Upload folder using huggingface_hub

config.json

@@ -60,6 +60,54 @@
     "format": "nvfp4-pack-quantized",
     "global_compression_ratio": null,
     "ignore": [
+      "model.layers.0.mlp.gate",
+      "model.layers.1.mlp.gate",
+      "model.layers.2.mlp.gate",
+      "model.layers.3.mlp.gate",
+      "model.layers.4.mlp.gate",
+      "model.layers.5.mlp.gate",
+      "model.layers.6.mlp.gate",
+      "model.layers.7.mlp.gate",
+      "model.layers.8.mlp.gate",
+      "model.layers.9.mlp.gate",
+      "model.layers.10.mlp.gate",
+      "model.layers.11.mlp.gate",
+      "model.layers.12.mlp.gate",
+      "model.layers.13.mlp.gate",
+      "model.layers.14.mlp.gate",
+      "model.layers.15.mlp.gate",
+      "model.layers.16.mlp.gate",
+      "model.layers.17.mlp.gate",
+      "model.layers.18.mlp.gate",
+      "model.layers.19.mlp.gate",
+      "model.layers.20.mlp.gate",
+      "model.layers.21.mlp.gate",
+      "model.layers.22.mlp.gate",
+      "model.layers.23.mlp.gate",
+      "model.layers.24.mlp.gate",
+      "model.layers.25.mlp.gate",
+      "model.layers.26.mlp.gate",
+      "model.layers.27.mlp.gate",
+      "model.layers.28.mlp.gate",
+      "model.layers.29.mlp.gate",
+      "model.layers.30.mlp.gate",
+      "model.layers.31.mlp.gate",
+      "model.layers.32.mlp.gate",
+      "model.layers.33.mlp.gate",
+      "model.layers.34.mlp.gate",
+      "model.layers.35.mlp.gate",
+      "model.layers.36.mlp.gate",
+      "model.layers.37.mlp.gate",
+      "model.layers.38.mlp.gate",
+      "model.layers.39.mlp.gate",
+      "model.layers.40.mlp.gate",
+      "model.layers.41.mlp.gate",
+      "model.layers.42.mlp.gate",
+      "model.layers.43.mlp.gate",
+      "model.layers.44.mlp.gate",
+      "model.layers.45.mlp.gate",
+      "model.layers.46.mlp.gate",
+      "model.layers.47.mlp.gate",
       "lm_head"
     ],
     "kv_cache_scheme": null,

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:261387433864dde38de406aef129574caef5247125fb164e085b5eb24ff0982d
-size 5001811128
+oid sha256:3cc625c6fc82c8d84d196d3c9ec6c6813594ccb8321e1a1f29d6d2827c99a498
+size 5002279496

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e94ee2fc7fe3c27f90cca5eab2987ab50a6b6ca628900401c39a0dd4ef831525
-size 5001977392
+oid sha256:5512103702dd54a3c410f6a367e08cef8e1107faf3276bfb584f3195befad0fc
+size 5002724080

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a38450094e8370f3a2d329b4e8a3414f15c49b42263bf9d92efa8d31f02a8864
-size 5002279016
+oid sha256:5699f8c32a1254f67071924c40a7c2f26375001592c17d83f52fc4bcdc90a2d1
+size 5002036032

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9214cd1a5aa7c8cfcb65bc658be9073df94c7d81f5a39af8bc0cb7ad5b206e6
-size 3072570048
+oid sha256:cea1e3dbae26e04a2773b68450059c3bf3da633a00747be37c4f9b3a95cb3acb
+size 3089670712

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 18069370752
+    "total_size": 18087458304
   },
   "weight_map": {
     "lm_head.weight": "model-00004-of-00004.safetensors",
@@ -1542,10 +1542,7 @@
     "model.layers.0.mlp.experts.99.up_proj.weight_global_scale": "model-00001-of-00004.safetensors",
     "model.layers.0.mlp.experts.99.up_proj.weight_packed": "model-00001-of-00004.safetensors",
     "model.layers.0.mlp.experts.99.up_proj.weight_scale": "model-00001-of-00004.safetensors",
-    "model.layers.0.mlp.gate.input_global_scale": "model-00001-of-00004.safetensors",
-    "model.layers.0.mlp.gate.weight_global_scale": "model-00001-of-00004.safetensors",
-    "model.layers.0.mlp.gate.weight_packed": "model-00001-of-00004.safetensors",
-    "model.layers.0.mlp.gate.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate.weight": "model-00001-of-00004.safetensors",
     "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
     "model.layers.0.self_attn.k_proj.input_global_scale": "model-00001-of-00004.safetensors",
@@ -3102,10 +3099,7 @@
     "model.layers.1.mlp.experts.99.up_proj.weight_global_scale": "model-00001-of-00004.safetensors",
     "model.layers.1.mlp.experts.99.up_proj.weight_packed": "model-00001-of-00004.safetensors",
     "model.layers.1.mlp.experts.99.up_proj.weight_scale": "model-00001-of-00004.safetensors",
-    "model.layers.1.mlp.gate.input_global_scale": "model-00001-of-00004.safetensors",
-    "model.layers.1.mlp.gate.weight_global_scale": "model-00001-of-00004.safetensors",
-    "model.layers.1.mlp.gate.weight_packed": "model-00001-of-00004.safetensors",
-    "model.layers.1.mlp.gate.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate.weight": "model-00001-of-00004.safetensors",
     "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
     "model.layers.1.self_attn.k_proj.input_global_scale": "model-00001-of-00004.safetensors",
@@ -4662,10 +4656,7 @@
     "model.layers.10.mlp.experts.99.up_proj.weight_global_scale": "model-00001-of-00004.safetensors",
     "model.layers.10.mlp.experts.99.up_proj.weight_packed": "model-00001-of-00004.safetensors",
     "model.layers.10.mlp.experts.99.up_proj.weight_scale": "model-00001-of-00004.safetensors",
-    "model.layers.10.mlp.gate.input_global_scale": "model-00001-of-00004.safetensors",
-    "model.layers.10.mlp.gate.weight_global_scale": "model-00001-of-00004.safetensors",
-    "model.layers.10.mlp.gate.weight_packed": "model-00001-of-00004.safetensors",
-    "model.layers.10.mlp.gate.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.10.mlp.gate.weight": "model-00001-of-00004.safetensors",
     "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
     "model.layers.10.self_attn.k_proj.input_global_scale": "model-00001-of-00004.safetensors",
@@ -6222,10 +6213,7 @@
     "model.layers.11.mlp.experts.99.up_proj.weight_global_scale": "model-00001-of-00004.safetensors",
     "model.layers.11.mlp.experts.99.up_proj.weight_packed": "model-00001-of-00004.safetensors",
     "model.layers.11.mlp.experts.99.up_proj.weight_scale": "model-00001-of-00004.safetensors",
-    "model.layers.11.mlp.gate.input_global_scale": "model-00001-of-00004.safetensors",
-    "model.layers.11.mlp.gate.weight_global_scale": "model-00001-of-00004.safetensors",
-    "model.layers.11.mlp.gate.weight_packed": "model-00001-of-00004.safetensors",
-    "model.layers.11.mlp.gate.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.11.mlp.gate.weight": "model-00001-of-00004.safetensors",
     "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
     "model.layers.11.self_attn.k_proj.input_global_scale": "model-00001-of-00004.safetensors",
@@ -7230,10 +7218,10 @@
     "model.layers.12.mlp.experts.57.up_proj.weight_global_scale": "model-00001-of-00004.safetensors",
     "model.layers.12.mlp.experts.57.up_proj.weight_packed": "model-00001-of-00004.safetensors",
     "model.layers.12.mlp.experts.57.up_proj.weight_scale": "model-00001-of-00004.safetensors",
-    "model.layers.12.mlp.experts.58.down_proj.input_global_scale": "model-00001-of-00004.safetensors",
-    "model.layers.12.mlp.experts.58.down_proj.weight_global_scale": "model-00001-of-00004.safetensors",
-    "model.layers.12.mlp.experts.58.down_proj.weight_packed": "model-00001-of-00004.safetensors",
-    "model.layers.12.mlp.experts.58.down_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.12.mlp.experts.58.down_proj.input_global_scale": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.experts.58.down_proj.weight_global_scale": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.experts.58.down_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.experts.58.down_proj.weight_scale": "model-00002-of-00004.safetensors",
     "model.layers.12.mlp.experts.58.gate_proj.input_global_scale": "model-00001-of-00004.safetensors",
     "model.layers.12.mlp.experts.58.gate_proj.weight_global_scale": "model-00001-of-00004.safetensors",
     "model.layers.12.mlp.experts.58.gate_proj.weight_packed": "model-00001-of-00004.safetensors",
@@ -7242,18 +7230,18 @@
     "model.layers.12.mlp.experts.58.up_proj.weight_global_scale": "model-00001-of-00004.safetensors",
     "model.layers.12.mlp.experts.58.up_proj.weight_packed": "model-00001-of-00004.safetensors",
     "model.layers.12.mlp.experts.58.up_proj.weight_scale": "model-00001-of-00004.safetensors",
-    "model.layers.12.mlp.experts.59.down_proj.input_global_scale": "model-00001-of-00004.safetensors",
-    "model.layers.12.mlp.experts.59.down_proj.weight_global_scale": "model-00001-of-00004.safetensors",
-    "model.layers.12.mlp.experts.59.down_proj.weight_packed": "model-00001-of-00004.safetensors",
-    "model.layers.12.mlp.experts.59.down_proj.weight_scale": "model-00001-of-00004.safetensors",
-    "model.layers.12.mlp.experts.59.gate_proj.input_global_scale": "model-00001-of-00004.safetensors",
-    "model.layers.12.mlp.experts.59.gate_proj.weight_global_scale": "model-00001-of-00004.safetensors",
-    "model.layers.12.mlp.experts.59.gate_proj.weight_packed": "model-00001-of-00004.safetensors",
-    "model.layers.12.mlp.experts.59.gate_proj.weight_scale": "model-00001-of-00004.safetensors",
-    "model.layers.12.mlp.experts.59.up_proj.input_global_scale": "model-00001-of-00004.safetensors",
-    "model.layers.12.mlp.experts.59.up_proj.weight_global_scale": "model-00001-of-00004.safetensors",
-    "model.layers.12.mlp.experts.59.up_proj.weight_packed": "model-00001-of-00004.safetensors",
-    "model.layers.12.mlp.experts.59.up_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.12.mlp.experts.59.down_proj.input_global_scale": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.experts.59.down_proj.weight_global_scale": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.experts.59.down_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.experts.59.down_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.experts.59.gate_proj.input_global_scale": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.experts.59.gate_proj.weight_global_scale": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.experts.59.gate_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.experts.59.gate_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.experts.59.up_proj.input_global_scale": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.experts.59.up_proj.weight_global_scale": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.experts.59.up_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.experts.59.up_proj.weight_scale": "model-00002-of-00004.safetensors",
     "model.layers.12.mlp.experts.6.down_proj.input_global_scale": "model-00001-of-00004.safetensors",
     "model.layers.12.mlp.experts.6.down_proj.weight_global_scale": "model-00001-of-00004.safetensors",
     "model.layers.12.mlp.experts.6.down_proj.weight_packed": "model-00001-of-00004.safetensors",
@@ -7270,10 +7258,10 @@
     "model.layers.12.mlp.experts.60.down_proj.weight_global_scale": "model-00002-of-00004.safetensors",
     "model.layers.12.mlp.experts.60.down_proj.weight_packed": "model-00002-of-00004.safetensors",
     "model.layers.12.mlp.experts.60.down_proj.weight_scale": "model-00002-of-00004.safetensors",
-    "model.layers.12.mlp.experts.60.gate_proj.input_global_scale": "model-00001-of-00004.safetensors",
-    "model.layers.12.mlp.experts.60.gate_proj.weight_global_scale": "model-00001-of-00004.safetensors",
-    "model.layers.12.mlp.experts.60.gate_proj.weight_packed": "model-00001-of-00004.safetensors",
-    "model.layers.12.mlp.experts.60.gate_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.12.mlp.experts.60.gate_proj.input_global_scale": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.experts.60.gate_proj.weight_global_scale": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.experts.60.gate_proj.weight_packed": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.experts.60.gate_proj.weight_scale": "model-00002-of-00004.safetensors",
     "model.layers.12.mlp.experts.60.up_proj.input_global_scale": "model-00002-of-00004.safetensors",
     "model.layers.12.mlp.experts.60.up_proj.weight_global_scale": "model-00002-of-00004.safetensors",
     "model.layers.12.mlp.experts.60.up_proj.weight_packed": "model-00002-of-00004.safetensors",
@@ -7782,10 +7770,7 @@
     "model.layers.12.mlp.experts.99.up_proj.weight_global_scale": "model-00002-of-00004.safetensors",
     "model.layers.12.mlp.experts.99.up_proj.weight_packed": "model-00002-of-00004.safetensors",
     "model.layers.12.mlp.experts.99.up_proj.weight_scale": "model-00002-of-00004.safetensors",
-    "model.layers.12.mlp.gate.input_global_scale": "model-00001-of-00004.safetensors",
-    "model.layers.12.mlp.gate.weight_global_scale": "model-00001-of-00004.safetensors",
-    "model.layers.12.mlp.gate.weight_packed": "model-00001-of-00004.safetensors",
-    "model.layers.12.mlp.gate.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.12.mlp.gate.weight": "model-00001-of-00004.safetensors",
     "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
     "model.layers.12.self_attn.k_proj.input_global_scale": "model-00001-of-00004.safetensors",
@@ -9342,10 +9327,7 @@
     "model.layers.13.mlp.experts.99.up_proj.weight_global_scale": "model-00002-of-00004.safetensors",
     "model.layers.13.mlp.experts.99.up_proj.weight_packed": "model-00002-of-00004.safetensors",
     "model.layers.13.mlp.experts.99.up_proj.weight_scale": "model-00002-of-00004.safetensors",
-    "model.layers.13.mlp.gate.input_global_scale": "model-00002-of-00004.safetensors",
-    "model.layers.13.mlp.gate.weight_global_scale": "model-00002-of-00004.safetensors",
-    "model.layers.13.mlp.gate.weight_packed": "model-00002-of-00004.safetensors",
-    "model.layers.13.mlp.gate.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate.weight": "model-00002-of-00004.safetensors",
     "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
     "model.layers.13.self_attn.k_proj.input_global_scale": "model-00002-of-00004.safetensors",
@@ -10902,10 +10884,7 @@
     "model.layers.14.mlp.experts.99.up_proj.weight_global_scale": "model-00002-of-00004.safetensors",
     "model.layers.14.mlp.experts.99.up_proj.weight_packed": "model-00002-of-00004.safetensors",
     "model.layers.14.mlp.experts.99.up_proj.weight_scale": "model-00002-of-00004.safetensors",
-    "model.layers.14.mlp.gate.input_global_scale": "model-00002-of-00004.safetensors",
-    "model.layers.14.mlp.gate.weight_global_scale": "model-00002-of-00004.safetensors",
-    "model.layers.14.mlp.gate.weight_packed": "model-00002-of-00004.safetensors",
-    "model.layers.14.mlp.gate.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate.weight": "model-00002-of-00004.safetensors",
     "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
     "model.layers.14.self_attn.k_proj.input_global_scale": "model-00002-of-00004.safetensors",
@@ -12462,10 +12441,7 @@
     "model.layers.15.mlp.experts.99.up_proj.weight_global_scale": "model-00002-of-00004.safetensors",
     "model.layers.15.mlp.experts.99.up_proj.weight_packed": "model-00002-of-00004.safetensors",
     "model.layers.15.mlp.experts.99.up_proj.weight_scale": "model-00002-of-00004.safetensors",
-    "model.layers.15.mlp.gate.input_global_scale": "model-00002-of-00004.safetensors",
-    "model.layers.15.mlp.gate.weight_global_scale": "model-00002-of-00004.safetensors",
-    "model.layers.15.mlp.gate.weight_packed": "model-00002-of-00004.safetensors",
-    "model.layers.15.mlp.gate.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate.weight": "model-00002-of-00004.safetensors",
     "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
     "model.layers.15.self_attn.k_proj.input_global_scale": "model-00002-of-00004.safetensors",
@@ -14022,10 +13998,7 @@
     "model.layers.16.mlp.experts.99.up_proj.weight_global_scale": "model-00002-of-00004.safetensors",
     "model.layers.16.mlp.experts.99.up_proj.weight_packed": "model-00002-of-00004.safetensors",
     "model.layers.16.mlp.experts.99.up_proj.weight_scale": "model-00002-of-00004.safetensors",
-    "model.layers.16.mlp.gate.input_global_scale": "model-00002-of-00004.safetensors",
-    "model.layers.16.mlp.gate.weight_global_scale": "model-00002-of-00004.safetensors",
-    "model.layers.16.mlp.gate.weight_packed": "model-00002-of-00004.safetensors",
-    "model.layers.16.mlp.gate.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate.weight": "model-00002-of-00004.safetensors",
     "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
     "model.layers.16.self_attn.k_proj.input_global_scale": "model-00002-of-00004.safetensors",
@@ -15582,10 +15555,7 @@
     "model.layers.17.mlp.experts.99.up_proj.weight_global_scale": "model-00002-of-00004.safetensors",
     "model.layers.17.mlp.experts.99.up_proj.weight_packed": "model-00002-of-00004.safetensors",
     "model.layers.17.mlp.experts.99.up_proj.weight_scale": "model-00002-of-00004.safetensors",
-    "model.layers.17.mlp.gate.input_global_scale": "model-00002-of-00004.safetensors",
-    "model.layers.17.mlp.gate.weight_global_scale": "model-00002-of-00004.safetensors",
-    "model.layers.17.mlp.gate.weight_packed": "model-00002-of-00004.safetensors",
-    "model.layers.17.mlp.gate.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate.weight": "model-00002-of-00004.safetensors",
     "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
     "model.layers.17.self_attn.k_proj.input_global_scale": "model-00002-of-00004.safetensors",
@@ -17142,10 +17112,7 @@
     "model.layers.18.mlp.experts.99.up_proj.weight_global_scale": "model-00002-of-00004.safetensors",
     "model.layers.18.mlp.experts.99.up_proj.weight_packed": "model-00002-of-00004.safetensors",
     "model.layers.18.mlp.experts.99.up_proj.weight_scale": "model-00002-of-00004.safetensors",
-    "model.layers.18.mlp.gate.input_global_scale": "model-00002-of-00004.safetensors",
-    "model.layers.18.mlp.gate.weight_global_scale": "model-00002-of-00004.safetensors",
-    "model.layers.18.mlp.gate.weight_packed": "model-00002-of-00004.safetensors",
-    "model.layers.18.mlp.gate.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate.weight": "model-00002-of-00004.safetensors",
     "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
     "model.layers.18.self_attn.k_proj.input_global_scale": "model-00002-of-00004.safetensors",
@@ -18702,10 +18669,7 @@
     "model.layers.19.mlp.experts.99.up_proj.weight_global_scale": "model-00002-of-00004.safetensors",
     "model.layers.19.mlp.experts.99.up_proj.weight_packed": "model-00002-of-00004.safetensors",
     "model.layers.19.mlp.experts.99.up_proj.weight_scale": "model-00002-of-00004.safetensors",
-    "model.layers.19.mlp.gate.input_global_scale": "model-00002-of-00004.safetensors",
-    "model.layers.19.mlp.gate.weight_global_scale": "model-00002-of-00004.safetensors",
-    "model.layers.19.mlp.gate.weight_packed": "model-00002-of-00004.safetensors",
-    "model.layers.19.mlp.gate.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate.weight": "model-00002-of-00004.safetensors",
     "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
     "model.layers.19.self_attn.k_proj.input_global_scale": "model-00002-of-00004.safetensors",
@@ -20262,10 +20226,7 @@
     "model.layers.2.mlp.experts.99.up_proj.weight_global_scale": "model-00001-of-00004.safetensors",
     "model.layers.2.mlp.experts.99.up_proj.weight_packed": "model-00001-of-00004.safetensors",
     "model.layers.2.mlp.experts.99.up_proj.weight_scale": "model-00001-of-00004.safetensors",
-    "model.layers.2.mlp.gate.input_global_scale": "model-00001-of-00004.safetensors",
-    "model.layers.2.mlp.gate.weight_global_scale": "model-00001-of-00004.safetensors",
-    "model.layers.2.mlp.gate.weight_packed": "model-00001-of-00004.safetensors",
-    "model.layers.2.mlp.gate.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate.weight": "model-00001-of-00004.safetensors",
     "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
     "model.layers.2.self_attn.k_proj.input_global_scale": "model-00001-of-00004.safetensors",
@@ -21822,10 +21783,7 @@
     "model.layers.20.mlp.experts.99.up_proj.weight_global_scale": "model-00002-of-00004.safetensors",
     "model.layers.20.mlp.experts.99.up_proj.weight_packed": "model-00002-of-00004.safetensors",
     "model.layers.20.mlp.experts.99.up_proj.weight_scale": "model-00002-of-00004.safetensors",
-    "model.layers.20.mlp.gate.input_global_scale": "model-00002-of-00004.safetensors",
-    "model.layers.20.mlp.gate.weight_global_scale": "model-00002-of-00004.safetensors",
-    "model.layers.20.mlp.gate.weight_packed": "model-00002-of-00004.safetensors",
-    "model.layers.20.mlp.gate.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate.weight": "model-00002-of-00004.safetensors",
     "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
     "model.layers.20.self_attn.k_proj.input_global_scale": "model-00002-of-00004.safetensors",
@@ -23382,10 +23340,7 @@
     "model.layers.21.mlp.experts.99.up_proj.weight_global_scale": "model-00002-of-00004.safetensors",
     "model.layers.21.mlp.experts.99.up_proj.weight_packed": "model-00002-of-00004.safetensors",
     "model.layers.21.mlp.experts.99.up_proj.weight_scale": "model-00002-of-00004.safetensors",
-    "model.layers.21.mlp.gate.input_global_scale": "model-00002-of-00004.safetensors",
-    "model.layers.21.mlp.gate.weight_global_scale": "model-00002-of-00004.safetensors",
-    "model.layers.21.mlp.gate.weight_packed": "model-00002-of-00004.safetensors",
-    "model.layers.21.mlp.gate.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.gate.weight": "model-00002-of-00004.safetensors",
     "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
     "model.layers.21.self_attn.k_proj.input_global_scale": "model-00002-of-00004.safetensors",
@@ -24942,10 +24897,7 @@
     "model.layers.22.mlp.experts.99.up_proj.weight_global_scale": "model-00002-of-00004.safetensors",
     "model.layers.22.mlp.experts.99.up_proj.weight_packed": "model-00002-of-00004.safetensors",
     "model.layers.22.mlp.experts.99.up_proj.weight_scale": "model-00002-of-00004.safetensors",
-    "model.layers.22.mlp.gate.input_global_scale": "model-00002-of-00004.safetensors",
-    "model.layers.22.mlp.gate.weight_global_scale": "model-00002-of-00004.safetensors",
-    "model.layers.22.mlp.gate.weight_packed": "model-00002-of-00004.safetensors",
-    "model.layers.22.mlp.gate.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.22.mlp.gate.weight": "model-00002-of-00004.safetensors",
     "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
     "model.layers.22.self_attn.k_proj.input_global_scale": "model-00002-of-00004.safetensors",
@@ -26502,10 +26454,7 @@
     "model.layers.23.mlp.experts.99.up_proj.weight_global_scale": "model-00002-of-00004.safetensors",
     "model.layers.23.mlp.experts.99.up_proj.weight_packed": "model-00002-of-00004.safetensors",
     "model.layers.23.mlp.experts.99.up_proj.weight_scale": "model-00002-of-00004.safetensors",
-    "model.layers.23.mlp.gate.input_global_scale": "model-00002-of-00004.safetensors",
-    "model.layers.23.mlp.gate.weight_global_scale": "model-00002-of-00004.safetensors",
-    "model.layers.23.mlp.gate.weight_packed": "model-00002-of-00004.safetensors",
-    "model.layers.23.mlp.gate.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.23.mlp.gate.weight": "model-00002-of-00004.safetensors",
     "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
     "model.layers.23.self_attn.k_proj.input_global_scale": "model-00002-of-00004.safetensors",
@@ -28062,10 +28011,7 @@
     "model.layers.24.mlp.experts.99.up_proj.weight_global_scale": "model-00002-of-00004.safetensors",
     "model.layers.24.mlp.experts.99.up_proj.weight_packed": "model-00002-of-00004.safetensors",
     "model.layers.24.mlp.experts.99.up_proj.weight_scale": "model-00002-of-00004.safetensors",
-    "model.layers.24.mlp.gate.input_global_scale": "model-00002-of-00004.safetensors",
-    "model.layers.24.mlp.gate.weight_global_scale": "model-00002-of-00004.safetensors",
-    "model.layers.24.mlp.gate.weight_packed": "model-00002-of-00004.safetensors",
-    "model.layers.24.mlp.gate.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.24.mlp.gate.weight": "model-00002-of-00004.safetensors",
     "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
     "model.layers.24.self_attn.k_proj.input_global_scale": "model-00002-of-00004.safetensors",
@@ -29622,10 +29568,7 @@
     "model.layers.25.mlp.experts.99.up_proj.weight_global_scale": "model-00002-of-00004.safetensors",
     "model.layers.25.mlp.experts.99.up_proj.weight_packed": "model-00002-of-00004.safetensors",
     "model.layers.25.mlp.experts.99.up_proj.weight_scale": "model-00002-of-00004.safetensors",
-    "model.layers.25.mlp.gate.input_global_scale": "model-00002-of-00004.safetensors",
-    "model.layers.25.mlp.gate.weight_global_scale": "model-00002-of-00004.safetensors",
-    "model.layers.25.mlp.gate.weight_packed": "model-00002-of-00004.safetensors",
-    "model.layers.25.mlp.gate.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.25.mlp.gate.weight": "model-00002-of-00004.safetensors",
     "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
     "model.layers.25.self_attn.k_proj.input_global_scale": "model-00002-of-00004.safetensors",
@@ -31074,10 +31017,10 @@
     "model.layers.26.mlp.experts.90.up_proj.weight_global_scale": "model-00002-of-00004.safetensors",
     "model.layers.26.mlp.experts.90.up_proj.weight_packed": "model-00002-of-00004.safetensors",
     "model.layers.26.mlp.experts.90.up_proj.weight_scale": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.experts.91.down_proj.input_global_scale": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.experts.91.down_proj.weight_global_scale": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.experts.91.down_proj.weight_packed": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.experts.91.down_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.26.mlp.experts.91.down_proj.input_global_scale": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.experts.91.down_proj.weight_global_scale": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.experts.91.down_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.experts.91.down_proj.weight_scale": "model-00003-of-00004.safetensors",
     "model.layers.26.mlp.experts.91.gate_proj.input_global_scale": "model-00002-of-00004.safetensors",
     "model.layers.26.mlp.experts.91.gate_proj.weight_global_scale": "model-00002-of-00004.safetensors",
     "model.layers.26.mlp.experts.91.gate_proj.weight_packed": "model-00002-of-00004.safetensors",
@@ -31085,43 +31028,43 @@
     "model.layers.26.mlp.experts.91.up_proj.input_global_scale": "model-00002-of-00004.safetensors",
     "model.layers.26.mlp.experts.91.up_proj.weight_global_scale": "model-00002-of-00004.safetensors",
     "model.layers.26.mlp.experts.91.up_proj.weight_packed": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.experts.91.up_proj.weight_scale": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.experts.92.down_proj.input_global_scale": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.experts.92.down_proj.weight_global_scale": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.experts.92.down_proj.weight_packed": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.experts.92.down_proj.weight_scale": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.experts.92.gate_proj.input_global_scale": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.experts.92.gate_proj.weight_global_scale": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.experts.92.gate_proj.weight_packed": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.experts.92.gate_proj.weight_scale": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.experts.92.up_proj.input_global_scale": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.experts.92.up_proj.weight_global_scale": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.experts.92.up_proj.weight_packed": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.experts.92.up_proj.weight_scale": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.experts.93.down_proj.input_global_scale": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.experts.93.down_proj.weight_global_scale": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.experts.93.down_proj.weight_packed": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.experts.93.down_proj.weight_scale": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.experts.93.gate_proj.input_global_scale": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.experts.93.gate_proj.weight_global_scale": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.experts.93.gate_proj.weight_packed": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.experts.93.gate_proj.weight_scale": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.experts.93.up_proj.input_global_scale": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.experts.93.up_proj.weight_global_scale": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.experts.93.up_proj.weight_packed": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.experts.93.up_proj.weight_scale": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.experts.94.down_proj.input_global_scale": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.experts.94.down_proj.weight_global_scale": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.experts.94.down_proj.weight_packed": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.experts.94.down_proj.weight_scale": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.experts.94.gate_proj.input_global_scale": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.experts.94.gate_proj.weight_global_scale": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.experts.94.gate_proj.weight_packed": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.experts.94.gate_proj.weight_scale": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.experts.94.up_proj.input_global_scale": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.experts.94.up_proj.weight_global_scale": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.experts.94.up_proj.weight_packed": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.experts.94.up_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.26.mlp.experts.91.up_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.experts.92.down_proj.input_global_scale": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.experts.92.down_proj.weight_global_scale": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.experts.92.down_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.experts.92.down_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.experts.92.gate_proj.input_global_scale": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.experts.92.gate_proj.weight_global_scale": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.experts.92.gate_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.experts.92.gate_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.experts.92.up_proj.input_global_scale": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.experts.92.up_proj.weight_global_scale": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.experts.92.up_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.experts.92.up_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.experts.93.down_proj.input_global_scale": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.experts.93.down_proj.weight_global_scale": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.experts.93.down_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.experts.93.down_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.experts.93.gate_proj.input_global_scale": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.experts.93.gate_proj.weight_global_scale": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.experts.93.gate_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.experts.93.gate_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.experts.93.up_proj.input_global_scale": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.experts.93.up_proj.weight_global_scale": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.experts.93.up_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.experts.93.up_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.experts.94.down_proj.input_global_scale": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.experts.94.down_proj.weight_global_scale": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.experts.94.down_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.experts.94.down_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.experts.94.gate_proj.input_global_scale": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.experts.94.gate_proj.weight_global_scale": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.experts.94.gate_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.experts.94.gate_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.experts.94.up_proj.input_global_scale": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.experts.94.up_proj.weight_global_scale": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.experts.94.up_proj.weight_packed": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.experts.94.up_proj.weight_scale": "model-00003-of-00004.safetensors",
     "model.layers.26.mlp.experts.95.down_proj.input_global_scale": "model-00003-of-00004.safetensors",
     "model.layers.26.mlp.experts.95.down_proj.weight_global_scale": "model-00003-of-00004.safetensors",
     "model.layers.26.mlp.experts.95.down_proj.weight_packed": "model-00003-of-00004.safetensors",
@@ -31182,10 +31125,7 @@
     "model.layers.26.mlp.experts.99.up_proj.weight_global_scale": "model-00003-of-00004.safetensors",
     "model.layers.26.mlp.experts.99.up_proj.weight_packed": "model-00003-of-00004.safetensors",
     "model.layers.26.mlp.experts.99.up_proj.weight_scale": "model-00003-of-00004.safetensors",
-    "model.layers.26.mlp.gate.input_global_scale": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.gate.weight_global_scale": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.gate.weight_packed": "model-00002-of-00004.safetensors",
-    "model.layers.26.mlp.gate.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.26.mlp.gate.weight": "model-00002-of-00004.safetensors",
     "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
     "model.layers.26.self_attn.k_proj.input_global_scale": "model-00002-of-00004.safetensors",
@@ -32742,10 +32682,7 @@
     "model.layers.27.mlp.experts.99.up_proj.weight_global_scale": "model-00003-of-00004.safetensors",
     "model.layers.27.mlp.experts.99.up_proj.weight_packed": "model-00003-of-00004.safetensors",
     "model.layers.27.mlp.experts.99.up_proj.weight_scale": "model-00003-of-00004.safetensors",
-    "model.layers.27.mlp.gate.input_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.27.mlp.gate.weight_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.27.mlp.gate.weight_packed": "model-00003-of-00004.safetensors",
-    "model.layers.27.mlp.gate.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate.weight": "model-00003-of-00004.safetensors",
     "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
     "model.layers.27.self_attn.k_proj.input_global_scale": "model-00003-of-00004.safetensors",
@@ -34302,10 +34239,7 @@
     "model.layers.28.mlp.experts.99.up_proj.weight_global_scale": "model-00003-of-00004.safetensors",
     "model.layers.28.mlp.experts.99.up_proj.weight_packed": "model-00003-of-00004.safetensors",
     "model.layers.28.mlp.experts.99.up_proj.weight_scale": "model-00003-of-00004.safetensors",
-    "model.layers.28.mlp.gate.input_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.28.mlp.gate.weight_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.28.mlp.gate.weight_packed": "model-00003-of-00004.safetensors",
-    "model.layers.28.mlp.gate.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate.weight": "model-00003-of-00004.safetensors",
     "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
     "model.layers.28.self_attn.k_proj.input_global_scale": "model-00003-of-00004.safetensors",
@@ -35862,10 +35796,7 @@
     "model.layers.29.mlp.experts.99.up_proj.weight_global_scale": "model-00003-of-00004.safetensors",
     "model.layers.29.mlp.experts.99.up_proj.weight_packed": "model-00003-of-00004.safetensors",
     "model.layers.29.mlp.experts.99.up_proj.weight_scale": "model-00003-of-00004.safetensors",
-    "model.layers.29.mlp.gate.input_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.29.mlp.gate.weight_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.29.mlp.gate.weight_packed": "model-00003-of-00004.safetensors",
-    "model.layers.29.mlp.gate.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate.weight": "model-00003-of-00004.safetensors",
     "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
     "model.layers.29.self_attn.k_proj.input_global_scale": "model-00003-of-00004.safetensors",
@@ -37422,10 +37353,7 @@
     "model.layers.3.mlp.experts.99.up_proj.weight_global_scale": "model-00001-of-00004.safetensors",
     "model.layers.3.mlp.experts.99.up_proj.weight_packed": "model-00001-of-00004.safetensors",
     "model.layers.3.mlp.experts.99.up_proj.weight_scale": "model-00001-of-00004.safetensors",
-    "model.layers.3.mlp.gate.input_global_scale": "model-00001-of-00004.safetensors",
-    "model.layers.3.mlp.gate.weight_global_scale": "model-00001-of-00004.safetensors",
-    "model.layers.3.mlp.gate.weight_packed": "model-00001-of-00004.safetensors",
-    "model.layers.3.mlp.gate.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate.weight": "model-00001-of-00004.safetensors",
     "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
     "model.layers.3.self_attn.k_proj.input_global_scale": "model-00001-of-00004.safetensors",
@@ -38982,10 +38910,7 @@
     "model.layers.30.mlp.experts.99.up_proj.weight_global_scale": "model-00003-of-00004.safetensors",
     "model.layers.30.mlp.experts.99.up_proj.weight_packed": "model-00003-of-00004.safetensors",
     "model.layers.30.mlp.experts.99.up_proj.weight_scale": "model-00003-of-00004.safetensors",
-    "model.layers.30.mlp.gate.input_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.30.mlp.gate.weight_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.30.mlp.gate.weight_packed": "model-00003-of-00004.safetensors",
-    "model.layers.30.mlp.gate.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate.weight": "model-00003-of-00004.safetensors",
     "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
     "model.layers.30.self_attn.k_proj.input_global_scale": "model-00003-of-00004.safetensors",
@@ -40542,10 +40467,7 @@
     "model.layers.31.mlp.experts.99.up_proj.weight_global_scale": "model-00003-of-00004.safetensors",
     "model.layers.31.mlp.experts.99.up_proj.weight_packed": "model-00003-of-00004.safetensors",
     "model.layers.31.mlp.experts.99.up_proj.weight_scale": "model-00003-of-00004.safetensors",
-    "model.layers.31.mlp.gate.input_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.31.mlp.gate.weight_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.31.mlp.gate.weight_packed": "model-00003-of-00004.safetensors",
-    "model.layers.31.mlp.gate.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate.weight": "model-00003-of-00004.safetensors",
     "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
     "model.layers.31.self_attn.k_proj.input_global_scale": "model-00003-of-00004.safetensors",
@@ -42102,10 +42024,7 @@
     "model.layers.32.mlp.experts.99.up_proj.weight_global_scale": "model-00003-of-00004.safetensors",
     "model.layers.32.mlp.experts.99.up_proj.weight_packed": "model-00003-of-00004.safetensors",
     "model.layers.32.mlp.experts.99.up_proj.weight_scale": "model-00003-of-00004.safetensors",
-    "model.layers.32.mlp.gate.input_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.32.mlp.gate.weight_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.32.mlp.gate.weight_packed": "model-00003-of-00004.safetensors",
-    "model.layers.32.mlp.gate.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.gate.weight": "model-00003-of-00004.safetensors",
     "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
     "model.layers.32.self_attn.k_proj.input_global_scale": "model-00003-of-00004.safetensors",
@@ -43662,10 +43581,7 @@
     "model.layers.33.mlp.experts.99.up_proj.weight_global_scale": "model-00003-of-00004.safetensors",
     "model.layers.33.mlp.experts.99.up_proj.weight_packed": "model-00003-of-00004.safetensors",
     "model.layers.33.mlp.experts.99.up_proj.weight_scale": "model-00003-of-00004.safetensors",
-    "model.layers.33.mlp.gate.input_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.33.mlp.gate.weight_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.33.mlp.gate.weight_packed": "model-00003-of-00004.safetensors",
-    "model.layers.33.mlp.gate.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.gate.weight": "model-00003-of-00004.safetensors",
     "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
     "model.layers.33.self_attn.k_proj.input_global_scale": "model-00003-of-00004.safetensors",
@@ -45222,10 +45138,7 @@
     "model.layers.34.mlp.experts.99.up_proj.weight_global_scale": "model-00003-of-00004.safetensors",
     "model.layers.34.mlp.experts.99.up_proj.weight_packed": "model-00003-of-00004.safetensors",
     "model.layers.34.mlp.experts.99.up_proj.weight_scale": "model-00003-of-00004.safetensors",
-    "model.layers.34.mlp.gate.input_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.34.mlp.gate.weight_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.34.mlp.gate.weight_packed": "model-00003-of-00004.safetensors",
-    "model.layers.34.mlp.gate.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.gate.weight": "model-00003-of-00004.safetensors",
     "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
     "model.layers.34.self_attn.k_proj.input_global_scale": "model-00003-of-00004.safetensors",
@@ -46782,10 +46695,7 @@
     "model.layers.35.mlp.experts.99.up_proj.weight_global_scale": "model-00003-of-00004.safetensors",
     "model.layers.35.mlp.experts.99.up_proj.weight_packed": "model-00003-of-00004.safetensors",
     "model.layers.35.mlp.experts.99.up_proj.weight_scale": "model-00003-of-00004.safetensors",
-    "model.layers.35.mlp.gate.input_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.35.mlp.gate.weight_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.35.mlp.gate.weight_packed": "model-00003-of-00004.safetensors",
-    "model.layers.35.mlp.gate.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.35.mlp.gate.weight": "model-00003-of-00004.safetensors",
     "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.35.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
     "model.layers.35.self_attn.k_proj.input_global_scale": "model-00003-of-00004.safetensors",
@@ -48342,10 +48252,7 @@
     "model.layers.36.mlp.experts.99.up_proj.weight_global_scale": "model-00003-of-00004.safetensors",
     "model.layers.36.mlp.experts.99.up_proj.weight_packed": "model-00003-of-00004.safetensors",
     "model.layers.36.mlp.experts.99.up_proj.weight_scale": "model-00003-of-00004.safetensors",
-    "model.layers.36.mlp.gate.input_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.36.mlp.gate.weight_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.36.mlp.gate.weight_packed": "model-00003-of-00004.safetensors",
-    "model.layers.36.mlp.gate.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.36.mlp.gate.weight": "model-00003-of-00004.safetensors",
     "model.layers.36.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.36.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
     "model.layers.36.self_attn.k_proj.input_global_scale": "model-00003-of-00004.safetensors",
@@ -49902,10 +49809,7 @@
     "model.layers.37.mlp.experts.99.up_proj.weight_global_scale": "model-00003-of-00004.safetensors",
     "model.layers.37.mlp.experts.99.up_proj.weight_packed": "model-00003-of-00004.safetensors",
     "model.layers.37.mlp.experts.99.up_proj.weight_scale": "model-00003-of-00004.safetensors",
-    "model.layers.37.mlp.gate.input_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.37.mlp.gate.weight_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.37.mlp.gate.weight_packed": "model-00003-of-00004.safetensors",
-    "model.layers.37.mlp.gate.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.37.mlp.gate.weight": "model-00003-of-00004.safetensors",
     "model.layers.37.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.37.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
     "model.layers.37.self_attn.k_proj.input_global_scale": "model-00003-of-00004.safetensors",
@@ -51462,10 +51366,7 @@
     "model.layers.38.mlp.experts.99.up_proj.weight_global_scale": "model-00003-of-00004.safetensors",
     "model.layers.38.mlp.experts.99.up_proj.weight_packed": "model-00003-of-00004.safetensors",
     "model.layers.38.mlp.experts.99.up_proj.weight_scale": "model-00003-of-00004.safetensors",
-    "model.layers.38.mlp.gate.input_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.38.mlp.gate.weight_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.38.mlp.gate.weight_packed": "model-00003-of-00004.safetensors",
-    "model.layers.38.mlp.gate.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.38.mlp.gate.weight": "model-00003-of-00004.safetensors",
     "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.38.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
     "model.layers.38.self_attn.k_proj.input_global_scale": "model-00003-of-00004.safetensors",
@@ -53022,10 +52923,7 @@
     "model.layers.39.mlp.experts.99.up_proj.weight_global_scale": "model-00003-of-00004.safetensors",
     "model.layers.39.mlp.experts.99.up_proj.weight_packed": "model-00003-of-00004.safetensors",
     "model.layers.39.mlp.experts.99.up_proj.weight_scale": "model-00003-of-00004.safetensors",
-    "model.layers.39.mlp.gate.input_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.39.mlp.gate.weight_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.39.mlp.gate.weight_packed": "model-00003-of-00004.safetensors",
-    "model.layers.39.mlp.gate.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.39.mlp.gate.weight": "model-00003-of-00004.safetensors",
     "model.layers.39.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.39.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
     "model.layers.39.self_attn.k_proj.input_global_scale": "model-00003-of-00004.safetensors",
@@ -54582,10 +54480,7 @@
     "model.layers.4.mlp.experts.99.up_proj.weight_global_scale": "model-00001-of-00004.safetensors",
     "model.layers.4.mlp.experts.99.up_proj.weight_packed": "model-00001-of-00004.safetensors",
     "model.layers.4.mlp.experts.99.up_proj.weight_scale": "model-00001-of-00004.safetensors",
-    "model.layers.4.mlp.gate.input_global_scale": "model-00001-of-00004.safetensors",
-    "model.layers.4.mlp.gate.weight_global_scale": "model-00001-of-00004.safetensors",
-    "model.layers.4.mlp.gate.weight_packed": "model-00001-of-00004.safetensors",
-    "model.layers.4.mlp.gate.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate.weight": "model-00001-of-00004.safetensors",
     "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
     "model.layers.4.self_attn.k_proj.input_global_scale": "model-00001-of-00004.safetensors",
@@ -54605,7 +54500,7 @@
     "model.layers.4.self_attn.v_proj.weight_global_scale": "model-00001-of-00004.safetensors",
     "model.layers.4.self_attn.v_proj.weight_packed": "model-00001-of-00004.safetensors",
     "model.layers.4.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors",
-    "model.layers.40.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00004-of-00004.safetensors",
     "model.layers.40.mlp.experts.0.down_proj.input_global_scale": "model-00003-of-00004.safetensors",
     "model.layers.40.mlp.experts.0.down_proj.weight_global_scale": "model-00003-of-00004.safetensors",
     "model.layers.40.mlp.experts.0.down_proj.weight_packed": "model-00003-of-00004.safetensors",
@@ -54954,54 +54849,54 @@
     "model.layers.40.mlp.experts.123.up_proj.weight_global_scale": "model-00003-of-00004.safetensors",
     "model.layers.40.mlp.experts.123.up_proj.weight_packed": "model-00003-of-00004.safetensors",
     "model.layers.40.mlp.experts.123.up_proj.weight_scale": "model-00003-of-00004.safetensors",
-    "model.layers.40.mlp.experts.124.down_proj.input_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.40.mlp.experts.124.down_proj.weight_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.40.mlp.experts.124.down_proj.weight_packed": "model-00003-of-00004.safetensors",
-    "model.layers.40.mlp.experts.124.down_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.40.mlp.experts.124.down_proj.input_global_scale": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.experts.124.down_proj.weight_global_scale": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.experts.124.down_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.experts.124.down_proj.weight_scale": "model-00004-of-00004.safetensors",
     "model.layers.40.mlp.experts.124.gate_proj.input_global_scale": "model-00003-of-00004.safetensors",
     "model.layers.40.mlp.experts.124.gate_proj.weight_global_scale": "model-00003-of-00004.safetensors",
     "model.layers.40.mlp.experts.124.gate_proj.weight_packed": "model-00003-of-00004.safetensors",
     "model.layers.40.mlp.experts.124.gate_proj.weight_scale": "model-00003-of-00004.safetensors",
-    "model.layers.40.mlp.experts.124.up_proj.input_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.40.mlp.experts.124.up_proj.weight_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.40.mlp.experts.124.up_proj.weight_packed": "model-00003-of-00004.safetensors",
-    "model.layers.40.mlp.experts.124.up_proj.weight_scale": "model-00003-of-00004.safetensors",
-    "model.layers.40.mlp.experts.125.down_proj.input_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.40.mlp.experts.125.down_proj.weight_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.40.mlp.experts.125.down_proj.weight_packed": "model-00003-of-00004.safetensors",
-    "model.layers.40.mlp.experts.125.down_proj.weight_scale": "model-00003-of-00004.safetensors",
-    "model.layers.40.mlp.experts.125.gate_proj.input_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.40.mlp.experts.125.gate_proj.weight_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.40.mlp.experts.125.gate_proj.weight_packed": "model-00003-of-00004.safetensors",
-    "model.layers.40.mlp.experts.125.gate_proj.weight_scale": "model-00003-of-00004.safetensors",
-    "model.layers.40.mlp.experts.125.up_proj.input_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.40.mlp.experts.125.up_proj.weight_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.40.mlp.experts.125.up_proj.weight_packed": "model-00003-of-00004.safetensors",
-    "model.layers.40.mlp.experts.125.up_proj.weight_scale": "model-00003-of-00004.safetensors",
-    "model.layers.40.mlp.experts.126.down_proj.input_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.40.mlp.experts.126.down_proj.weight_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.40.mlp.experts.126.down_proj.weight_packed": "model-00003-of-00004.safetensors",
-    "model.layers.40.mlp.experts.126.down_proj.weight_scale": "model-00003-of-00004.safetensors",
-    "model.layers.40.mlp.experts.126.gate_proj.input_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.40.mlp.experts.126.gate_proj.weight_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.40.mlp.experts.126.gate_proj.weight_packed": "model-00003-of-00004.safetensors",
-    "model.layers.40.mlp.experts.126.gate_proj.weight_scale": "model-00003-of-00004.safetensors",
-    "model.layers.40.mlp.experts.126.up_proj.input_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.40.mlp.experts.126.up_proj.weight_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.40.mlp.experts.126.up_proj.weight_packed": "model-00003-of-00004.safetensors",
-    "model.layers.40.mlp.experts.126.up_proj.weight_scale": "model-00003-of-00004.safetensors",
-    "model.layers.40.mlp.experts.127.down_proj.input_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.40.mlp.experts.127.down_proj.weight_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.40.mlp.experts.127.down_proj.weight_packed": "model-00003-of-00004.safetensors",
-    "model.layers.40.mlp.experts.127.down_proj.weight_scale": "model-00003-of-00004.safetensors",
-    "model.layers.40.mlp.experts.127.gate_proj.input_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.40.mlp.experts.127.gate_proj.weight_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.40.mlp.experts.127.gate_proj.weight_packed": "model-00003-of-00004.safetensors",
-    "model.layers.40.mlp.experts.127.gate_proj.weight_scale": "model-00003-of-00004.safetensors",
-    "model.layers.40.mlp.experts.127.up_proj.input_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.40.mlp.experts.127.up_proj.weight_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.40.mlp.experts.127.up_proj.weight_packed": "model-00003-of-00004.safetensors",
-    "model.layers.40.mlp.experts.127.up_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.40.mlp.experts.124.up_proj.input_global_scale": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.experts.124.up_proj.weight_global_scale": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.experts.124.up_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.experts.124.up_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.experts.125.down_proj.input_global_scale": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.experts.125.down_proj.weight_global_scale": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.experts.125.down_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.experts.125.down_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.experts.125.gate_proj.input_global_scale": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.experts.125.gate_proj.weight_global_scale": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.experts.125.gate_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.experts.125.gate_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.experts.125.up_proj.input_global_scale": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.experts.125.up_proj.weight_global_scale": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.experts.125.up_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.experts.125.up_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.experts.126.down_proj.input_global_scale": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.experts.126.down_proj.weight_global_scale": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.experts.126.down_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.experts.126.down_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.experts.126.gate_proj.input_global_scale": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.experts.126.gate_proj.weight_global_scale": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.experts.126.gate_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.experts.126.gate_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.experts.126.up_proj.input_global_scale": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.experts.126.up_proj.weight_global_scale": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.experts.126.up_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.experts.126.up_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.experts.127.down_proj.input_global_scale": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.experts.127.down_proj.weight_global_scale": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.experts.127.down_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.experts.127.down_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.experts.127.gate_proj.input_global_scale": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.experts.127.gate_proj.weight_global_scale": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.experts.127.gate_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.experts.127.gate_proj.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.experts.127.up_proj.input_global_scale": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.experts.127.up_proj.weight_global_scale": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.experts.127.up_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.experts.127.up_proj.weight_scale": "model-00004-of-00004.safetensors",
     "model.layers.40.mlp.experts.13.down_proj.input_global_scale": "model-00003-of-00004.safetensors",
     "model.layers.40.mlp.experts.13.down_proj.weight_global_scale": "model-00003-of-00004.safetensors",
     "model.layers.40.mlp.experts.13.down_proj.weight_packed": "model-00003-of-00004.safetensors",
@@ -56142,11 +56037,8 @@
     "model.layers.40.mlp.experts.99.up_proj.weight_global_scale": "model-00003-of-00004.safetensors",
     "model.layers.40.mlp.experts.99.up_proj.weight_packed": "model-00003-of-00004.safetensors",
     "model.layers.40.mlp.experts.99.up_proj.weight_scale": "model-00003-of-00004.safetensors",
-    "model.layers.40.mlp.gate.input_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.40.mlp.gate.weight_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.40.mlp.gate.weight_packed": "model-00003-of-00004.safetensors",
-    "model.layers.40.mlp.gate.weight_scale": "model-00003-of-00004.safetensors",
-    "model.layers.40.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.40.mlp.gate.weight": "model-00003-of-00004.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
     "model.layers.40.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
     "model.layers.40.self_attn.k_proj.input_global_scale": "model-00003-of-00004.safetensors",
     "model.layers.40.self_attn.k_proj.weight_global_scale": "model-00003-of-00004.safetensors",
@@ -57702,10 +57594,7 @@
     "model.layers.41.mlp.experts.99.up_proj.weight_global_scale": "model-00004-of-00004.safetensors",
     "model.layers.41.mlp.experts.99.up_proj.weight_packed": "model-00004-of-00004.safetensors",
     "model.layers.41.mlp.experts.99.up_proj.weight_scale": "model-00004-of-00004.safetensors",
-    "model.layers.41.mlp.gate.input_global_scale": "model-00004-of-00004.safetensors",
-    "model.layers.41.mlp.gate.weight_global_scale": "model-00004-of-00004.safetensors",
-    "model.layers.41.mlp.gate.weight_packed": "model-00004-of-00004.safetensors",
-    "model.layers.41.mlp.gate.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.41.mlp.gate.weight": "model-00004-of-00004.safetensors",
     "model.layers.41.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
     "model.layers.41.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
     "model.layers.41.self_attn.k_proj.input_global_scale": "model-00004-of-00004.safetensors",
@@ -57717,10 +57606,10 @@
     "model.layers.41.self_attn.o_proj.weight_packed": "model-00004-of-00004.safetensors",
     "model.layers.41.self_attn.o_proj.weight_scale": "model-00004-of-00004.safetensors",
     "model.layers.41.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.41.self_attn.q_proj.input_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.41.self_attn.q_proj.weight_global_scale": "model-00003-of-00004.safetensors",
-    "model.layers.41.self_attn.q_proj.weight_packed": "model-00003-of-00004.safetensors",
-    "model.layers.41.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.41.self_attn.q_proj.input_global_scale": "model-00004-of-00004.safetensors",
+    "model.layers.41.self_attn.q_proj.weight_global_scale": "model-00004-of-00004.safetensors",
+    "model.layers.41.self_attn.q_proj.weight_packed": "model-00004-of-00004.safetensors",
+    "model.layers.41.self_attn.q_proj.weight_scale": "model-00004-of-00004.safetensors",
     "model.layers.41.self_attn.v_proj.input_global_scale": "model-00004-of-00004.safetensors",
     "model.layers.41.self_attn.v_proj.weight_global_scale": "model-00004-of-00004.safetensors",
     "model.layers.41.self_attn.v_proj.weight_packed": "model-00004-of-00004.safetensors",
@@ -59262,10 +59151,7 @@
     "model.layers.42.mlp.experts.99.up_proj.weight_global_scale": "model-00004-of-00004.safetensors",
     "model.layers.42.mlp.experts.99.up_proj.weight_packed": "model-00004-of-00004.safetensors",
     "model.layers.42.mlp.experts.99.up_proj.weight_scale": "model-00004-of-00004.safetensors",
-    "model.layers.42.mlp.gate.input_global_scale": "model-00004-of-00004.safetensors",
-    "model.layers.42.mlp.gate.weight_global_scale": "model-00004-of-00004.safetensors",
-    "model.layers.42.mlp.gate.weight_packed": "model-00004-of-00004.safetensors",
-    "model.layers.42.mlp.gate.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.42.mlp.gate.weight": "model-00004-of-00004.safetensors",
     "model.layers.42.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
     "model.layers.42.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
     "model.layers.42.self_attn.k_proj.input_global_scale": "model-00004-of-00004.safetensors",
@@ -60822,10 +60708,7 @@
     "model.layers.43.mlp.experts.99.up_proj.weight_global_scale": "model-00004-of-00004.safetensors",
     "model.layers.43.mlp.experts.99.up_proj.weight_packed": "model-00004-of-00004.safetensors",
     "model.layers.43.mlp.experts.99.up_proj.weight_scale": "model-00004-of-00004.safetensors",
-    "model.layers.43.mlp.gate.input_global_scale": "model-00004-of-00004.safetensors",
-    "model.layers.43.mlp.gate.weight_global_scale": "model-00004-of-00004.safetensors",
-    "model.layers.43.mlp.gate.weight_packed": "model-00004-of-00004.safetensors",
-    "model.layers.43.mlp.gate.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.43.mlp.gate.weight": "model-00004-of-00004.safetensors",
     "model.layers.43.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
     "model.layers.43.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
     "model.layers.43.self_attn.k_proj.input_global_scale": "model-00004-of-00004.safetensors",
@@ -62382,10 +62265,7 @@
     "model.layers.44.mlp.experts.99.up_proj.weight_global_scale": "model-00004-of-00004.safetensors",
     "model.layers.44.mlp.experts.99.up_proj.weight_packed": "model-00004-of-00004.safetensors",
     "model.layers.44.mlp.experts.99.up_proj.weight_scale": "model-00004-of-00004.safetensors",
-    "model.layers.44.mlp.gate.input_global_scale": "model-00004-of-00004.safetensors",
-    "model.layers.44.mlp.gate.weight_global_scale": "model-00004-of-00004.safetensors",
-    "model.layers.44.mlp.gate.weight_packed": "model-00004-of-00004.safetensors",
-    "model.layers.44.mlp.gate.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.44.mlp.gate.weight": "model-00004-of-00004.safetensors",
     "model.layers.44.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
     "model.layers.44.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
     "model.layers.44.self_attn.k_proj.input_global_scale": "model-00004-of-00004.safetensors",
@@ -63942,10 +63822,7 @@
     "model.layers.45.mlp.experts.99.up_proj.weight_global_scale": "model-00004-of-00004.safetensors",
     "model.layers.45.mlp.experts.99.up_proj.weight_packed": "model-00004-of-00004.safetensors",
     "model.layers.45.mlp.experts.99.up_proj.weight_scale": "model-00004-of-00004.safetensors",
-    "model.layers.45.mlp.gate.input_global_scale": "model-00004-of-00004.safetensors",
-    "model.layers.45.mlp.gate.weight_global_scale": "model-00004-of-00004.safetensors",
-    "model.layers.45.mlp.gate.weight_packed": "model-00004-of-00004.safetensors",
-    "model.layers.45.mlp.gate.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.45.mlp.gate.weight": "model-00004-of-00004.safetensors",
     "model.layers.45.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
     "model.layers.45.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
     "model.layers.45.self_attn.k_proj.input_global_scale": "model-00004-of-00004.safetensors",
@@ -65502,10 +65379,7 @@
     "model.layers.46.mlp.experts.99.up_proj.weight_global_scale": "model-00004-of-00004.safetensors",
     "model.layers.46.mlp.experts.99.up_proj.weight_packed": "model-00004-of-00004.safetensors",
     "model.layers.46.mlp.experts.99.up_proj.weight_scale": "model-00004-of-00004.safetensors",
-    "model.layers.46.mlp.gate.input_global_scale": "model-00004-of-00004.safetensors",
-    "model.layers.46.mlp.gate.weight_global_scale": "model-00004-of-00004.safetensors",
-    "model.layers.46.mlp.gate.weight_packed": "model-00004-of-00004.safetensors",
-    "model.layers.46.mlp.gate.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.46.mlp.gate.weight": "model-00004-of-00004.safetensors",
     "model.layers.46.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
     "model.layers.46.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
     "model.layers.46.self_attn.k_proj.input_global_scale": "model-00004-of-00004.safetensors",
@@ -67062,10 +66936,7 @@
     "model.layers.47.mlp.experts.99.up_proj.weight_global_scale": "model-00004-of-00004.safetensors",
     "model.layers.47.mlp.experts.99.up_proj.weight_packed": "model-00004-of-00004.safetensors",
     "model.layers.47.mlp.experts.99.up_proj.weight_scale": "model-00004-of-00004.safetensors",
-    "model.layers.47.mlp.gate.input_global_scale": "model-00004-of-00004.safetensors",
-    "model.layers.47.mlp.gate.weight_global_scale": "model-00004-of-00004.safetensors",
-    "model.layers.47.mlp.gate.weight_packed": "model-00004-of-00004.safetensors",
-    "model.layers.47.mlp.gate.weight_scale": "model-00004-of-00004.safetensors",
+    "model.layers.47.mlp.gate.weight": "model-00004-of-00004.safetensors",
     "model.layers.47.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
     "model.layers.47.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
     "model.layers.47.self_attn.k_proj.input_global_scale": "model-00004-of-00004.safetensors",
@@ -68622,10 +68493,7 @@
     "model.layers.5.mlp.experts.99.up_proj.weight_global_scale": "model-00001-of-00004.safetensors",
     "model.layers.5.mlp.experts.99.up_proj.weight_packed": "model-00001-of-00004.safetensors",
     "model.layers.5.mlp.experts.99.up_proj.weight_scale": "model-00001-of-00004.safetensors",
-    "model.layers.5.mlp.gate.input_global_scale": "model-00001-of-00004.safetensors",
-    "model.layers.5.mlp.gate.weight_global_scale": "model-00001-of-00004.safetensors",
-    "model.layers.5.mlp.gate.weight_packed": "model-00001-of-00004.safetensors",
-    "model.layers.5.mlp.gate.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate.weight": "model-00001-of-00004.safetensors",
     "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
     "model.layers.5.self_attn.k_proj.input_global_scale": "model-00001-of-00004.safetensors",
@@ -70182,10 +70050,7 @@
     "model.layers.6.mlp.experts.99.up_proj.weight_global_scale": "model-00001-of-00004.safetensors",
     "model.layers.6.mlp.experts.99.up_proj.weight_packed": "model-00001-of-00004.safetensors",
     "model.layers.6.mlp.experts.99.up_proj.weight_scale": "model-00001-of-00004.safetensors",
-    "model.layers.6.mlp.gate.input_global_scale": "model-00001-of-00004.safetensors",
-    "model.layers.6.mlp.gate.weight_global_scale": "model-00001-of-00004.safetensors",
-    "model.layers.6.mlp.gate.weight_packed": "model-00001-of-00004.safetensors",
-    "model.layers.6.mlp.gate.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate.weight": "model-00001-of-00004.safetensors",
     "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
     "model.layers.6.self_attn.k_proj.input_global_scale": "model-00001-of-00004.safetensors",
@@ -71742,10 +71607,7 @@
     "model.layers.7.mlp.experts.99.up_proj.weight_global_scale": "model-00001-of-00004.safetensors",
     "model.layers.7.mlp.experts.99.up_proj.weight_packed": "model-00001-of-00004.safetensors",
     "model.layers.7.mlp.experts.99.up_proj.weight_scale": "model-00001-of-00004.safetensors",
-    "model.layers.7.mlp.gate.input_global_scale": "model-00001-of-00004.safetensors",
-    "model.layers.7.mlp.gate.weight_global_scale": "model-00001-of-00004.safetensors",
-    "model.layers.7.mlp.gate.weight_packed": "model-00001-of-00004.safetensors",
-    "model.layers.7.mlp.gate.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate.weight": "model-00001-of-00004.safetensors",
     "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
     "model.layers.7.self_attn.k_proj.input_global_scale": "model-00001-of-00004.safetensors",
@@ -73302,10 +73164,7 @@
     "model.layers.8.mlp.experts.99.up_proj.weight_global_scale": "model-00001-of-00004.safetensors",
     "model.layers.8.mlp.experts.99.up_proj.weight_packed": "model-00001-of-00004.safetensors",
     "model.layers.8.mlp.experts.99.up_proj.weight_scale": "model-00001-of-00004.safetensors",
-    "model.layers.8.mlp.gate.input_global_scale": "model-00001-of-00004.safetensors",
-    "model.layers.8.mlp.gate.weight_global_scale": "model-00001-of-00004.safetensors",
-    "model.layers.8.mlp.gate.weight_packed": "model-00001-of-00004.safetensors",
-    "model.layers.8.mlp.gate.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate.weight": "model-00001-of-00004.safetensors",
     "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
     "model.layers.8.self_attn.k_proj.input_global_scale": "model-00001-of-00004.safetensors",
@@ -74862,10 +74721,7 @@
     "model.layers.9.mlp.experts.99.up_proj.weight_global_scale": "model-00001-of-00004.safetensors",
     "model.layers.9.mlp.experts.99.up_proj.weight_packed": "model-00001-of-00004.safetensors",
     "model.layers.9.mlp.experts.99.up_proj.weight_scale": "model-00001-of-00004.safetensors",
-    "model.layers.9.mlp.gate.input_global_scale": "model-00001-of-00004.safetensors",
-    "model.layers.9.mlp.gate.weight_global_scale": "model-00001-of-00004.safetensors",
-    "model.layers.9.mlp.gate.weight_packed": "model-00001-of-00004.safetensors",
-    "model.layers.9.mlp.gate.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.gate.weight": "model-00001-of-00004.safetensors",
     "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
     "model.layers.9.self_attn.k_proj.input_global_scale": "model-00001-of-00004.safetensors",

recipe.yaml

@@ -2,5 +2,5 @@ default_stage:
   default_modifiers:
     QuantizationModifier:
       targets: [Linear]
-      ignore: [lm_head]
+      ignore: [lm_head, 're:.*mlp.gate$']
       scheme: NVFP4