Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
This is an unavoidable double quantization due to the release state of Ideogram4.
|
| 2 |
|
| 3 |
The FP8 weights were cast to FP32 with the FP8 scales, then downcast to BF16 before being converted to INT8.
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
license_name: ideogram-4-non-commercial
|
| 4 |
+
license_link: https://huggingface.co/ideogram-ai/ideogram-4-fp8/blob/main/LICENSE.md
|
| 5 |
+
pipeline_tag: text-to-image
|
| 6 |
+
tags:
|
| 7 |
+
- text-to-image
|
| 8 |
+
- image-generation
|
| 9 |
+
- diffusion
|
| 10 |
+
- flow-matching
|
| 11 |
+
- dit
|
| 12 |
+
- ideogram
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
This is an unavoidable double quantization due to the release state of Ideogram4.
|
| 16 |
|
| 17 |
The FP8 weights were cast to FP32 with the FP8 scales, then downcast to BF16 before being converted to INT8.
|