Upload Qwen3ForCausalLM

config.json

@@ -20,7 +20,18 @@
   "quantization_config": {
     "config_groups": {
       "group_0": {
-        "input_activations": null,
+        "input_activations": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": true,
+          "group_size": null,
+          "num_bits": 8,
+          "observer": null,
+          "observer_kwargs": {},
+          "strategy": "token",
+          "symmetric": true,
+          "type": "int"
+        },
         "output_activations": null,
         "targets": [
           "Linear"
@@ -29,17 +40,17 @@
           "actorder": null,
           "block_structure": null,
           "dynamic": false,
-          "group_size": 128,
-          "num_bits": 4,
+          "group_size": null,
+          "num_bits": 8,
           "observer": "minmax",
           "observer_kwargs": {},
-          "strategy": "group",
+          "strategy": "channel",
           "symmetric": true,
           "type": "int"
         }
       }
     },
-    "format": "pack-quantized",
+    "format": "int-quantized",
     "global_compression_ratio": null,
     "ignore": [
       "lm_head"

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28f4e35de4c9cfcbd67a6d655fdd2d9dc4b7da11bb6ad1647f580f0b1c2a7640
-size 856637120
+oid sha256:7acaff9792cb5d9456a90130d4ecaa2e2c5f55d994fae6811daa5b256c6edafb
+size 1064427600