Upload folder using huggingface_hub

config.json

@@ -20,25 +20,36 @@
       "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"
+          "type": "int",
+          "zp_dtype": "torch.int8"
         },
         "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"
+          "type": "int",
+          "zp_dtype": null
         }
       }
     },
@@ -48,12 +59,11 @@
       "lm_head"
     ],
     "kv_cache_scheme": 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:c3c4a3972ad4a41508e28905ef4caabff4ff44986aa4bd0d8320fcf88b5ae046
+oid sha256:bf85937fc50c3cc69521a36ace3825bb2c0047b42af0524bbf980134a47e59c0
 size 1232041608

recipe.yaml

@@ -14,10 +14,32 @@ quant_stage:
       config_groups:
         group_0:
           targets: [Linear]
-          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}
+          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: {}
           output_activations: null
           format: null
       targets: [Linear]