Silan10 commited on
Commit
ee4ce9e
·
verified ·
1 Parent(s): fc26347

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -1
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,