Update README.md
Browse files
README.md
CHANGED
|
@@ -5,6 +5,7 @@ library_name: transformers
|
|
| 5 |
---
|
| 6 |
Converted with https://github.com/qwopqwop200/GPTQ-for-LLaMa
|
| 7 |
All models tested on A100-80G
|
|
|
|
| 8 |
|
| 9 |
Installation instructions as mentioned in above repo:
|
| 10 |
1. Install Anaconda and create a venv with python 3.8
|
|
|
|
| 5 |
---
|
| 6 |
Converted with https://github.com/qwopqwop200/GPTQ-for-LLaMa
|
| 7 |
All models tested on A100-80G
|
| 8 |
+
*Conversion may require lot of RAM, LLaMA-7b takes ~12 GB, 13b around 21 GB, 30b around 62 and 65b takes more than 120 GB of RAM.
|
| 9 |
|
| 10 |
Installation instructions as mentioned in above repo:
|
| 11 |
1. Install Anaconda and create a venv with python 3.8
|