
| 10 |
-
These are my own quantizations (updated almost daily).
|
|
|
|
| 11 |
The difference with normal quantizations is that I quantize the output and embed tensors to f16.
|
| 12 |
and the other tensors to 15_k,q6_k or q8_0.
|
| 13 |
This creates models that are little or not degraded at all and have a smaller size.
|
|
|
|
| 7 |
pinned: true
|
| 8 |
---
|
| 9 |
|
| 10 |
+
[These are my own quantizations (updated almost daily).](https://huggingface.co/spaces/RobertSinclair)
|
| 11 |
+
|
| 12 |
The difference with normal quantizations is that I quantize the output and embed tensors to f16.
|
| 13 |
and the other tensors to 15_k,q6_k or q8_0.
|
| 14 |
This creates models that are little or not degraded at all and have a smaller size.
|