Commit
•
d2214d5
1
Parent(s):
ee0081f
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,2 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
Attention quantization: HQQ 4-bit, groupsize 64, compress zero, compress scale with groupsize 256 \
|
| 2 |
Experts quantization: HQQ 3-bit, groupsize 64, compress zero, compress scale with groupsize 128
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
- fr
|
| 6 |
+
- it
|
| 7 |
+
- de
|
| 8 |
+
- es
|
| 9 |
+
library_name: transformers
|
| 10 |
+
tags:
|
| 11 |
+
- mixtral
|
| 12 |
+
- text-generation-inference
|
| 13 |
+
---
|
| 14 |
Attention quantization: HQQ 4-bit, groupsize 64, compress zero, compress scale with groupsize 256 \
|
| 15 |
Experts quantization: HQQ 3-bit, groupsize 64, compress zero, compress scale with groupsize 128
|