Update README.md
Browse files
README.md
CHANGED
|
@@ -11,6 +11,16 @@ tags:
|
|
| 11 |
license: cc-by-nc-4.0
|
| 12 |
---
|
| 13 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
<!-- description start -->
|
| 15 |
## Description
|
| 16 |
|
|
|
|
| 11 |
license: cc-by-nc-4.0
|
| 12 |
---
|
| 13 |
|
| 14 |
+
|
| 15 |
+
<br/><br/>
|
| 16 |
+
4.5bpw/h6 exl2 quantization of [NeverSleep/NoromaidxOpenGPT4-2](https://huggingface.co/NeverSleep/NoromaidxOpenGPT4-2) using default exllamav2 calibration dataset.
|
| 17 |
+
|
| 18 |
+
Fits in 32GB VRAM with 32k+ context (Q4cache)
|
| 19 |
+
|
| 20 |
+
---
|
| 21 |
+
|
| 22 |
+
**ORIGINAL CARD:**
|
| 23 |
+
|
| 24 |
<!-- description start -->
|
| 25 |
## Description
|
| 26 |
|