Instructions to use Technotech/MagicPrompt-tinystories-33M-epoch10-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Technotech/MagicPrompt-tinystories-33M-epoch10-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("models/TinyStories-33M") model = PeftModel.from_pretrained(base_model, "Technotech/MagicPrompt-tinystories-33M-epoch10-lora") - Notebooks
- Google Colab
- Kaggle
Commit ·
f8f9da2
1
Parent(s): ea74db4
Update README.md
Browse files
README.md
CHANGED
|
@@ -12,7 +12,7 @@ tags:
|
|
| 12 |
|
| 13 |
## Info
|
| 14 |
|
| 15 |
-
Magic prompt completion model trained on a dataset
|
| 16 |
|
| 17 |
Model seems to be pretty decent for 33M params due to the TinyStories base, but it clearly lacks much of an understanding of pretty much anything. Still, considering the size, I think it's decent. Whether you would use this over a small GPT-2 based model is up to you.
|
| 18 |
|
|
|
|
| 12 |
|
| 13 |
## Info
|
| 14 |
|
| 15 |
+
Magic prompt completion model trained on a dataset of 80k Stable Diffusion prompts. Base model: TinyStories-33M. Inspired by [MagicPrompt-Stable-Diffusion](https://huggingface.co/Gustavosta/MagicPrompt-Stable-Diffusion).
|
| 16 |
|
| 17 |
Model seems to be pretty decent for 33M params due to the TinyStories base, but it clearly lacks much of an understanding of pretty much anything. Still, considering the size, I think it's decent. Whether you would use this over a small GPT-2 based model is up to you.
|
| 18 |
|