Eviation commited on
Commit
487e890
·
verified ·
1 Parent(s): d7891f5

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -0
README.md CHANGED
@@ -55,6 +55,7 @@ Using [llama.cpp quantize cae9fb4](https://github.com/ggerganov/llama.cpp/commit
55
  - [Latent loss](https://huggingface.co/Eviation/flux-imatrix/blob/main/images/latent_loss.png)
56
  - [Per layer quantization cost](https://huggingface.co/Eviation/flux-imatrix/blob/main/images/casting_cost.png) from [chrisgoringe/casting_cost](https://github.com/chrisgoringe/mixed-gguf-converter/blob/main/costs/casting_cost.yaml)
57
  - [Ablation latent loss per weight type](https://huggingface.co/Eviation/flux-imatrix/blob/main/images/latent_loss_ablation.png)
 
58
 
59
  # Alpha
60
  Simple imatrix: 512x512 single image 8/20 steps [city96/flux1-dev-Q3_K_S](https://huggingface.co/city96/FLUX.1-dev-gguf/blob/main/flux1-dev-Q3_K_S.gguf) euler
 
55
  - [Latent loss](https://huggingface.co/Eviation/flux-imatrix/blob/main/images/latent_loss.png)
56
  - [Per layer quantization cost](https://huggingface.co/Eviation/flux-imatrix/blob/main/images/casting_cost.png) from [chrisgoringe/casting_cost](https://github.com/chrisgoringe/mixed-gguf-converter/blob/main/costs/casting_cost.yaml)
57
  - [Ablation latent loss per weight type](https://huggingface.co/Eviation/flux-imatrix/blob/main/images/latent_loss_ablation.png)
58
+ - [Pareto front loss vs. size](https://huggingface.co/Eviation/flux-imatrix/blob/main/images/latent_loss_size_pareto.png)
59
 
60
  # Alpha
61
  Simple imatrix: 512x512 single image 8/20 steps [city96/flux1-dev-Q3_K_S](https://huggingface.co/city96/FLUX.1-dev-gguf/blob/main/flux1-dev-Q3_K_S.gguf) euler