Instructions to use Franzabner/mixed-quant-epi with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Franzabner/mixed-quant-epi with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Franzabner/mixed-quant-epi", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Add placeholder README
Browse files
README.md
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
tags:
|
| 4 |
+
- quantization
|
| 5 |
+
- energy-efficiency
|
| 6 |
+
---
|
| 7 |
+
|
| 8 |
+
# mixed-quant-epi
|
| 9 |
+
|
| 10 |
+
Per-layer mixed quantization evaluated by EPI -- accuracy vs energy Pareto frontier
|
| 11 |
+
|
| 12 |
+
> Placeholder -- full content coming soon. See the [GitHub repo](https://github.com/Franzabner/mixed-quant-epi) for current work.
|