Upload folder using huggingface_hub

config.json

@@ -20,36 +20,25 @@
       "group_0": {
         "format": "int-quantized",
         "input_activations": {
-          "actorder": null,
-          "block_structure": null,
           "dynamic": true,
           "group_size": null,
           "num_bits": 8,
-          "observer": null,
-          "observer_kwargs": {},
-          "scale_dtype": null,
           "strategy": "token",
           "symmetric": false,
-          "type": "int",
-          "zp_dtype": "torch.int8"
+          "type": "int"
         },
         "output_activations": null,
         "targets": [
           "Linear"
         ],
         "weights": {
-          "actorder": null,
-          "block_structure": null,
           "dynamic": false,
           "group_size": null,
           "num_bits": 8,
           "observer": "memoryless_minmax",
-          "observer_kwargs": {},
-          "scale_dtype": null,
           "strategy": "channel",
           "symmetric": true,
-          "type": "int",
-          "zp_dtype": null
+          "type": "int"
         }
       }
     },
@@ -59,11 +48,12 @@
       "lm_head"
     ],
     "kv_cache_scheme": null,
+    "moe_sparsity_config": null,
     "quant_method": "compressed-tensors",
     "quantization_status": "compressed",
     "sparsity_config": {},
     "transform_config": {},
-    "version": "0.19.1a20261014"
+    "version": "0.19.1a20261015"
   },
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7200394ac39e13e7729b6ad6c8e604058a0c44910e96e8df629bd085471f0a0
+oid sha256:632a0d850f196be09420b1a643aa88301c4c9a67907e1cd1360fc7f680a0e6bf
 size 1232041608

recipe.yaml

@@ -14,32 +14,10 @@ quant_stage:
       config_groups:
         group_0:
           targets: [Linear]
-          weights:
-            num_bits: 8
-            type: int
-            symmetric: true
-            group_size: null
-            strategy: channel
-            block_structure: null
-            dynamic: false
-            actorder: null
-            scale_dtype: null
-            zp_dtype: null
-            observer: memoryless_minmax
-            observer_kwargs: {}
-          input_activations:
-            num_bits: 8
-            type: int
-            symmetric: false
-            group_size: null
-            strategy: token
-            block_structure: null
-            dynamic: true
-            actorder: null
-            scale_dtype: null
-            zp_dtype: torch.int8
-            observer: null
-            observer_kwargs: {}
+          weights: {num_bits: 8, type: int, symmetric: true, group_size: null, strategy: channel,
+            dynamic: false, observer: memoryless_minmax}
+          input_activations: {num_bits: 8, type: int, symmetric: false, group_size: null,
+            strategy: token, dynamic: true}
           output_activations: null
           format: null
       targets: [Linear]