Update README.md
Browse files
README.md
CHANGED
|
@@ -5,7 +5,7 @@ base_model_relation: quantized
|
|
| 5 |
---
|
| 6 |
|
| 7 |
|
| 8 |
-
FP8 quantized version of [AuraFlow v0.3](fal/AuraFlow-v0.3)
|
| 9 |
|
| 10 |
Just casted to `torch.float8_e4m3fn` all linear weights of the flow transformer except `t_embedder`, `final_linear`, `modF`.
|
| 11 |
|
|
|
|
| 5 |
---
|
| 6 |
|
| 7 |
|
| 8 |
+
FP8 quantized version of [AuraFlow v0.3](https://huggingface.co/fal/AuraFlow-v0.3)
|
| 9 |
|
| 10 |
Just casted to `torch.float8_e4m3fn` all linear weights of the flow transformer except `t_embedder`, `final_linear`, `modF`.
|
| 11 |
|