Updated model.pt
Browse files
README.md
CHANGED
|
@@ -20,7 +20,7 @@ A: ✨ This is because the author did not train this model by regressing these
|
|
| 20 |
|
| 21 |
A: 🤐 All training data (~55K) are obtained from PIXIV. 🤐
|
| 22 |
|
| 23 |
-
**Q4: Why this model is trained
|
| 24 |
|
| 25 |
A: 👾 The author initially hoped to finetune the [Anything-V5](https://civitai.com/models/9409?modelVersionId=90854) model by RLHF based on [D3PO (arxiv.2311.13231)](https://github.com/yk7333/d3po), and this model is designed to play the role of a multi-objective reward model. And for fun :)👾
|
| 26 |
|
|
|
|
| 20 |
|
| 21 |
A: 🤐 All training data (~55K) are obtained from PIXIV. 🤐
|
| 22 |
|
| 23 |
+
**Q4: Why this model is trained.**
|
| 24 |
|
| 25 |
A: 👾 The author initially hoped to finetune the [Anything-V5](https://civitai.com/models/9409?modelVersionId=90854) model by RLHF based on [D3PO (arxiv.2311.13231)](https://github.com/yk7333/d3po), and this model is designed to play the role of a multi-objective reward model. And for fun :)👾
|
| 26 |
|
scorer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6e0fbd38c11cf659395c45da95811803b3b50a6d32d3cb0b489c8ed3ef0cadeb
|
| 3 |
+
size 373114570
|