Update README.md

README.md

@@ -1,6 +1,6 @@
 ---
 datasets:
-- AdamCodd/Civitai-2m-prompts
+- AdamCodd/Civitai-8m-prompts
 metrics:
 - accuracy
 - f1
@@ -46,12 +46,12 @@ license: cc-by-nc-4.0
 
 This model has been retrained on the improved [AdamCodd/Civitai-8m-prompts](https://huggingface.co/datasets/AdamCodd/Civitai-8m-prompts) dataset, on ~5 million positive prompts, evenly split between SFW and NSFW categories (2,820,319 samples of each, ensuring a balanced dataset). 
 It achieves the following results on the evaluation set:
-* Loss: 0.2139 (31.07% improvement over V1)
-* Accuracy: 0.9114 (5.46% improvement over V1)
-* F1: 0.9093 (5.58% improvement over V1)
-* AUC: 0.9716 (3.27% improvement over V1)
-* Precision: 0.9318 (5.81% improvement over V1)
-* Recall: 0.8879 (5.36% improvement over V1)
+* Loss: 0.2139 (↓ 31.07% over V1)
+* Accuracy: 0.9114 (↑ 5.46% over V1)
+* F1: 0.9093 (↑ 5.58% over V1)
+* AUC: 0.9716 (↑ 3.27% over V1)
+* Precision: 0.9318 (↑ 5.81% over V1)
+* Recall: 0.8879 (↑ 5.36% over V1)
 
 [Confusion matrix](https://huggingface.co/AdamCodd/distilroberta-nsfw-prompt-stable-diffusion/resolve/main/Confusion_matrix.png):
 
@@ -128,7 +128,7 @@ Metrics: Accuracy, F1, Precision, Recall, AUC
 'eval_roc_auc': 0.9408,
 ```
 
-[Confusion matrix](https://huggingface.co/AdamCodd/distilroberta-nsfw-prompt-stable-diffusion/resolve/main/Confusion_matrix.png):
+[Confusion matrix](https://huggingface.co/AdamCodd/distilroberta-nsfw-prompt-stable-diffusion/resolve/V1/Confusion_matrix.png):
 
 [[184931  23859]