Upload model files

config.json

@@ -16,7 +16,7 @@
   "model_type": "llama",
   "num_attention_heads": 4,
   "num_hidden_layers": 2,
-  "num_key_value_heads": 4,
+  "num_key_value_heads": 2,
   "pretraining_tp": 1,
   "quantization_config": {
     "algo_config": null,
@@ -36,7 +36,7 @@
       "weight": {
         "ch_axis": 1,
         "dtype": "uint4",
-        "group_size": 128,
+        "group_size": 32,
         "is_dynamic": false,
         "observer_cls": "PerGroupMinMaxObserver",
         "qscheme": "per_group",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f29a95ff0e7c5e6df73ab3d6673a736bed4b48d7b4db4c39d70af0952c56bc79
-size 19496088
+oid sha256:6adccba13f3eb67040fc2deb588948bca63a605b4e4701354b2c9a31882d13cd
+size 20086792