Upload Qwen3ForCausalLM

config.json

@@ -19,7 +19,7 @@
   "num_key_value_heads": 8,
   "quantization_config": {
     "config_groups": {
-      "group_1": {
+      "group_0": {
         "input_activations": {
           "actorder": null,
           "block_structure": null,
@@ -50,14 +50,15 @@
         }
       }
     },
-    "format": "pack-quantized",
+    "format": "int-quantized",
     "global_compression_ratio": null,
     "ignore": [
       "lm_head"
     ],
     "kv_cache_scheme": null,
     "quant_method": "compressed-tensors",
-    "quantization_status": "compressed"
+    "quantization_status": "compressed",
+    "sparsity_config": {}
   },
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
@@ -69,4 +70,4 @@
   "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 151936
-}
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dbfdc6bcd07183093c48cf1b47eca099b99e534d0e147e0ee656278993d95e7
-size 762101160
+oid sha256:df89ca56d8fa8a03a708fc1e9ebab6d4061561e5e00b21e42a3f323e7c209d9c
+size 758636928