Update README.md
Browse files
README.md
CHANGED
|
@@ -22,7 +22,10 @@ inference:
|
|
| 22 |
|
| 23 |
# BLOOM-560m RLHF SD2 Prompter
|
| 24 |
|
|
|
|
|
|
|
| 25 |
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
|
|
|
|
| 26 |
```
|
| 27 |
batch_size = 16
|
| 28 |
learning_rate = 0.001 # this is why I didn't have to spend _forever_ on it
|
|
|
|
| 22 |
|
| 23 |
# BLOOM-560m RLHF SD2 Prompter
|
| 24 |
|
| 25 |
+
**COLAB DEMO INCLUDING STABLE DIFFUSION: https://colab.research.google.com/github/aicrumb/doohickey/blob/main/rlhf_prompt_tuner.ipynb**
|
| 26 |
+
|
| 27 |
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
|
| 28 |
+
|
| 29 |
```
|
| 30 |
batch_size = 16
|
| 31 |
learning_rate = 0.001 # this is why I didn't have to spend _forever_ on it
|