New GPTQ with no groupsize.

OpenAssistant-SFT-7-Llama-30B-GPTQ-4bit.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3200d0314235e82313021303fd2be12e86a819deb6bf951d8179c84d7dd5acfd
+size 16940554392

quantize_config.json

@@ -0,0 +1,8 @@
+{
+  "bits": 4,
+  "group_size": -1,
+  "damp_percent": 0.01,
+  "desc_act": true,
+  "sym": true,
+  "true_sequential": true
+}