adding quant config

2024-04-18 17:29:56 +00:00
parent cef4e59fba
commit 92a9d27fb6
1 changed files with 6 additions and 0 deletions
--- a/quant_config.json
+++ b/quant_config.json
@@ -0,0 +1,6 @@
+{
+  "zero_point": true,
+  "q_group_size": 128,
+  "w_bit": 4,
+  "version": "GEMM"
+}