update readme
Browse files
README.md
CHANGED
|
@@ -2,6 +2,7 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model:
|
| 4 |
- rhymes-ai/Aria
|
|
|
|
| 5 |
---
|
| 6 |
|
| 7 |
This repository offers int8 quantized weights of the [rhymes-ai/Aria](https://huggingface.co/rhymes-ai/Aria) model utilizing the [TorchAO](https://github.com/pytorch/ao) quantization framework. It now supports inference within 30GB of GPU memory.
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model:
|
| 4 |
- rhymes-ai/Aria
|
| 5 |
+
base_model_relation: quantized
|
| 6 |
---
|
| 7 |
|
| 8 |
This repository offers int8 quantized weights of the [rhymes-ai/Aria](https://huggingface.co/rhymes-ai/Aria) model utilizing the [TorchAO](https://github.com/pytorch/ao) quantization framework. It now supports inference within 30GB of GPU memory.
|