Update README.md
Browse files
README.md
CHANGED
|
@@ -204,6 +204,11 @@ The following are the minimum/recommended GPU requirements for running inference
|
|
| 204 |
* Examples: Nvidia RTX 3070, RTX 3080 or T4
|
| 205 |
|
| 206 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 207 |
### Citation
|
| 208 |
|
| 209 |
```none
|
|
|
|
| 204 |
* Examples: Nvidia RTX 3070, RTX 3080 or T4
|
| 205 |
|
| 206 |
|
| 207 |
+
## Effect of Quantization
|
| 208 |
+
|
| 209 |
+
We have seen 2.6% drop in score (to 0.338) for the same model quantized 4bit
|
| 210 |
+
|
| 211 |
+
|
| 212 |
### Citation
|
| 213 |
|
| 214 |
```none
|