Upload folder using huggingface_hub

config.json

@@ -20,18 +20,13 @@
       "group_0": {
         "format": "nvfp4-pack-quantized",
         "input_activations": {
-          "actorder": null,
-          "block_structure": null,
           "dynamic": "local",
           "group_size": 16,
           "num_bits": 4,
           "observer": "minmax",
-          "observer_kwargs": {},
-          "scale_dtype": null,
           "strategy": "tensor_group",
           "symmetric": true,
-          "type": "float",
-          "zp_dtype": null
+          "type": "float"
         },
         "output_activations": null,
         "targets": [
@@ -39,53 +34,38 @@
           "re:.*\\.(gate|up)_proj$"
         ],
         "weights": {
-          "actorder": null,
-          "block_structure": null,
           "dynamic": false,
           "group_size": 16,
           "num_bits": 4,
           "observer": "memoryless_minmax",
-          "observer_kwargs": {},
           "scale_dtype": "torch.float8_e4m3fn",
           "strategy": "tensor_group",
           "symmetric": true,
-          "type": "float",
-          "zp_dtype": null
+          "type": "float"
         }
       },
       "group_1": {
         "format": "float-quantized",
         "input_activations": {
-          "actorder": null,
-          "block_structure": null,
           "dynamic": true,
           "group_size": null,
           "num_bits": 8,
-          "observer": null,
-          "observer_kwargs": {},
-          "scale_dtype": null,
           "strategy": "token",
           "symmetric": true,
-          "type": "float",
-          "zp_dtype": null
+          "type": "float"
         },
         "output_activations": null,
         "targets": [
           "re:.*\\.down_proj$"
         ],
         "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": "float",
-          "zp_dtype": null
+          "type": "float"
         }
       }
     },
@@ -95,11 +75,12 @@
       "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 sha256:52657b4907a8c0e4084b532b53a5ae17e13efae1b1ac1dd8426f68162a57c99d
+oid sha256:52097402bc79a2ad215a71ff1a473d572674162ea7a60bbb4cf55b65815b01f9
 size 918504936

recipe.yaml

@@ -4,62 +4,18 @@ quant_stage:
       config_groups:
         group_0:
           targets: ['re:.*\.down_proj$']
-          weights:
-            num_bits: 8
-            type: float
-            symmetric: true
-            group_size: null
-            strategy: channel
-            block_structure: null
-            dynamic: false
-            actorder: null
-            scale_dtype: null
-            zp_dtype: null
-            observer: memoryless_minmax
-            observer_kwargs: {}
-          input_activations:
-            num_bits: 8
-            type: float
-            symmetric: true
-            group_size: null
-            strategy: token
-            block_structure: null
-            dynamic: true
-            actorder: null
-            scale_dtype: null
-            zp_dtype: null
-            observer: null
-            observer_kwargs: {}
+          weights: {num_bits: 8, type: float, symmetric: true, group_size: null, strategy: channel,
+            dynamic: false, observer: memoryless_minmax}
+          input_activations: {num_bits: 8, type: float, symmetric: true, group_size: null,
+            strategy: token, dynamic: true}
           output_activations: null
           format: null
         group_1:
           targets: ['re:.*self_attn\.(k|o|q|v)_proj$', 're:.*\.(gate|up)_proj$']
-          weights:
-            num_bits: 4
-            type: float
-            symmetric: true
-            group_size: 16
-            strategy: tensor_group
-            block_structure: null
-            dynamic: false
-            actorder: null
-            scale_dtype: torch.float8_e4m3fn
-            zp_dtype: null
-            observer: memoryless_minmax
-            observer_kwargs: {}
-          input_activations:
-            num_bits: 4
-            type: float
-            symmetric: true
-            group_size: 16
-            strategy: tensor_group
-            block_structure: null
-            dynamic: local
-            actorder: null
-            scale_dtype: null
-            zp_dtype: null
-            observer: minmax
-            observer_kwargs: {}
+          weights: {num_bits: 4, type: float, symmetric: true, group_size: 16, strategy: tensor_group,
+            dynamic: false, scale_dtype: torch.float8_e4m3fn, observer: memoryless_minmax}
+          input_activations: {num_bits: 4, type: float, symmetric: true, group_size: 16, strategy: tensor_group,
+            dynamic: local, observer: minmax}
           output_activations: null
           format: null
       targets: [Linear]