Update README.md
Browse files
README.md
CHANGED
|
@@ -11,6 +11,18 @@ tags:
|
|
| 11 |
- merge
|
| 12 |
|
| 13 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
# Miqu-MS-70B
|
| 15 |
|
| 16 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
|
|
|
| 11 |
- merge
|
| 12 |
|
| 13 |
---
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
<br/><br/>
|
| 17 |
+
3.2bpw/h6 exl2 quantization of [Undi95/Miqu-MS-70B](https://huggingface.co/Undi95/Miqu-MS-70B) using default exllamav2 calibration dataset.
|
| 18 |
+
|
| 19 |
+
Fits in 32GB VRAM with 32k+ context (Q4cache)
|
| 20 |
+
|
| 21 |
+
---
|
| 22 |
+
|
| 23 |
+
**ORIGINAL CARD:**
|
| 24 |
+
|
| 25 |
+
|
| 26 |
# Miqu-MS-70B
|
| 27 |
|
| 28 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|