Update README.md
Browse files
README.md
CHANGED
|
@@ -11,7 +11,8 @@ pipeline_tag: text-to-image
|
|
| 11 |
|
| 12 |
`Silan10/flux_quantized_half` is a **half-precision (FP16) variant** of the
|
| 13 |
[`black-forest-labs/FLUX.1-dev`](https://huggingface.co/black-forest-labs/FLUX.1-dev)
|
| 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,
|
|
|
|
| 11 |
|
| 12 |
`Silan10/flux_quantized_half` is a **half-precision (FP16) variant** of the
|
| 13 |
[`black-forest-labs/FLUX.1-dev`](https://huggingface.co/black-forest-labs/FLUX.1-dev)
|
| 14 |
+
text-to-image model. In this version, the **`transformers`**, **`text_encoder`** and
|
| 15 |
+
**`text_encoder_2`** folders from FLUX.1-dev have been converted to FP16.
|
| 16 |
|
| 17 |
This repository only changes the **numerical precision of the weights** to
|
| 18 |
`torch.float16` using PyTorch. This is not real quantization (like int8/int4). Still,
|