danielhanchen commited on
Commit
d2ba892
·
verified ·
1 Parent(s): 66de2f3

Add quantization header and logos

Browse files
Files changed (1) hide show
  1. README.md +18 -0
README.md CHANGED
@@ -33,6 +33,24 @@ widget:
33
  output:
34
  url: samples/fp8_2.png
35
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
36
 
37
  ### Samples
38
 
 
33
  output:
34
  url: samples/fp8_2.png
35
  ---
36
+ This is an FP8 / INT8 quantized version of [FLUX.2-dev](https://huggingface.co/black-forest-labs/FLUX.2-dev). <br>
37
+ - Optimized for efficient inference with reduced memory footprint. Same-seed LPIPS vs the bf16 model (lower is better): 0.078 INT8, 0.073 FP8.
38
+
39
+ <div>
40
+ <div style="display: flex; gap: 5px; align-items: center; ">
41
+ <a href="https://github.com/unslothai/unsloth/">
42
+ <img src="https://github.com/unslothai/unsloth/raw/main/images/unsloth%20new%20logo.png" width="133">
43
+ </a>
44
+ <a href="https://discord.gg/unsloth">
45
+ <img src="https://github.com/unslothai/unsloth/raw/main/images/Discord%20button.png" width="173">
46
+ </a>
47
+ <a href="https://docs.unsloth.ai/">
48
+ <img src="https://raw.githubusercontent.com/unslothai/unsloth/refs/heads/main/images/documentation%20green%20button.png" width="143">
49
+ </a>
50
+ </div>
51
+ </div>
52
+
53
+ ---
54
 
55
  ### Samples
56