Upload folder using huggingface_hub

config.json

@@ -88,9 +88,11 @@
           "num_bits": 8,
           "observer": null,
           "observer_kwargs": {},
+          "scale_dtype": null,
           "strategy": "token",
           "symmetric": true,
-          "type": "int"
+          "type": "int",
+          "zp_dtype": null
         },
         "output_activations": null,
         "targets": [
@@ -104,9 +106,11 @@
           "num_bits": 8,
           "observer": "minmax",
           "observer_kwargs": {},
+          "scale_dtype": null,
           "strategy": "channel",
           "symmetric": true,
-          "type": "int"
+          "type": "int",
+          "zp_dtype": null
         }
       }
     },
@@ -114,45 +118,117 @@
     "global_compression_ratio": null,
     "ignore": [
       "model.layers.0.block_sparse_moe.router.layer",
+      "model.layers.0.mixer.in_proj",
+      "model.layers.0.mixer.out_proj",
       "model.layers.1.block_sparse_moe.router.layer",
+      "model.layers.1.mixer.in_proj",
+      "model.layers.1.mixer.out_proj",
       "model.layers.2.block_sparse_moe.router.layer",
+      "model.layers.2.mixer.in_proj",
+      "model.layers.2.mixer.out_proj",
       "model.layers.3.block_sparse_moe.router.layer",
+      "model.layers.3.mixer.in_proj",
+      "model.layers.3.mixer.out_proj",
       "model.layers.4.block_sparse_moe.router.layer",
+      "model.layers.4.mixer.in_proj",
+      "model.layers.4.mixer.out_proj",
       "model.layers.5.block_sparse_moe.router.layer",
       "model.layers.6.block_sparse_moe.router.layer",
+      "model.layers.6.mixer.in_proj",
+      "model.layers.6.mixer.out_proj",
       "model.layers.7.block_sparse_moe.router.layer",
+      "model.layers.7.mixer.in_proj",
+      "model.layers.7.mixer.out_proj",
       "model.layers.8.block_sparse_moe.router.layer",
+      "model.layers.8.mixer.in_proj",
+      "model.layers.8.mixer.out_proj",
       "model.layers.9.block_sparse_moe.router.layer",
+      "model.layers.9.mixer.in_proj",
+      "model.layers.9.mixer.out_proj",
       "model.layers.10.block_sparse_moe.router.layer",
+      "model.layers.10.mixer.in_proj",
+      "model.layers.10.mixer.out_proj",
       "model.layers.11.block_sparse_moe.router.layer",
+      "model.layers.11.mixer.in_proj",
+      "model.layers.11.mixer.out_proj",
       "model.layers.12.block_sparse_moe.router.layer",
+      "model.layers.12.mixer.in_proj",
+      "model.layers.12.mixer.out_proj",
       "model.layers.13.block_sparse_moe.router.layer",
+      "model.layers.13.mixer.in_proj",
+      "model.layers.13.mixer.out_proj",
       "model.layers.14.block_sparse_moe.router.layer",
+      "model.layers.14.mixer.in_proj",
+      "model.layers.14.mixer.out_proj",
       "model.layers.15.block_sparse_moe.router.layer",
       "model.layers.16.block_sparse_moe.router.layer",
+      "model.layers.16.mixer.in_proj",
+      "model.layers.16.mixer.out_proj",
       "model.layers.17.block_sparse_moe.router.layer",
+      "model.layers.17.mixer.in_proj",
+      "model.layers.17.mixer.out_proj",
       "model.layers.18.block_sparse_moe.router.layer",
+      "model.layers.18.mixer.in_proj",
+      "model.layers.18.mixer.out_proj",
       "model.layers.19.block_sparse_moe.router.layer",
+      "model.layers.19.mixer.in_proj",
+      "model.layers.19.mixer.out_proj",
       "model.layers.20.block_sparse_moe.router.layer",
+      "model.layers.20.mixer.in_proj",
+      "model.layers.20.mixer.out_proj",
       "model.layers.21.block_sparse_moe.router.layer",
+      "model.layers.21.mixer.in_proj",
+      "model.layers.21.mixer.out_proj",
       "model.layers.22.block_sparse_moe.router.layer",
+      "model.layers.22.mixer.in_proj",
+      "model.layers.22.mixer.out_proj",
       "model.layers.23.block_sparse_moe.router.layer",
+      "model.layers.23.mixer.in_proj",
+      "model.layers.23.mixer.out_proj",
       "model.layers.24.block_sparse_moe.router.layer",
+      "model.layers.24.mixer.in_proj",
+      "model.layers.24.mixer.out_proj",
       "model.layers.25.block_sparse_moe.router.layer",
       "model.layers.26.block_sparse_moe.router.layer",
+      "model.layers.26.mixer.in_proj",
+      "model.layers.26.mixer.out_proj",
       "model.layers.27.block_sparse_moe.router.layer",
+      "model.layers.27.mixer.in_proj",
+      "model.layers.27.mixer.out_proj",
       "model.layers.28.block_sparse_moe.router.layer",
+      "model.layers.28.mixer.in_proj",
+      "model.layers.28.mixer.out_proj",
       "model.layers.29.block_sparse_moe.router.layer",
+      "model.layers.29.mixer.in_proj",
+      "model.layers.29.mixer.out_proj",
       "model.layers.30.block_sparse_moe.router.layer",
+      "model.layers.30.mixer.in_proj",
+      "model.layers.30.mixer.out_proj",
       "model.layers.31.block_sparse_moe.router.layer",
+      "model.layers.31.mixer.in_proj",
+      "model.layers.31.mixer.out_proj",
       "model.layers.32.block_sparse_moe.router.layer",
+      "model.layers.32.mixer.in_proj",
+      "model.layers.32.mixer.out_proj",
       "model.layers.33.block_sparse_moe.router.layer",
+      "model.layers.33.mixer.in_proj",
+      "model.layers.33.mixer.out_proj",
       "model.layers.34.block_sparse_moe.router.layer",
+      "model.layers.34.mixer.in_proj",
+      "model.layers.34.mixer.out_proj",
       "model.layers.35.block_sparse_moe.router.layer",
       "model.layers.36.block_sparse_moe.router.layer",
+      "model.layers.36.mixer.in_proj",
+      "model.layers.36.mixer.out_proj",
       "model.layers.37.block_sparse_moe.router.layer",
+      "model.layers.37.mixer.in_proj",
+      "model.layers.37.mixer.out_proj",
       "model.layers.38.block_sparse_moe.router.layer",
+      "model.layers.38.mixer.in_proj",
+      "model.layers.38.mixer.out_proj",
       "model.layers.39.block_sparse_moe.router.layer",
+      "model.layers.39.mixer.in_proj",
+      "model.layers.39.mixer.out_proj",
       "lm_head"
     ],
     "kv_cache_scheme": null,

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b0554408cf70bd7a3ac428bbad8b1174dac869261a0a859e36b060f802e61bc
-size 3555814896
+oid sha256:d3e7a8a9aa0924de09973bd0fc1b37aa4ef75b78a7c73508c788467caa9ca4b8
+size 3819693440

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c63cc268573feb82230a97468d0bfbd51731ec3b4507f38aaf1b6fc6345144e7
-size 3556232256
+oid sha256:2c11d03fd82edfc467006a0dff085e4ca3225f87b0032fc934e3e9bc9083cd0c
+size 3818189840

model.safetensors.index.json

@@ -1,7 +1,7 @@
 {
   "metadata": {
-    "total_parameters": 6946038016,
-    "total_size": 7111950848
+    "total_parameters": 6945750592,
+    "total_size": 7637793920
   },
   "weight_map": {
     "model.layers.0.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
@@ -173,10 +173,8 @@
     "model.layers.0.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
     "model.layers.0.mamba.dt_bias": "model-00002-of-00002.safetensors",
     "model.layers.0.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.0.mamba.in_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.0.mamba.norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.0.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.0.mamba.out_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.0.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
     "model.layers.0.shared_mlp.input_linear.weight_scale": "model-00002-of-00002.safetensors",
@@ -190,10 +188,8 @@
     "model.layers.1.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
     "model.layers.1.mamba.dt_bias": "model-00002-of-00002.safetensors",
     "model.layers.1.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.1.mamba.in_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.1.mamba.norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.1.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.1.mamba.out_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.1.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
     "model.layers.1.shared_mlp.input_linear.weight_scale": "model-00002-of-00002.safetensors",
@@ -207,10 +203,8 @@
     "model.layers.10.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
     "model.layers.10.mamba.dt_bias": "model-00002-of-00002.safetensors",
     "model.layers.10.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.10.mamba.in_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.10.mamba.norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.10.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.10.mamba.out_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.10.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
     "model.layers.10.shared_mlp.input_linear.weight_scale": "model-00002-of-00002.safetensors",
@@ -224,10 +218,8 @@
     "model.layers.11.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
     "model.layers.11.mamba.dt_bias": "model-00002-of-00002.safetensors",
     "model.layers.11.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.11.mamba.in_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.11.mamba.norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.11.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.11.mamba.out_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.11.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
     "model.layers.11.shared_mlp.input_linear.weight_scale": "model-00002-of-00002.safetensors",
@@ -241,10 +233,8 @@
     "model.layers.12.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
     "model.layers.12.mamba.dt_bias": "model-00002-of-00002.safetensors",
     "model.layers.12.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.12.mamba.in_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.12.mamba.norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.12.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.12.mamba.out_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.12.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
     "model.layers.12.shared_mlp.input_linear.weight_scale": "model-00002-of-00002.safetensors",
@@ -258,10 +248,8 @@
     "model.layers.13.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
     "model.layers.13.mamba.dt_bias": "model-00002-of-00002.safetensors",
     "model.layers.13.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.13.mamba.in_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.13.mamba.norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.13.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.13.mamba.out_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.13.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
     "model.layers.13.shared_mlp.input_linear.weight_scale": "model-00002-of-00002.safetensors",
@@ -275,10 +263,8 @@
     "model.layers.14.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
     "model.layers.14.mamba.dt_bias": "model-00002-of-00002.safetensors",
     "model.layers.14.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.14.mamba.in_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.14.mamba.norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.14.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.14.mamba.out_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.14.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
     "model.layers.14.shared_mlp.input_linear.weight_scale": "model-00002-of-00002.safetensors",
@@ -307,10 +293,8 @@
     "model.layers.16.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
     "model.layers.16.mamba.dt_bias": "model-00002-of-00002.safetensors",
     "model.layers.16.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.16.mamba.in_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.16.mamba.norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.16.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.16.mamba.out_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.16.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
     "model.layers.16.shared_mlp.input_linear.weight_scale": "model-00002-of-00002.safetensors",
@@ -324,27 +308,23 @@
     "model.layers.17.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
     "model.layers.17.mamba.dt_bias": "model-00002-of-00002.safetensors",
     "model.layers.17.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.17.mamba.in_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.17.mamba.norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.17.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.17.mamba.out_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.17.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
-    "model.layers.17.shared_mlp.input_linear.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.17.shared_mlp.output_linear.weight": "model-00002-of-00002.safetensors",
-    "model.layers.17.shared_mlp.output_linear.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.18.block_sparse_moe.router.layer.weight": "model-00002-of-00002.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.18.mamba.A_log": "model-00002-of-00002.safetensors",
-    "model.layers.18.mamba.D": "model-00002-of-00002.safetensors",
-    "model.layers.18.mamba.conv1d.bias": "model-00002-of-00002.safetensors",
-    "model.layers.18.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
-    "model.layers.18.mamba.dt_bias": "model-00002-of-00002.safetensors",
-    "model.layers.18.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.18.mamba.in_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.shared_mlp.input_linear.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.17.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.shared_mlp.output_linear.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.18.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mamba.A_log": "model-00001-of-00002.safetensors",
+    "model.layers.18.mamba.D": "model-00001-of-00002.safetensors",
+    "model.layers.18.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mamba.dt_bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.mamba.norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.18.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.18.mamba.out_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.18.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
     "model.layers.18.shared_mlp.input_linear.weight_scale": "model-00002-of-00002.safetensors",
@@ -358,27 +338,23 @@
     "model.layers.19.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
     "model.layers.19.mamba.dt_bias": "model-00002-of-00002.safetensors",
     "model.layers.19.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.19.mamba.in_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.19.mamba.norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.19.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.19.mamba.out_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.19.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
-    "model.layers.19.shared_mlp.input_linear.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.19.shared_mlp.output_linear.weight": "model-00002-of-00002.safetensors",
-    "model.layers.19.shared_mlp.output_linear.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.2.block_sparse_moe.router.layer.weight": "model-00002-of-00002.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.2.mamba.A_log": "model-00002-of-00002.safetensors",
-    "model.layers.2.mamba.D": "model-00002-of-00002.safetensors",
-    "model.layers.2.mamba.conv1d.bias": "model-00002-of-00002.safetensors",
-    "model.layers.2.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
-    "model.layers.2.mamba.dt_bias": "model-00002-of-00002.safetensors",
-    "model.layers.2.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.2.mamba.in_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.19.mamba.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.shared_mlp.input_linear.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.19.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.shared_mlp.output_linear.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mamba.A_log": "model-00001-of-00002.safetensors",
+    "model.layers.2.mamba.D": "model-00001-of-00002.safetensors",
+    "model.layers.2.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mamba.dt_bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.mamba.norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.2.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.2.mamba.out_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.2.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
     "model.layers.2.shared_mlp.input_linear.weight_scale": "model-00002-of-00002.safetensors",
@@ -392,27 +368,23 @@
     "model.layers.20.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
     "model.layers.20.mamba.dt_bias": "model-00002-of-00002.safetensors",
     "model.layers.20.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.20.mamba.in_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.20.mamba.norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.20.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.20.mamba.out_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.20.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
-    "model.layers.20.shared_mlp.input_linear.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.20.shared_mlp.output_linear.weight": "model-00002-of-00002.safetensors",
-    "model.layers.20.shared_mlp.output_linear.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.21.block_sparse_moe.router.layer.weight": "model-00002-of-00002.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.21.mamba.A_log": "model-00002-of-00002.safetensors",
-    "model.layers.21.mamba.D": "model-00002-of-00002.safetensors",
-    "model.layers.21.mamba.conv1d.bias": "model-00002-of-00002.safetensors",
-    "model.layers.21.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
-    "model.layers.21.mamba.dt_bias": "model-00002-of-00002.safetensors",
-    "model.layers.21.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.21.mamba.in_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.20.mamba.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.shared_mlp.input_linear.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.20.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.shared_mlp.output_linear.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.21.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mamba.A_log": "model-00001-of-00002.safetensors",
+    "model.layers.21.mamba.D": "model-00001-of-00002.safetensors",
+    "model.layers.21.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mamba.dt_bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.mamba.norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.21.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.21.mamba.out_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.21.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
     "model.layers.21.shared_mlp.input_linear.weight_scale": "model-00002-of-00002.safetensors",
@@ -426,80 +398,72 @@
     "model.layers.22.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
     "model.layers.22.mamba.dt_bias": "model-00002-of-00002.safetensors",
     "model.layers.22.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.mamba.in_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.22.mamba.norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.mamba.out_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.shared_mlp.input_linear.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.22.shared_mlp.output_linear.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.shared_mlp.output_linear.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.23.block_sparse_moe.router.layer.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.mamba.A_log": "model-00002-of-00002.safetensors",
-    "model.layers.23.mamba.D": "model-00002-of-00002.safetensors",
-    "model.layers.23.mamba.conv1d.bias": "model-00002-of-00002.safetensors",
-    "model.layers.23.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.mamba.dt_bias": "model-00002-of-00002.safetensors",
-    "model.layers.23.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.mamba.in_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.23.mamba.norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.23.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.23.mamba.out_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.23.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mamba.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.shared_mlp.input_linear.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.22.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.shared_mlp.output_linear.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.23.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mamba.A_log": "model-00001-of-00002.safetensors",
+    "model.layers.23.mamba.D": "model-00001-of-00002.safetensors",
+    "model.layers.23.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mamba.dt_bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mamba.norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
     "model.layers.23.shared_mlp.input_linear.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.23.shared_mlp.output_linear.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.shared_mlp.output_linear.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.24.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.24.mamba.A_log": "model-00001-of-00002.safetensors",
-    "model.layers.24.mamba.D": "model-00001-of-00002.safetensors",
-    "model.layers.24.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
-    "model.layers.24.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
-    "model.layers.24.mamba.dt_bias": "model-00001-of-00002.safetensors",
-    "model.layers.24.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.24.mamba.in_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.24.mamba.norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.24.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.24.mamba.out_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.24.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
-    "model.layers.24.shared_mlp.input_linear.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.24.shared_mlp.output_linear.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.shared_mlp.output_linear.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.24.block_sparse_moe.router.layer.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mamba.A_log": "model-00002-of-00002.safetensors",
+    "model.layers.24.mamba.D": "model-00002-of-00002.safetensors",
+    "model.layers.24.mamba.conv1d.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mamba.dt_bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mamba.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.shared_mlp.input_linear.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.24.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
     "model.layers.24.shared_mlp.output_linear.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.25.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
     "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.25.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.25.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.25.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.25.shared_mlp.input_linear.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.25.shared_mlp.output_linear.weight": "model-00002-of-00002.safetensors",
-    "model.layers.25.shared_mlp.output_linear.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.26.block_sparse_moe.router.layer.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.mamba.A_log": "model-00002-of-00002.safetensors",
-    "model.layers.26.mamba.D": "model-00002-of-00002.safetensors",
-    "model.layers.26.mamba.conv1d.bias": "model-00002-of-00002.safetensors",
-    "model.layers.26.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.mamba.dt_bias": "model-00002-of-00002.safetensors",
-    "model.layers.26.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.mamba.in_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.26.mamba.norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.26.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.26.mamba.out_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.26.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.26.shared_mlp.input_linear.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.26.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.25.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.shared_mlp.input_linear.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.25.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.shared_mlp.output_linear.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.26.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mamba.A_log": "model-00001-of-00002.safetensors",
+    "model.layers.26.mamba.D": "model-00001-of-00002.safetensors",
+    "model.layers.26.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mamba.dt_bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mamba.norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.shared_mlp.input_linear.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.26.shared_mlp.output_linear.weight": "model-00002-of-00002.safetensors",
     "model.layers.26.shared_mlp.output_linear.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.27.block_sparse_moe.router.layer.weight": "model-00002-of-00002.safetensors",
     "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
@@ -509,27 +473,23 @@
     "model.layers.27.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
     "model.layers.27.mamba.dt_bias": "model-00002-of-00002.safetensors",
     "model.layers.27.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.mamba.in_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.27.mamba.norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.27.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.27.mamba.out_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.27.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
     "model.layers.27.shared_mlp.input_linear.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.27.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.27.shared_mlp.output_linear.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.28.block_sparse_moe.router.layer.weight": "model-00002-of-00002.safetensors",
-    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.28.mamba.A_log": "model-00002-of-00002.safetensors",
-    "model.layers.28.mamba.D": "model-00002-of-00002.safetensors",
-    "model.layers.28.mamba.conv1d.bias": "model-00002-of-00002.safetensors",
-    "model.layers.28.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.shared_mlp.output_linear.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.28.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mamba.A_log": "model-00001-of-00002.safetensors",
+    "model.layers.28.mamba.D": "model-00001-of-00002.safetensors",
+    "model.layers.28.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.28.mamba.dt_bias": "model-00001-of-00002.safetensors",
     "model.layers.28.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.28.mamba.in_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.28.mamba.norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.28.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.28.mamba.out_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.28.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
     "model.layers.28.shared_mlp.input_linear.weight_scale": "model-00002-of-00002.safetensors",
@@ -543,10 +503,8 @@
     "model.layers.29.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
     "model.layers.29.mamba.dt_bias": "model-00002-of-00002.safetensors",
     "model.layers.29.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.29.mamba.in_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.29.mamba.norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.29.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.29.mamba.out_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.29.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
     "model.layers.29.shared_mlp.input_linear.weight_scale": "model-00001-of-00002.safetensors",
@@ -560,10 +518,8 @@
     "model.layers.3.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.mamba.dt_bias": "model-00001-of-00002.safetensors",
     "model.layers.3.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.mamba.in_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.3.mamba.norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.3.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.3.mamba.out_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.3.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
     "model.layers.3.shared_mlp.input_linear.weight_scale": "model-00002-of-00002.safetensors",
@@ -577,10 +533,8 @@
     "model.layers.30.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
     "model.layers.30.mamba.dt_bias": "model-00002-of-00002.safetensors",
     "model.layers.30.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.30.mamba.in_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.30.mamba.norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.30.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.30.mamba.out_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.30.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
     "model.layers.30.shared_mlp.input_linear.weight_scale": "model-00001-of-00002.safetensors",
@@ -594,10 +548,8 @@
     "model.layers.31.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.31.mamba.dt_bias": "model-00001-of-00002.safetensors",
     "model.layers.31.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.31.mamba.in_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.31.mamba.norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.31.mamba.out_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.shared_mlp.input_linear.weight_scale": "model-00002-of-00002.safetensors",
@@ -611,10 +563,8 @@
     "model.layers.32.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
     "model.layers.32.mamba.dt_bias": "model-00002-of-00002.safetensors",
     "model.layers.32.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.32.mamba.in_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.32.mamba.norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.32.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.32.mamba.out_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.32.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
     "model.layers.32.shared_mlp.input_linear.weight_scale": "model-00001-of-00002.safetensors",
@@ -628,10 +578,8 @@
     "model.layers.33.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.33.mamba.dt_bias": "model-00001-of-00002.safetensors",
     "model.layers.33.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.33.mamba.in_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.33.mamba.norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.33.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.33.mamba.out_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.33.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
     "model.layers.33.shared_mlp.input_linear.weight_scale": "model-00002-of-00002.safetensors",
@@ -645,10 +593,8 @@
     "model.layers.34.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
     "model.layers.34.mamba.dt_bias": "model-00002-of-00002.safetensors",
     "model.layers.34.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.34.mamba.in_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.34.mamba.norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.34.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.34.mamba.out_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.34.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
     "model.layers.34.shared_mlp.input_linear.weight_scale": "model-00001-of-00002.safetensors",
@@ -658,33 +604,31 @@
     "model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.35.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.35.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.35.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.35.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.35.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.35.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.35.shared_mlp.input_linear.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.35.shared_mlp.output_linear.weight": "model-00002-of-00002.safetensors",
-    "model.layers.35.shared_mlp.output_linear.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.36.block_sparse_moe.router.layer.weight": "model-00002-of-00002.safetensors",
-    "model.layers.36.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.36.mamba.A_log": "model-00002-of-00002.safetensors",
-    "model.layers.36.mamba.D": "model-00002-of-00002.safetensors",
-    "model.layers.36.mamba.conv1d.bias": "model-00002-of-00002.safetensors",
-    "model.layers.36.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
-    "model.layers.36.mamba.dt_bias": "model-00002-of-00002.safetensors",
-    "model.layers.36.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.36.mamba.in_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.36.mamba.norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.36.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.36.mamba.out_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.36.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.36.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.36.shared_mlp.input_linear.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.36.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.35.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.shared_mlp.input_linear.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.35.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.shared_mlp.output_linear.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.36.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.36.mamba.A_log": "model-00001-of-00002.safetensors",
+    "model.layers.36.mamba.D": "model-00001-of-00002.safetensors",
+    "model.layers.36.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+    "model.layers.36.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+    "model.layers.36.mamba.dt_bias": "model-00001-of-00002.safetensors",
+    "model.layers.36.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.36.mamba.norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.36.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.36.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
+    "model.layers.36.shared_mlp.input_linear.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.36.shared_mlp.output_linear.weight": "model-00002-of-00002.safetensors",
     "model.layers.36.shared_mlp.output_linear.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.37.block_sparse_moe.router.layer.weight": "model-00002-of-00002.safetensors",
     "model.layers.37.input_layernorm.weight": "model-00002-of-00002.safetensors",
@@ -694,76 +638,68 @@
     "model.layers.37.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
     "model.layers.37.mamba.dt_bias": "model-00002-of-00002.safetensors",
     "model.layers.37.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.37.mamba.in_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.37.mamba.norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.37.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.37.mamba.out_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.37.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.37.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
     "model.layers.37.shared_mlp.input_linear.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.37.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.37.shared_mlp.output_linear.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.38.block_sparse_moe.router.layer.weight": "model-00002-of-00002.safetensors",
+    "model.layers.37.shared_mlp.output_linear.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.38.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
     "model.layers.38.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.38.mamba.A_log": "model-00001-of-00002.safetensors",
     "model.layers.38.mamba.D": "model-00001-of-00002.safetensors",
     "model.layers.38.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
     "model.layers.38.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
-    "model.layers.38.mamba.dt_bias": "model-00002-of-00002.safetensors",
-    "model.layers.38.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.38.mamba.in_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.38.mamba.norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.38.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.38.mamba.out_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.38.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.38.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.38.shared_mlp.input_linear.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.38.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.38.shared_mlp.output_linear.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.39.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
-    "model.layers.39.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.39.mamba.A_log": "model-00001-of-00002.safetensors",
-    "model.layers.39.mamba.D": "model-00001-of-00002.safetensors",
-    "model.layers.39.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
-    "model.layers.39.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
-    "model.layers.39.mamba.dt_bias": "model-00001-of-00002.safetensors",
-    "model.layers.39.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.39.mamba.in_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.39.mamba.norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.39.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.39.mamba.out_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.39.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
-    "model.layers.39.shared_mlp.input_linear.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.39.shared_mlp.output_linear.weight": "model-00002-of-00002.safetensors",
-    "model.layers.39.shared_mlp.output_linear.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.4.block_sparse_moe.router.layer.weight": "model-00002-of-00002.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.4.mamba.A_log": "model-00002-of-00002.safetensors",
-    "model.layers.4.mamba.D": "model-00002-of-00002.safetensors",
-    "model.layers.4.mamba.conv1d.bias": "model-00002-of-00002.safetensors",
-    "model.layers.4.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
-    "model.layers.4.mamba.dt_bias": "model-00002-of-00002.safetensors",
-    "model.layers.4.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.4.mamba.in_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.4.mamba.norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.mamba.out_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.shared_mlp.input_linear.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.4.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.shared_mlp.output_linear.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.5.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.38.mamba.dt_bias": "model-00001-of-00002.safetensors",
+    "model.layers.38.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.38.mamba.norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.38.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.38.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
+    "model.layers.38.shared_mlp.input_linear.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.38.shared_mlp.output_linear.weight": "model-00002-of-00002.safetensors",
+    "model.layers.38.shared_mlp.output_linear.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.39.block_sparse_moe.router.layer.weight": "model-00002-of-00002.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.39.mamba.A_log": "model-00002-of-00002.safetensors",
+    "model.layers.39.mamba.D": "model-00002-of-00002.safetensors",
+    "model.layers.39.mamba.conv1d.bias": "model-00002-of-00002.safetensors",
+    "model.layers.39.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
+    "model.layers.39.mamba.dt_bias": "model-00002-of-00002.safetensors",
+    "model.layers.39.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.39.mamba.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.39.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.39.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.39.shared_mlp.input_linear.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.39.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.39.shared_mlp.output_linear.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mamba.A_log": "model-00001-of-00002.safetensors",
+    "model.layers.4.mamba.D": "model-00001-of-00002.safetensors",
+    "model.layers.4.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mamba.dt_bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mamba.norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.shared_mlp.input_linear.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.4.shared_mlp.output_linear.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.shared_mlp.output_linear.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.router.layer.weight": "model-00002-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.5.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.5.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.5.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.shared_mlp.input_linear.weight_scale": "model-00002-of-00002.safetensors",
@@ -777,66 +713,58 @@
     "model.layers.6.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
     "model.layers.6.mamba.dt_bias": "model-00002-of-00002.safetensors",
     "model.layers.6.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.6.mamba.in_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.6.mamba.norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.mamba.out_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.shared_mlp.input_linear.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.6.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.shared_mlp.output_linear.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.7.block_sparse_moe.router.layer.weight": "model-00002-of-00002.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.7.mamba.A_log": "model-00002-of-00002.safetensors",
-    "model.layers.7.mamba.D": "model-00002-of-00002.safetensors",
-    "model.layers.7.mamba.conv1d.bias": "model-00002-of-00002.safetensors",
-    "model.layers.7.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
-    "model.layers.7.mamba.dt_bias": "model-00002-of-00002.safetensors",
-    "model.layers.7.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.7.mamba.in_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.7.mamba.norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.mamba.out_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.shared_mlp.input_linear.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.7.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.shared_mlp.output_linear.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.6.shared_mlp.output_linear.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mamba.A_log": "model-00001-of-00002.safetensors",
+    "model.layers.7.mamba.D": "model-00001-of-00002.safetensors",
+    "model.layers.7.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mamba.dt_bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mamba.norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.7.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.7.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
+    "model.layers.7.shared_mlp.input_linear.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.7.shared_mlp.output_linear.weight": "model-00002-of-00002.safetensors",
+    "model.layers.7.shared_mlp.output_linear.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.8.block_sparse_moe.router.layer.weight": "model-00002-of-00002.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.mamba.A_log": "model-00001-of-00002.safetensors",
-    "model.layers.8.mamba.D": "model-00001-of-00002.safetensors",
-    "model.layers.8.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
-    "model.layers.8.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.mamba.dt_bias": "model-00001-of-00002.safetensors",
-    "model.layers.8.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.mamba.in_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.8.mamba.norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.8.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.8.mamba.out_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.8.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
-    "model.layers.8.shared_mlp.input_linear.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.8.shared_mlp.output_linear.weight": "model-00002-of-00002.safetensors",
-    "model.layers.8.shared_mlp.output_linear.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.9.block_sparse_moe.router.layer.weight": "model-00002-of-00002.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.9.mamba.A_log": "model-00002-of-00002.safetensors",
-    "model.layers.9.mamba.D": "model-00002-of-00002.safetensors",
-    "model.layers.9.mamba.conv1d.bias": "model-00002-of-00002.safetensors",
-    "model.layers.9.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
-    "model.layers.9.mamba.dt_bias": "model-00002-of-00002.safetensors",
-    "model.layers.9.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.9.mamba.in_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.9.mamba.norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.mamba.out_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.shared_mlp.input_linear.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.9.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.shared_mlp.output_linear.weight_scale": "model-00001-of-00002.safetensors",
-    "model.norm.weight": "model-00001-of-00002.safetensors"
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.8.mamba.A_log": "model-00002-of-00002.safetensors",
+    "model.layers.8.mamba.D": "model-00002-of-00002.safetensors",
+    "model.layers.8.mamba.conv1d.bias": "model-00002-of-00002.safetensors",
+    "model.layers.8.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
+    "model.layers.8.mamba.dt_bias": "model-00002-of-00002.safetensors",
+    "model.layers.8.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.8.mamba.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.shared_mlp.input_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.shared_mlp.input_linear.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.8.shared_mlp.output_linear.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.shared_mlp.output_linear.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.router.layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mamba.A_log": "model-00001-of-00002.safetensors",
+    "model.layers.9.mamba.D": "model-00001-of-00002.safetensors",
+    "model.layers.9.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mamba.dt_bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mamba.norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.9.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.9.shared_mlp.input_linear.weight": "model-00002-of-00002.safetensors",
+    "model.layers.9.shared_mlp.input_linear.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.9.shared_mlp.output_linear.weight": "model-00002-of-00002.safetensors",
+    "model.layers.9.shared_mlp.output_linear.weight_scale": "model-00002-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
   }
 }

recipe.yaml

@@ -12,7 +12,7 @@ default_stage:
       ignore: []
     GPTQModifier:
       targets: [Linear]
-      ignore: [lm_head, 're:.*block_sparse_moe.router']
+      ignore: [lm_head, 're:.*block_sparse_moe.router', 're:.*mamba.in_proj', 're:.*mamba.out_proj']
       scheme: W8A8
       block_size: 128
       dampening_frac: 0.01