Upload Qwen3ForCausalLM

config.json

@@ -65,6 +65,14 @@
           "base_config": {
             "_data": {
               "group_size": 128,
+              "int4_choose_qparams_algorithm": {
+                "_data": "TINYGEMM",
+                "_type": "Int4ChooseQParamsAlgorithm"
+              },
+              "int4_packing_format": {
+                "_data": "PLAIN",
+                "_type": "Int4PackingFormat"
+              },
               "layout": {
                 "_data": {
                   "inner_k_tiles": 8
@@ -72,10 +80,6 @@
                 "_type": "TensorCoreTiledLayout",
                 "_version": 1
               },
-              "packing_format": {
-                "_data": "PLAIN",
-                "_type": "PackingFormat"
-              },
               "preserve_zero": null,
               "set_inductor_config": true,
               "use_hqq": false,

pytorch_model-00001-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4299aa4727ee8efc6db4393b7aa6618ef11a5f07013410f5359c2ebc80f3d32c
+oid sha256:20da9306eb208967f598cf115a672b36d68ca5853d8ee0c2fc6904b566d1732e
 size 4938272073

pytorch_model-00002-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:384fdd2533f4ae69c02f82295132283b76bd1144fcb8f1f9052e495e36c14d53
+oid sha256:760a161b40a3e47adedecad1feeac1c8b6b24b1f3f1b23a58e5b785b44df736e
 size 330623983