Add files using upload-large-folder tool

README.md

@@ -1,8 +1,8 @@
 ---
 license: apache-2.0
+base_model: GreenBitAI/Qwen-3-30B-A3B-layer-mix-bpw-4.0
 tags:
 - mlx
-base_model: GreenBitAI/Qwen-3-30B-A3B-layer-mix-bpw-4.0
 ---
 
 # GreenBitAI/Qwen-3-30B-A3B-layer-mix-bpw-4.0-mlx

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c44322b1f6e702660446b0bb1bdae07d3d574e5ae2de44102d5ef44df67d0e1b
-size 5335275403
+oid sha256:b907ce117995e499b5561b3cdcf06ed4996cdc1b5220c20efd61be40a5ac5cb1
+size 5368520320

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8af7268502593bc413f6b7fd69ddf09fd4f3c0c3fd4971408606b76778dba9a0
-size 5297878378
+oid sha256:cd22c58b5ab6b8ccfcc6ead4e7623acffb44b8b352999cfa63a7ac349e2a3925
+size 5303777239

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97b6352c4952bbddaf13a0523e339d307a67fb1c3091ab6fe9ac2e8f32a2c637
-size 5297878380
+oid sha256:c6337179e8bb4da998b7c4baffa8e41484796d837760da5ca95df782bc69bf0b
+size 5297485560

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ceb9073f30683fe38cf034b1639fe8ef524acb0e1f132c29303b63f10fb436b
-size 2451930388
+oid sha256:9711624715dc488fbb77e3cc1bc28daec04cea54110afc8f3d0b87b757f38a9b
+size 1167337251

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
     "metadata": {
-        "total_size": 18382749696
+        "total_size": 17136906240
     },
     "weight_map": {
         "lm_head.weight": "model-00004-of-00004.safetensors",
@@ -163,15 +163,15 @@
         "model.layers.12.mlp.gate.qweight": "model-00001-of-00004.safetensors",
         "model.layers.12.mlp.gate.scales": "model-00001-of-00004.safetensors",
         "model.layers.12.mlp.gate.zeros": "model-00001-of-00004.safetensors",
-        "model.layers.12.mlp.switch_mlp.down_proj.qweight": "model-00002-of-00004.safetensors",
-        "model.layers.12.mlp.switch_mlp.down_proj.scales": "model-00002-of-00004.safetensors",
-        "model.layers.12.mlp.switch_mlp.down_proj.zeros": "model-00002-of-00004.safetensors",
+        "model.layers.12.mlp.switch_mlp.down_proj.qweight": "model-00001-of-00004.safetensors",
+        "model.layers.12.mlp.switch_mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.12.mlp.switch_mlp.down_proj.zeros": "model-00001-of-00004.safetensors",
         "model.layers.12.mlp.switch_mlp.gate_proj.qweight": "model-00001-of-00004.safetensors",
         "model.layers.12.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
         "model.layers.12.mlp.switch_mlp.gate_proj.zeros": "model-00001-of-00004.safetensors",
-        "model.layers.12.mlp.switch_mlp.up_proj.qweight": "model-00002-of-00004.safetensors",
-        "model.layers.12.mlp.switch_mlp.up_proj.scales": "model-00002-of-00004.safetensors",
-        "model.layers.12.mlp.switch_mlp.up_proj.zeros": "model-00002-of-00004.safetensors",
+        "model.layers.12.mlp.switch_mlp.up_proj.qweight": "model-00001-of-00004.safetensors",
+        "model.layers.12.mlp.switch_mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.12.mlp.switch_mlp.up_proj.zeros": "model-00001-of-00004.safetensors",
         "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
         "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
         "model.layers.12.self_attn.k_proj.channel_scale": "model-00001-of-00004.safetensors",
@@ -195,82 +195,82 @@
         "model.layers.12.self_attn.v_proj.qweight": "model-00001-of-00004.safetensors",
         "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
         "model.layers.12.self_attn.v_proj.zeros": "model-00001-of-00004.safetensors",
-        "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
-        "model.layers.13.mlp.gate.channel_scale": "model-00002-of-00004.safetensors",
-        "model.layers.13.mlp.gate.q_perm": "model-00002-of-00004.safetensors",
-        "model.layers.13.mlp.gate.qweight": "model-00002-of-00004.safetensors",
-        "model.layers.13.mlp.gate.scales": "model-00002-of-00004.safetensors",
-        "model.layers.13.mlp.gate.zeros": "model-00002-of-00004.safetensors",
-        "model.layers.13.mlp.switch_mlp.down_proj.qweight": "model-00002-of-00004.safetensors",
-        "model.layers.13.mlp.switch_mlp.down_proj.scales": "model-00002-of-00004.safetensors",
-        "model.layers.13.mlp.switch_mlp.down_proj.zeros": "model-00002-of-00004.safetensors",
-        "model.layers.13.mlp.switch_mlp.gate_proj.qweight": "model-00002-of-00004.safetensors",
-        "model.layers.13.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
-        "model.layers.13.mlp.switch_mlp.gate_proj.zeros": "model-00002-of-00004.safetensors",
-        "model.layers.13.mlp.switch_mlp.up_proj.qweight": "model-00002-of-00004.safetensors",
-        "model.layers.13.mlp.switch_mlp.up_proj.scales": "model-00002-of-00004.safetensors",
-        "model.layers.13.mlp.switch_mlp.up_proj.zeros": "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.channel_scale": "model-00002-of-00004.safetensors",
-        "model.layers.13.self_attn.k_proj.q_perm": "model-00002-of-00004.safetensors",
-        "model.layers.13.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors",
-        "model.layers.13.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
-        "model.layers.13.self_attn.k_proj.zeros": "model-00002-of-00004.safetensors",
-        "model.layers.13.self_attn.o_proj.channel_scale": "model-00002-of-00004.safetensors",
-        "model.layers.13.self_attn.o_proj.q_perm": "model-00002-of-00004.safetensors",
-        "model.layers.13.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors",
-        "model.layers.13.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
-        "model.layers.13.self_attn.o_proj.zeros": "model-00002-of-00004.safetensors",
-        "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
-        "model.layers.13.self_attn.q_proj.channel_scale": "model-00002-of-00004.safetensors",
-        "model.layers.13.self_attn.q_proj.q_perm": "model-00002-of-00004.safetensors",
-        "model.layers.13.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors",
-        "model.layers.13.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
-        "model.layers.13.self_attn.q_proj.zeros": "model-00002-of-00004.safetensors",
-        "model.layers.13.self_attn.v_proj.channel_scale": "model-00002-of-00004.safetensors",
-        "model.layers.13.self_attn.v_proj.q_perm": "model-00002-of-00004.safetensors",
-        "model.layers.13.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors",
-        "model.layers.13.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
-        "model.layers.13.self_attn.v_proj.zeros": "model-00002-of-00004.safetensors",
-        "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
-        "model.layers.14.mlp.gate.channel_scale": "model-00002-of-00004.safetensors",
-        "model.layers.14.mlp.gate.q_perm": "model-00002-of-00004.safetensors",
-        "model.layers.14.mlp.gate.qweight": "model-00002-of-00004.safetensors",
-        "model.layers.14.mlp.gate.scales": "model-00002-of-00004.safetensors",
-        "model.layers.14.mlp.gate.zeros": "model-00002-of-00004.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.13.mlp.gate.channel_scale": "model-00001-of-00004.safetensors",
+        "model.layers.13.mlp.gate.q_perm": "model-00001-of-00004.safetensors",
+        "model.layers.13.mlp.gate.qweight": "model-00001-of-00004.safetensors",
+        "model.layers.13.mlp.gate.scales": "model-00001-of-00004.safetensors",
+        "model.layers.13.mlp.gate.zeros": "model-00001-of-00004.safetensors",
+        "model.layers.13.mlp.switch_mlp.down_proj.qweight": "model-00001-of-00004.safetensors",
+        "model.layers.13.mlp.switch_mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.13.mlp.switch_mlp.down_proj.zeros": "model-00001-of-00004.safetensors",
+        "model.layers.13.mlp.switch_mlp.gate_proj.qweight": "model-00001-of-00004.safetensors",
+        "model.layers.13.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.13.mlp.switch_mlp.gate_proj.zeros": "model-00001-of-00004.safetensors",
+        "model.layers.13.mlp.switch_mlp.up_proj.qweight": "model-00001-of-00004.safetensors",
+        "model.layers.13.mlp.switch_mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.13.mlp.switch_mlp.up_proj.zeros": "model-00001-of-00004.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.13.self_attn.k_proj.channel_scale": "model-00001-of-00004.safetensors",
+        "model.layers.13.self_attn.k_proj.q_perm": "model-00001-of-00004.safetensors",
+        "model.layers.13.self_attn.k_proj.qweight": "model-00001-of-00004.safetensors",
+        "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.13.self_attn.k_proj.zeros": "model-00001-of-00004.safetensors",
+        "model.layers.13.self_attn.o_proj.channel_scale": "model-00001-of-00004.safetensors",
+        "model.layers.13.self_attn.o_proj.q_perm": "model-00001-of-00004.safetensors",
+        "model.layers.13.self_attn.o_proj.qweight": "model-00001-of-00004.safetensors",
+        "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.13.self_attn.o_proj.zeros": "model-00001-of-00004.safetensors",
+        "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.13.self_attn.q_proj.channel_scale": "model-00001-of-00004.safetensors",
+        "model.layers.13.self_attn.q_proj.q_perm": "model-00001-of-00004.safetensors",
+        "model.layers.13.self_attn.q_proj.qweight": "model-00001-of-00004.safetensors",
+        "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.13.self_attn.q_proj.zeros": "model-00001-of-00004.safetensors",
+        "model.layers.13.self_attn.v_proj.channel_scale": "model-00001-of-00004.safetensors",
+        "model.layers.13.self_attn.v_proj.q_perm": "model-00001-of-00004.safetensors",
+        "model.layers.13.self_attn.v_proj.qweight": "model-00001-of-00004.safetensors",
+        "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.13.self_attn.v_proj.zeros": "model-00001-of-00004.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.14.mlp.gate.channel_scale": "model-00001-of-00004.safetensors",
+        "model.layers.14.mlp.gate.q_perm": "model-00001-of-00004.safetensors",
+        "model.layers.14.mlp.gate.qweight": "model-00001-of-00004.safetensors",
+        "model.layers.14.mlp.gate.scales": "model-00001-of-00004.safetensors",
+        "model.layers.14.mlp.gate.zeros": "model-00001-of-00004.safetensors",
         "model.layers.14.mlp.switch_mlp.down_proj.qweight": "model-00002-of-00004.safetensors",
         "model.layers.14.mlp.switch_mlp.down_proj.scales": "model-00002-of-00004.safetensors",
         "model.layers.14.mlp.switch_mlp.down_proj.zeros": "model-00002-of-00004.safetensors",
-        "model.layers.14.mlp.switch_mlp.gate_proj.qweight": "model-00002-of-00004.safetensors",
+        "model.layers.14.mlp.switch_mlp.gate_proj.qweight": "model-00001-of-00004.safetensors",
         "model.layers.14.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
         "model.layers.14.mlp.switch_mlp.gate_proj.zeros": "model-00002-of-00004.safetensors",
         "model.layers.14.mlp.switch_mlp.up_proj.qweight": "model-00002-of-00004.safetensors",
         "model.layers.14.mlp.switch_mlp.up_proj.scales": "model-00002-of-00004.safetensors",
         "model.layers.14.mlp.switch_mlp.up_proj.zeros": "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.channel_scale": "model-00002-of-00004.safetensors",
-        "model.layers.14.self_attn.k_proj.q_perm": "model-00002-of-00004.safetensors",
-        "model.layers.14.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors",
-        "model.layers.14.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
-        "model.layers.14.self_attn.k_proj.zeros": "model-00002-of-00004.safetensors",
-        "model.layers.14.self_attn.o_proj.channel_scale": "model-00002-of-00004.safetensors",
-        "model.layers.14.self_attn.o_proj.q_perm": "model-00002-of-00004.safetensors",
-        "model.layers.14.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors",
-        "model.layers.14.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
-        "model.layers.14.self_attn.o_proj.zeros": "model-00002-of-00004.safetensors",
-        "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
-        "model.layers.14.self_attn.q_proj.channel_scale": "model-00002-of-00004.safetensors",
-        "model.layers.14.self_attn.q_proj.q_perm": "model-00002-of-00004.safetensors",
-        "model.layers.14.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors",
-        "model.layers.14.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
-        "model.layers.14.self_attn.q_proj.zeros": "model-00002-of-00004.safetensors",
-        "model.layers.14.self_attn.v_proj.channel_scale": "model-00002-of-00004.safetensors",
-        "model.layers.14.self_attn.v_proj.q_perm": "model-00002-of-00004.safetensors",
-        "model.layers.14.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors",
-        "model.layers.14.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
-        "model.layers.14.self_attn.v_proj.zeros": "model-00002-of-00004.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.14.self_attn.k_proj.channel_scale": "model-00001-of-00004.safetensors",
+        "model.layers.14.self_attn.k_proj.q_perm": "model-00001-of-00004.safetensors",
+        "model.layers.14.self_attn.k_proj.qweight": "model-00001-of-00004.safetensors",
+        "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.14.self_attn.k_proj.zeros": "model-00001-of-00004.safetensors",
+        "model.layers.14.self_attn.o_proj.channel_scale": "model-00001-of-00004.safetensors",
+        "model.layers.14.self_attn.o_proj.q_perm": "model-00001-of-00004.safetensors",
+        "model.layers.14.self_attn.o_proj.qweight": "model-00001-of-00004.safetensors",
+        "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.14.self_attn.o_proj.zeros": "model-00001-of-00004.safetensors",
+        "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.14.self_attn.q_proj.channel_scale": "model-00001-of-00004.safetensors",
+        "model.layers.14.self_attn.q_proj.q_perm": "model-00001-of-00004.safetensors",
+        "model.layers.14.self_attn.q_proj.qweight": "model-00001-of-00004.safetensors",
+        "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.14.self_attn.q_proj.zeros": "model-00001-of-00004.safetensors",
+        "model.layers.14.self_attn.v_proj.channel_scale": "model-00001-of-00004.safetensors",
+        "model.layers.14.self_attn.v_proj.q_perm": "model-00001-of-00004.safetensors",
+        "model.layers.14.self_attn.v_proj.qweight": "model-00001-of-00004.safetensors",
+        "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.14.self_attn.v_proj.zeros": "model-00001-of-00004.safetensors",
         "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
         "model.layers.15.mlp.gate.channel_scale": "model-00002-of-00004.safetensors",
         "model.layers.15.mlp.gate.q_perm": "model-00002-of-00004.safetensors",
@@ -809,15 +809,15 @@
         "model.layers.28.mlp.gate.qweight": "model-00002-of-00004.safetensors",
         "model.layers.28.mlp.gate.scales": "model-00002-of-00004.safetensors",
         "model.layers.28.mlp.gate.zeros": "model-00002-of-00004.safetensors",
-        "model.layers.28.mlp.switch_mlp.down_proj.qweight": "model-00003-of-00004.safetensors",
-        "model.layers.28.mlp.switch_mlp.down_proj.scales": "model-00003-of-00004.safetensors",
-        "model.layers.28.mlp.switch_mlp.down_proj.zeros": "model-00003-of-00004.safetensors",
+        "model.layers.28.mlp.switch_mlp.down_proj.qweight": "model-00002-of-00004.safetensors",
+        "model.layers.28.mlp.switch_mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.28.mlp.switch_mlp.down_proj.zeros": "model-00002-of-00004.safetensors",
         "model.layers.28.mlp.switch_mlp.gate_proj.qweight": "model-00002-of-00004.safetensors",
         "model.layers.28.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
         "model.layers.28.mlp.switch_mlp.gate_proj.zeros": "model-00002-of-00004.safetensors",
-        "model.layers.28.mlp.switch_mlp.up_proj.qweight": "model-00003-of-00004.safetensors",
-        "model.layers.28.mlp.switch_mlp.up_proj.scales": "model-00003-of-00004.safetensors",
-        "model.layers.28.mlp.switch_mlp.up_proj.zeros": "model-00003-of-00004.safetensors",
+        "model.layers.28.mlp.switch_mlp.up_proj.qweight": "model-00002-of-00004.safetensors",
+        "model.layers.28.mlp.switch_mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.28.mlp.switch_mlp.up_proj.zeros": "model-00002-of-00004.safetensors",
         "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
         "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
         "model.layers.28.self_attn.k_proj.channel_scale": "model-00002-of-00004.safetensors",
@@ -841,44 +841,44 @@
         "model.layers.28.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors",
         "model.layers.28.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
         "model.layers.28.self_attn.v_proj.zeros": "model-00002-of-00004.safetensors",
-        "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
-        "model.layers.29.mlp.gate.channel_scale": "model-00003-of-00004.safetensors",
-        "model.layers.29.mlp.gate.q_perm": "model-00003-of-00004.safetensors",
-        "model.layers.29.mlp.gate.qweight": "model-00003-of-00004.safetensors",
-        "model.layers.29.mlp.gate.scales": "model-00003-of-00004.safetensors",
-        "model.layers.29.mlp.gate.zeros": "model-00003-of-00004.safetensors",
-        "model.layers.29.mlp.switch_mlp.down_proj.qweight": "model-00003-of-00004.safetensors",
-        "model.layers.29.mlp.switch_mlp.down_proj.scales": "model-00003-of-00004.safetensors",
-        "model.layers.29.mlp.switch_mlp.down_proj.zeros": "model-00003-of-00004.safetensors",
-        "model.layers.29.mlp.switch_mlp.gate_proj.qweight": "model-00003-of-00004.safetensors",
-        "model.layers.29.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
-        "model.layers.29.mlp.switch_mlp.gate_proj.zeros": "model-00003-of-00004.safetensors",
-        "model.layers.29.mlp.switch_mlp.up_proj.qweight": "model-00003-of-00004.safetensors",
-        "model.layers.29.mlp.switch_mlp.up_proj.scales": "model-00003-of-00004.safetensors",
-        "model.layers.29.mlp.switch_mlp.up_proj.zeros": "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.channel_scale": "model-00003-of-00004.safetensors",
-        "model.layers.29.self_attn.k_proj.q_perm": "model-00003-of-00004.safetensors",
-        "model.layers.29.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors",
-        "model.layers.29.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
-        "model.layers.29.self_attn.k_proj.zeros": "model-00003-of-00004.safetensors",
-        "model.layers.29.self_attn.o_proj.channel_scale": "model-00003-of-00004.safetensors",
-        "model.layers.29.self_attn.o_proj.q_perm": "model-00003-of-00004.safetensors",
-        "model.layers.29.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors",
-        "model.layers.29.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
-        "model.layers.29.self_attn.o_proj.zeros": "model-00003-of-00004.safetensors",
-        "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
-        "model.layers.29.self_attn.q_proj.channel_scale": "model-00003-of-00004.safetensors",
-        "model.layers.29.self_attn.q_proj.q_perm": "model-00003-of-00004.safetensors",
-        "model.layers.29.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors",
-        "model.layers.29.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
-        "model.layers.29.self_attn.q_proj.zeros": "model-00003-of-00004.safetensors",
-        "model.layers.29.self_attn.v_proj.channel_scale": "model-00003-of-00004.safetensors",
-        "model.layers.29.self_attn.v_proj.q_perm": "model-00003-of-00004.safetensors",
-        "model.layers.29.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors",
-        "model.layers.29.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
-        "model.layers.29.self_attn.v_proj.zeros": "model-00003-of-00004.safetensors",
+        "model.layers.29.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.29.mlp.gate.channel_scale": "model-00002-of-00004.safetensors",
+        "model.layers.29.mlp.gate.q_perm": "model-00002-of-00004.safetensors",
+        "model.layers.29.mlp.gate.qweight": "model-00002-of-00004.safetensors",
+        "model.layers.29.mlp.gate.scales": "model-00002-of-00004.safetensors",
+        "model.layers.29.mlp.gate.zeros": "model-00002-of-00004.safetensors",
+        "model.layers.29.mlp.switch_mlp.down_proj.qweight": "model-00002-of-00004.safetensors",
+        "model.layers.29.mlp.switch_mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.29.mlp.switch_mlp.down_proj.zeros": "model-00002-of-00004.safetensors",
+        "model.layers.29.mlp.switch_mlp.gate_proj.qweight": "model-00002-of-00004.safetensors",
+        "model.layers.29.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.29.mlp.switch_mlp.gate_proj.zeros": "model-00002-of-00004.safetensors",
+        "model.layers.29.mlp.switch_mlp.up_proj.qweight": "model-00002-of-00004.safetensors",
+        "model.layers.29.mlp.switch_mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.29.mlp.switch_mlp.up_proj.zeros": "model-00002-of-00004.safetensors",
+        "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.29.self_attn.k_proj.channel_scale": "model-00002-of-00004.safetensors",
+        "model.layers.29.self_attn.k_proj.q_perm": "model-00002-of-00004.safetensors",
+        "model.layers.29.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors",
+        "model.layers.29.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.29.self_attn.k_proj.zeros": "model-00002-of-00004.safetensors",
+        "model.layers.29.self_attn.o_proj.channel_scale": "model-00002-of-00004.safetensors",
+        "model.layers.29.self_attn.o_proj.q_perm": "model-00002-of-00004.safetensors",
+        "model.layers.29.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors",
+        "model.layers.29.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.29.self_attn.o_proj.zeros": "model-00002-of-00004.safetensors",
+        "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.29.self_attn.q_proj.channel_scale": "model-00002-of-00004.safetensors",
+        "model.layers.29.self_attn.q_proj.q_perm": "model-00002-of-00004.safetensors",
+        "model.layers.29.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors",
+        "model.layers.29.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.29.self_attn.q_proj.zeros": "model-00002-of-00004.safetensors",
+        "model.layers.29.self_attn.v_proj.channel_scale": "model-00002-of-00004.safetensors",
+        "model.layers.29.self_attn.v_proj.q_perm": "model-00002-of-00004.safetensors",
+        "model.layers.29.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors",
+        "model.layers.29.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.29.self_attn.v_proj.zeros": "model-00002-of-00004.safetensors",
         "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
         "model.layers.3.mlp.gate.channel_scale": "model-00001-of-00004.safetensors",
         "model.layers.3.mlp.gate.q_perm": "model-00001-of-00004.safetensors",
@@ -917,44 +917,44 @@
         "model.layers.3.self_attn.v_proj.qweight": "model-00001-of-00004.safetensors",
         "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
         "model.layers.3.self_attn.v_proj.zeros": "model-00001-of-00004.safetensors",
-        "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
-        "model.layers.30.mlp.gate.channel_scale": "model-00003-of-00004.safetensors",
-        "model.layers.30.mlp.gate.q_perm": "model-00003-of-00004.safetensors",
-        "model.layers.30.mlp.gate.qweight": "model-00003-of-00004.safetensors",
-        "model.layers.30.mlp.gate.scales": "model-00003-of-00004.safetensors",
-        "model.layers.30.mlp.gate.zeros": "model-00003-of-00004.safetensors",
+        "model.layers.30.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.30.mlp.gate.channel_scale": "model-00002-of-00004.safetensors",
+        "model.layers.30.mlp.gate.q_perm": "model-00002-of-00004.safetensors",
+        "model.layers.30.mlp.gate.qweight": "model-00002-of-00004.safetensors",
+        "model.layers.30.mlp.gate.scales": "model-00002-of-00004.safetensors",
+        "model.layers.30.mlp.gate.zeros": "model-00002-of-00004.safetensors",
         "model.layers.30.mlp.switch_mlp.down_proj.qweight": "model-00003-of-00004.safetensors",
         "model.layers.30.mlp.switch_mlp.down_proj.scales": "model-00003-of-00004.safetensors",
         "model.layers.30.mlp.switch_mlp.down_proj.zeros": "model-00003-of-00004.safetensors",
-        "model.layers.30.mlp.switch_mlp.gate_proj.qweight": "model-00003-of-00004.safetensors",
-        "model.layers.30.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
-        "model.layers.30.mlp.switch_mlp.gate_proj.zeros": "model-00003-of-00004.safetensors",
+        "model.layers.30.mlp.switch_mlp.gate_proj.qweight": "model-00002-of-00004.safetensors",
+        "model.layers.30.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.30.mlp.switch_mlp.gate_proj.zeros": "model-00002-of-00004.safetensors",
         "model.layers.30.mlp.switch_mlp.up_proj.qweight": "model-00003-of-00004.safetensors",
         "model.layers.30.mlp.switch_mlp.up_proj.scales": "model-00003-of-00004.safetensors",
         "model.layers.30.mlp.switch_mlp.up_proj.zeros": "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.channel_scale": "model-00003-of-00004.safetensors",
-        "model.layers.30.self_attn.k_proj.q_perm": "model-00003-of-00004.safetensors",
-        "model.layers.30.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors",
-        "model.layers.30.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
-        "model.layers.30.self_attn.k_proj.zeros": "model-00003-of-00004.safetensors",
-        "model.layers.30.self_attn.o_proj.channel_scale": "model-00003-of-00004.safetensors",
-        "model.layers.30.self_attn.o_proj.q_perm": "model-00003-of-00004.safetensors",
-        "model.layers.30.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors",
-        "model.layers.30.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
-        "model.layers.30.self_attn.o_proj.zeros": "model-00003-of-00004.safetensors",
-        "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
-        "model.layers.30.self_attn.q_proj.channel_scale": "model-00003-of-00004.safetensors",
-        "model.layers.30.self_attn.q_proj.q_perm": "model-00003-of-00004.safetensors",
-        "model.layers.30.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors",
-        "model.layers.30.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
-        "model.layers.30.self_attn.q_proj.zeros": "model-00003-of-00004.safetensors",
-        "model.layers.30.self_attn.v_proj.channel_scale": "model-00003-of-00004.safetensors",
-        "model.layers.30.self_attn.v_proj.q_perm": "model-00003-of-00004.safetensors",
-        "model.layers.30.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors",
-        "model.layers.30.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
-        "model.layers.30.self_attn.v_proj.zeros": "model-00003-of-00004.safetensors",
+        "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.30.self_attn.k_proj.channel_scale": "model-00002-of-00004.safetensors",
+        "model.layers.30.self_attn.k_proj.q_perm": "model-00002-of-00004.safetensors",
+        "model.layers.30.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors",
+        "model.layers.30.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.30.self_attn.k_proj.zeros": "model-00002-of-00004.safetensors",
+        "model.layers.30.self_attn.o_proj.channel_scale": "model-00002-of-00004.safetensors",
+        "model.layers.30.self_attn.o_proj.q_perm": "model-00002-of-00004.safetensors",
+        "model.layers.30.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors",
+        "model.layers.30.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.30.self_attn.o_proj.zeros": "model-00002-of-00004.safetensors",
+        "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.30.self_attn.q_proj.channel_scale": "model-00002-of-00004.safetensors",
+        "model.layers.30.self_attn.q_proj.q_perm": "model-00002-of-00004.safetensors",
+        "model.layers.30.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors",
+        "model.layers.30.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.30.self_attn.q_proj.zeros": "model-00002-of-00004.safetensors",
+        "model.layers.30.self_attn.v_proj.channel_scale": "model-00002-of-00004.safetensors",
+        "model.layers.30.self_attn.v_proj.q_perm": "model-00002-of-00004.safetensors",
+        "model.layers.30.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors",
+        "model.layers.30.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.30.self_attn.v_proj.zeros": "model-00002-of-00004.safetensors",
         "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
         "model.layers.31.mlp.gate.channel_scale": "model-00003-of-00004.safetensors",
         "model.layers.31.mlp.gate.q_perm": "model-00003-of-00004.safetensors",
@@ -1493,15 +1493,15 @@
         "model.layers.44.mlp.gate.qweight": "model-00003-of-00004.safetensors",
         "model.layers.44.mlp.gate.scales": "model-00003-of-00004.safetensors",
         "model.layers.44.mlp.gate.zeros": "model-00003-of-00004.safetensors",
-        "model.layers.44.mlp.switch_mlp.down_proj.qweight": "model-00004-of-00004.safetensors",
-        "model.layers.44.mlp.switch_mlp.down_proj.scales": "model-00004-of-00004.safetensors",
-        "model.layers.44.mlp.switch_mlp.down_proj.zeros": "model-00004-of-00004.safetensors",
+        "model.layers.44.mlp.switch_mlp.down_proj.qweight": "model-00003-of-00004.safetensors",
+        "model.layers.44.mlp.switch_mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.44.mlp.switch_mlp.down_proj.zeros": "model-00003-of-00004.safetensors",
         "model.layers.44.mlp.switch_mlp.gate_proj.qweight": "model-00003-of-00004.safetensors",
         "model.layers.44.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
         "model.layers.44.mlp.switch_mlp.gate_proj.zeros": "model-00003-of-00004.safetensors",
-        "model.layers.44.mlp.switch_mlp.up_proj.qweight": "model-00004-of-00004.safetensors",
-        "model.layers.44.mlp.switch_mlp.up_proj.scales": "model-00004-of-00004.safetensors",
-        "model.layers.44.mlp.switch_mlp.up_proj.zeros": "model-00004-of-00004.safetensors",
+        "model.layers.44.mlp.switch_mlp.up_proj.qweight": "model-00003-of-00004.safetensors",
+        "model.layers.44.mlp.switch_mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.44.mlp.switch_mlp.up_proj.zeros": "model-00003-of-00004.safetensors",
         "model.layers.44.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
         "model.layers.44.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
         "model.layers.44.self_attn.k_proj.channel_scale": "model-00003-of-00004.safetensors",
@@ -1525,82 +1525,82 @@
         "model.layers.44.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors",
         "model.layers.44.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
         "model.layers.44.self_attn.v_proj.zeros": "model-00003-of-00004.safetensors",
-        "model.layers.45.input_layernorm.weight": "model-00004-of-00004.safetensors",
-        "model.layers.45.mlp.gate.channel_scale": "model-00004-of-00004.safetensors",
-        "model.layers.45.mlp.gate.q_perm": "model-00004-of-00004.safetensors",
-        "model.layers.45.mlp.gate.qweight": "model-00004-of-00004.safetensors",
-        "model.layers.45.mlp.gate.scales": "model-00004-of-00004.safetensors",
-        "model.layers.45.mlp.gate.zeros": "model-00004-of-00004.safetensors",
-        "model.layers.45.mlp.switch_mlp.down_proj.qweight": "model-00004-of-00004.safetensors",
-        "model.layers.45.mlp.switch_mlp.down_proj.scales": "model-00004-of-00004.safetensors",
-        "model.layers.45.mlp.switch_mlp.down_proj.zeros": "model-00004-of-00004.safetensors",
-        "model.layers.45.mlp.switch_mlp.gate_proj.qweight": "model-00004-of-00004.safetensors",
-        "model.layers.45.mlp.switch_mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
-        "model.layers.45.mlp.switch_mlp.gate_proj.zeros": "model-00004-of-00004.safetensors",
-        "model.layers.45.mlp.switch_mlp.up_proj.qweight": "model-00004-of-00004.safetensors",
-        "model.layers.45.mlp.switch_mlp.up_proj.scales": "model-00004-of-00004.safetensors",
-        "model.layers.45.mlp.switch_mlp.up_proj.zeros": "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.channel_scale": "model-00004-of-00004.safetensors",
-        "model.layers.45.self_attn.k_proj.q_perm": "model-00004-of-00004.safetensors",
-        "model.layers.45.self_attn.k_proj.qweight": "model-00004-of-00004.safetensors",
-        "model.layers.45.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
-        "model.layers.45.self_attn.k_proj.zeros": "model-00004-of-00004.safetensors",
-        "model.layers.45.self_attn.o_proj.channel_scale": "model-00004-of-00004.safetensors",
-        "model.layers.45.self_attn.o_proj.q_perm": "model-00004-of-00004.safetensors",
-        "model.layers.45.self_attn.o_proj.qweight": "model-00004-of-00004.safetensors",
-        "model.layers.45.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
-        "model.layers.45.self_attn.o_proj.zeros": "model-00004-of-00004.safetensors",
-        "model.layers.45.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
-        "model.layers.45.self_attn.q_proj.channel_scale": "model-00004-of-00004.safetensors",
-        "model.layers.45.self_attn.q_proj.q_perm": "model-00004-of-00004.safetensors",
-        "model.layers.45.self_attn.q_proj.qweight": "model-00004-of-00004.safetensors",
-        "model.layers.45.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
-        "model.layers.45.self_attn.q_proj.zeros": "model-00004-of-00004.safetensors",
-        "model.layers.45.self_attn.v_proj.channel_scale": "model-00004-of-00004.safetensors",
-        "model.layers.45.self_attn.v_proj.q_perm": "model-00004-of-00004.safetensors",
-        "model.layers.45.self_attn.v_proj.qweight": "model-00004-of-00004.safetensors",
-        "model.layers.45.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
-        "model.layers.45.self_attn.v_proj.zeros": "model-00004-of-00004.safetensors",
-        "model.layers.46.input_layernorm.weight": "model-00004-of-00004.safetensors",
-        "model.layers.46.mlp.gate.channel_scale": "model-00004-of-00004.safetensors",
-        "model.layers.46.mlp.gate.q_perm": "model-00004-of-00004.safetensors",
-        "model.layers.46.mlp.gate.qweight": "model-00004-of-00004.safetensors",
-        "model.layers.46.mlp.gate.scales": "model-00004-of-00004.safetensors",
-        "model.layers.46.mlp.gate.zeros": "model-00004-of-00004.safetensors",
+        "model.layers.45.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.45.mlp.gate.channel_scale": "model-00003-of-00004.safetensors",
+        "model.layers.45.mlp.gate.q_perm": "model-00003-of-00004.safetensors",
+        "model.layers.45.mlp.gate.qweight": "model-00003-of-00004.safetensors",
+        "model.layers.45.mlp.gate.scales": "model-00003-of-00004.safetensors",
+        "model.layers.45.mlp.gate.zeros": "model-00003-of-00004.safetensors",
+        "model.layers.45.mlp.switch_mlp.down_proj.qweight": "model-00003-of-00004.safetensors",
+        "model.layers.45.mlp.switch_mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.45.mlp.switch_mlp.down_proj.zeros": "model-00003-of-00004.safetensors",
+        "model.layers.45.mlp.switch_mlp.gate_proj.qweight": "model-00003-of-00004.safetensors",
+        "model.layers.45.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.45.mlp.switch_mlp.gate_proj.zeros": "model-00003-of-00004.safetensors",
+        "model.layers.45.mlp.switch_mlp.up_proj.qweight": "model-00003-of-00004.safetensors",
+        "model.layers.45.mlp.switch_mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.45.mlp.switch_mlp.up_proj.zeros": "model-00003-of-00004.safetensors",
+        "model.layers.45.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.45.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.45.self_attn.k_proj.channel_scale": "model-00003-of-00004.safetensors",
+        "model.layers.45.self_attn.k_proj.q_perm": "model-00003-of-00004.safetensors",
+        "model.layers.45.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors",
+        "model.layers.45.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.45.self_attn.k_proj.zeros": "model-00003-of-00004.safetensors",
+        "model.layers.45.self_attn.o_proj.channel_scale": "model-00003-of-00004.safetensors",
+        "model.layers.45.self_attn.o_proj.q_perm": "model-00003-of-00004.safetensors",
+        "model.layers.45.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors",
+        "model.layers.45.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.45.self_attn.o_proj.zeros": "model-00003-of-00004.safetensors",
+        "model.layers.45.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.45.self_attn.q_proj.channel_scale": "model-00003-of-00004.safetensors",
+        "model.layers.45.self_attn.q_proj.q_perm": "model-00003-of-00004.safetensors",
+        "model.layers.45.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors",
+        "model.layers.45.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.45.self_attn.q_proj.zeros": "model-00003-of-00004.safetensors",
+        "model.layers.45.self_attn.v_proj.channel_scale": "model-00003-of-00004.safetensors",
+        "model.layers.45.self_attn.v_proj.q_perm": "model-00003-of-00004.safetensors",
+        "model.layers.45.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors",
+        "model.layers.45.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.45.self_attn.v_proj.zeros": "model-00003-of-00004.safetensors",
+        "model.layers.46.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.46.mlp.gate.channel_scale": "model-00003-of-00004.safetensors",
+        "model.layers.46.mlp.gate.q_perm": "model-00003-of-00004.safetensors",
+        "model.layers.46.mlp.gate.qweight": "model-00003-of-00004.safetensors",
+        "model.layers.46.mlp.gate.scales": "model-00003-of-00004.safetensors",
+        "model.layers.46.mlp.gate.zeros": "model-00003-of-00004.safetensors",
         "model.layers.46.mlp.switch_mlp.down_proj.qweight": "model-00004-of-00004.safetensors",
         "model.layers.46.mlp.switch_mlp.down_proj.scales": "model-00004-of-00004.safetensors",
         "model.layers.46.mlp.switch_mlp.down_proj.zeros": "model-00004-of-00004.safetensors",
-        "model.layers.46.mlp.switch_mlp.gate_proj.qweight": "model-00004-of-00004.safetensors",
-        "model.layers.46.mlp.switch_mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
-        "model.layers.46.mlp.switch_mlp.gate_proj.zeros": "model-00004-of-00004.safetensors",
+        "model.layers.46.mlp.switch_mlp.gate_proj.qweight": "model-00003-of-00004.safetensors",
+        "model.layers.46.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.46.mlp.switch_mlp.gate_proj.zeros": "model-00003-of-00004.safetensors",
         "model.layers.46.mlp.switch_mlp.up_proj.qweight": "model-00004-of-00004.safetensors",
         "model.layers.46.mlp.switch_mlp.up_proj.scales": "model-00004-of-00004.safetensors",
         "model.layers.46.mlp.switch_mlp.up_proj.zeros": "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.channel_scale": "model-00004-of-00004.safetensors",
-        "model.layers.46.self_attn.k_proj.q_perm": "model-00004-of-00004.safetensors",
-        "model.layers.46.self_attn.k_proj.qweight": "model-00004-of-00004.safetensors",
-        "model.layers.46.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
-        "model.layers.46.self_attn.k_proj.zeros": "model-00004-of-00004.safetensors",
-        "model.layers.46.self_attn.o_proj.channel_scale": "model-00004-of-00004.safetensors",
-        "model.layers.46.self_attn.o_proj.q_perm": "model-00004-of-00004.safetensors",
-        "model.layers.46.self_attn.o_proj.qweight": "model-00004-of-00004.safetensors",
-        "model.layers.46.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
-        "model.layers.46.self_attn.o_proj.zeros": "model-00004-of-00004.safetensors",
-        "model.layers.46.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
-        "model.layers.46.self_attn.q_proj.channel_scale": "model-00004-of-00004.safetensors",
-        "model.layers.46.self_attn.q_proj.q_perm": "model-00004-of-00004.safetensors",
-        "model.layers.46.self_attn.q_proj.qweight": "model-00004-of-00004.safetensors",
-        "model.layers.46.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
-        "model.layers.46.self_attn.q_proj.zeros": "model-00004-of-00004.safetensors",
-        "model.layers.46.self_attn.v_proj.channel_scale": "model-00004-of-00004.safetensors",
-        "model.layers.46.self_attn.v_proj.q_perm": "model-00004-of-00004.safetensors",
-        "model.layers.46.self_attn.v_proj.qweight": "model-00004-of-00004.safetensors",
-        "model.layers.46.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
-        "model.layers.46.self_attn.v_proj.zeros": "model-00004-of-00004.safetensors",
+        "model.layers.46.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.46.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.46.self_attn.k_proj.channel_scale": "model-00003-of-00004.safetensors",
+        "model.layers.46.self_attn.k_proj.q_perm": "model-00003-of-00004.safetensors",
+        "model.layers.46.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors",
+        "model.layers.46.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.46.self_attn.k_proj.zeros": "model-00003-of-00004.safetensors",
+        "model.layers.46.self_attn.o_proj.channel_scale": "model-00003-of-00004.safetensors",
+        "model.layers.46.self_attn.o_proj.q_perm": "model-00003-of-00004.safetensors",
+        "model.layers.46.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors",
+        "model.layers.46.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.46.self_attn.o_proj.zeros": "model-00003-of-00004.safetensors",
+        "model.layers.46.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.46.self_attn.q_proj.channel_scale": "model-00003-of-00004.safetensors",
+        "model.layers.46.self_attn.q_proj.q_perm": "model-00003-of-00004.safetensors",
+        "model.layers.46.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors",
+        "model.layers.46.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.46.self_attn.q_proj.zeros": "model-00003-of-00004.safetensors",
+        "model.layers.46.self_attn.v_proj.channel_scale": "model-00003-of-00004.safetensors",
+        "model.layers.46.self_attn.v_proj.q_perm": "model-00003-of-00004.safetensors",
+        "model.layers.46.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors",
+        "model.layers.46.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.46.self_attn.v_proj.zeros": "model-00003-of-00004.safetensors",
         "model.layers.47.input_layernorm.weight": "model-00004-of-00004.safetensors",
         "model.layers.47.mlp.gate.channel_scale": "model-00004-of-00004.safetensors",
         "model.layers.47.mlp.gate.q_perm": "model-00004-of-00004.safetensors",