Upload folder using huggingface_hub

config.json

@@ -25,13 +25,18 @@
           "Linear"
         ],
         "weights": {
+          "actorder": null,
+          "block_structure": null,
           "dynamic": false,
           "group_size": null,
           "num_bits": 4,
           "observer": "memoryless_minmax",
+          "observer_kwargs": {},
+          "scale_dtype": null,
           "strategy": "channel",
           "symmetric": true,
-          "type": "int"
+          "type": "int",
+          "zp_dtype": null
         }
       }
     },
@@ -41,19 +46,24 @@
       "lm_head"
     ],
     "kv_cache_scheme": {
+      "actorder": null,
+      "block_structure": null,
       "dynamic": false,
       "group_size": null,
       "num_bits": 8,
+      "observer": null,
+      "observer_kwargs": {},
+      "scale_dtype": null,
       "strategy": "tensor",
       "symmetric": true,
-      "type": "float"
+      "type": "float",
+      "zp_dtype": null
     },
-    "moe_sparsity_config": null,
     "quant_method": "compressed-tensors",
     "quantization_status": "compressed",
     "sparsity_config": {},
     "transform_config": {},
-    "version": "0.19.1.dev39+g7195055d"
+    "version": "0.19.1.dev0"
   },
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,

generation_config.json

@@ -3,5 +3,5 @@
   "eos_token_id": 2,
   "max_length": 2048,
   "pad_token_id": 0,
-  "transformers_version": "5.20.2"
+  "transformers_version": "5.17.0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:027cde78b56ab6ff785459794ab75a6e31243bc7cffb0a3372792806683d8e9c
+oid sha256:5345897c2204a46f8adbf5f48456e31d7ddedc0732b0da50b82afce40822508a
 size 747622872

recipe.yaml

@@ -4,15 +4,37 @@ quant_stage:
       config_groups:
         group_0:
           targets: [Linear]
-          weights: {num_bits: 4, type: int, symmetric: true, group_size: null, strategy: channel,
-            dynamic: false, observer: memoryless_minmax}
+          weights:
+            num_bits: 4
+            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: null
           output_activations: null
           format: null
       targets: [Linear]
       ignore: [lm_head]
-      kv_cache_scheme: {num_bits: 8, type: float, symmetric: true, group_size: null, strategy: tensor,
-        dynamic: false}
+      kv_cache_scheme:
+        num_bits: 8
+        type: float
+        symmetric: true
+        group_size: null
+        strategy: tensor
+        block_structure: null
+        dynamic: false
+        actorder: null
+        scale_dtype: null
+        zp_dtype: null
+        observer: null
+        observer_kwargs: {}
       bypass_divisibility_checks: false
       requires_calibration_data: true
       block_size: 128