Update README.md
Browse files
README.md
CHANGED
|
@@ -11,7 +11,7 @@ tags:
|
|
| 11 |
- flux
|
| 12 |
- 4-bit
|
| 13 |
---
|
| 14 |
-
Dynamic 4 bit quantization of [black-forest-labs/FLUX.2-klein-
|
| 15 |
|
| 16 |
This model uses per layer fine grained quantization.
|
| 17 |
What dtype to use for a layer is selected dynamically by trial and error until the std normalized mse loss is lower than the selected threshold.
|
|
|
|
| 11 |
- flux
|
| 12 |
- 4-bit
|
| 13 |
---
|
| 14 |
+
Dynamic 4 bit quantization of [black-forest-labs/FLUX.2-klein-4B](https://huggingface.co/black-forest-labs/FLUX.2-klein-4B) using [SDNQ](https://github.com/Disty0/sdnq).
|
| 15 |
|
| 16 |
This model uses per layer fine grained quantization.
|
| 17 |
What dtype to use for a layer is selected dynamically by trial and error until the std normalized mse loss is lower than the selected threshold.
|