Update README.md
Browse files
README.md
CHANGED
|
@@ -14,7 +14,8 @@ pipeline_tag: text-to-image
|
|
| 14 |
text-to-image model.
|
| 15 |
|
| 16 |
This repository only changes the **numerical precision of the weights** to
|
| 17 |
-
`torch.float16` using PyTorch.
|
|
|
|
| 18 |
|
| 19 |
## Usage
|
| 20 |
|
|
|
|
| 14 |
text-to-image model.
|
| 15 |
|
| 16 |
This repository only changes the **numerical precision of the weights** to
|
| 17 |
+
`torch.float16` using PyTorch. This is not real quantization (like int8/int4). Still,
|
| 18 |
+
converting the model to float16 saves the memory, reduces RAM usage and speeds up loading times.
|
| 19 |
|
| 20 |
## Usage
|
| 21 |
|