Update README.md
Browse files
README.md
CHANGED
@@ -23,7 +23,7 @@ inference:
|
|
23 |
Using RLHF (Reinforcement Learning from Human Feedback) to finetune [mrm8488/bloom-560m-finetuned-sd-prompts](https://hf.co/mrm8488/bloom-560m-finetuned-sd-prompts) further for SD2.0
|
24 |
```
|
25 |
batch_size = 16
|
26 |
-
learning_rate = 0.001
|
27 |
```
|
28 |
|
29 |
Generate extension with "\<s>Prompt: " and whatever your normal prompt is.
|
|
|
23 |
Using RLHF (Reinforcement Learning from Human Feedback) to finetune [mrm8488/bloom-560m-finetuned-sd-prompts](https://hf.co/mrm8488/bloom-560m-finetuned-sd-prompts) further for SD2.0
|
24 |
```
|
25 |
batch_size = 16
|
26 |
+
learning_rate = 0.001 # this is why I didn't have to spend _forever_ on it
|
27 |
```
|
28 |
|
29 |
Generate extension with "\<s>Prompt: " and whatever your normal prompt is.
|