From d4e1890f8a07189623dfac3b7bef7db6a7288019 Mon Sep 17 00:00:00 2001 From: "first_name.last_name" Date: Thu, 25 Apr 2024 22:02:18 +0000 Subject: [PATCH] adding quant config --- quant_config.json | 6 ++++++ 1 file changed, 6 insertions(+) create mode 100644 quant_config.json diff --git a/quant_config.json b/quant_config.json new file mode 100644 index 0000000..4002036 --- /dev/null +++ b/quant_config.json @@ -0,0 +1,6 @@ +{ + "zero_point": true, + "q_group_size": 128, + "w_bit": 4, + "version": "GEMM" +} \ No newline at end of file