Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
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
|
| 2 |
```
|
| 3 |
batch_size = 8
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: bigscience-bloom-rail-1.0
|
| 3 |
+
tags:
|
| 4 |
+
- stable-diffusion
|
| 5 |
+
- diffusion
|
| 6 |
+
model-index:
|
| 7 |
+
- name: bloom-560m-RLHF-SD2-prompter
|
| 8 |
+
results: []
|
| 9 |
+
|
| 10 |
+
datasets:
|
| 11 |
+
- Gustavosta/Stable-Diffusion-Prompts
|
| 12 |
+
|
| 13 |
+
widget:
|
| 14 |
+
- text: "<s>Prompt:"
|
| 15 |
+
|
| 16 |
+
inference:
|
| 17 |
+
parameters:
|
| 18 |
+
eos_token_id: 2
|
| 19 |
+
max_length: 128
|
| 20 |
+
---
|
| 21 |
+
|
| 22 |
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
|
| 23 |
```
|
| 24 |
batch_size = 8
|