Update README.md
Browse files
README.md
CHANGED
|
@@ -2,6 +2,8 @@ Description
|
|
| 2 |
---
|
| 3 |
imatrix.dat and q4-k-s just for en or zh(beacuse of the data I used to imatrix)
|
| 4 |
---
|
|
|
|
|
|
|
| 5 |
I just made a gguf file for my own use, and then share it, please support the original author [haoranxu](https://huggingface.co/haoranxu)
|
| 6 |
---
|
| 7 |
This repo contains GGUF format model files for **[haoranxu/ALMA-7B-R](https://huggingface.co/haoranxu/ALMA-7B-R)**
|
|
|
|
| 2 |
---
|
| 3 |
imatrix.dat and q4-k-s just for en or zh(beacuse of the data I used to imatrix)
|
| 4 |
---
|
| 5 |
+
For this models, it seems that it would be better to quantize directly without using imatrix.
|
| 6 |
+
---
|
| 7 |
I just made a gguf file for my own use, and then share it, please support the original author [haoranxu](https://huggingface.co/haoranxu)
|
| 8 |
---
|
| 9 |
This repo contains GGUF format model files for **[haoranxu/ALMA-7B-R](https://huggingface.co/haoranxu/ALMA-7B-R)**
|