Commit
•
ba126fb
1
Parent(s):
c7f1973
Add missing quant_config.json for compatibility with vLLM backends out of the box. (#1)
Browse files- Add missing quant_config.json for compatibility with vLLM backends out of the box. (2a52ed5f3bf387eb0c2ee056c19fc46ad9b6afd8)
Co-authored-by: Vaclav Kosar <[email protected]>
- quant_config.json +6 -0
quant_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"zero_point": true,
|
3 |
+
"q_group_size": 128,
|
4 |
+
"w_bit": 4,
|
5 |
+
"version": "GEMM"
|
6 |
+
}
|