Upload folder using huggingface_hub

config.json

@@ -28,7 +28,7 @@
           "Linear"
         ],
         "weights": {
-          "actorder": "weight",
+          "actorder": "group",
           "block_structure": null,
           "dynamic": false,
           "group_size": 128,
@@ -42,7 +42,7 @@
       }
     },
     "format": "pack-quantized",
-    "global_compression_ratio": 1.883165566487463,
+    "global_compression_ratio": 1.8833636632816793,
     "ignore": [
       "lm_head"
     ],
@@ -51,7 +51,7 @@
     "quantization_status": "compressed",
     "sparsity_config": {
       "format": "dense",
-      "global_sparsity": 0.14292254340795876,
+      "global_sparsity": 0.1407252015594666,
       "ignore": [],
       "registry_requires_subclass": false,
       "sparsity_structure": "unstructured",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be61f74ba747c57efc6f2f920e60ef74e690fc46f0525ddfab231e2a58661e0a
-size 761968800
+oid sha256:a526374315ca3ab080a4c930dac9144a8a2a738a69ba9446ef6027e9fd2ab1e9
+size 763563248

recipe.yaml

@@ -5,5 +5,5 @@ quant_stage:
       config_groups:
         group_0:
           weights: {num_bits: 4, type: int, symmetric: true, strategy: group, group_size: 128,
-            actorder: weight}
+            actorder: group}
           targets: [Linear]

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 2048,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {