Upload folder using huggingface_hub

config.json

@@ -76,6 +76,26 @@
     "format": "pack-quantized",
     "global_compression_ratio": null,
     "ignore": [
+      "model.layers.0.conv.in_proj",
+      "model.layers.0.conv.out_proj",
+      "model.layers.1.conv.in_proj",
+      "model.layers.1.conv.out_proj",
+      "model.layers.3.conv.in_proj",
+      "model.layers.3.conv.out_proj",
+      "model.layers.4.conv.in_proj",
+      "model.layers.4.conv.out_proj",
+      "model.layers.6.conv.in_proj",
+      "model.layers.6.conv.out_proj",
+      "model.layers.7.conv.in_proj",
+      "model.layers.7.conv.out_proj",
+      "model.layers.9.conv.in_proj",
+      "model.layers.9.conv.out_proj",
+      "model.layers.11.conv.in_proj",
+      "model.layers.11.conv.out_proj",
+      "model.layers.13.conv.in_proj",
+      "model.layers.13.conv.out_proj",
+      "model.layers.15.conv.in_proj",
+      "model.layers.15.conv.out_proj",
       "lm_head"
     ],
     "kv_cache_scheme": null,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16d898a9185e038b62f3c76404c6151dd7c4f27286686110c1a32ae59605ac67
-size 1071353296
+oid sha256:18f84bbf9b45b9a9a03378d301e588bab8ccad63ab216b5e2382042a2cc4e833
+size 1320385384

recipe.yaml

@@ -2,7 +2,7 @@ default_stage:
   default_modifiers:
     AWQModifier:
       targets: [Linear]
-      ignore: [lm_head]
+      ignore: [lm_head, 're:.*conv\.in_proj.*', 're:.*conv\.out_proj.*']
       scheme: W4A16
       mappings:
       - smooth_layer: re:.*layers\.(2|5|8|10|12|14)\.operator_norm$