Add files using upload-large-folder tool

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5fdf8bce59e04fbbd9ee87f14cca71408b7ce981d270f3ee0f2f549adc9f578
-size 5364545324
+oid sha256:51d03b7e56ac99187423afccf456df860d80012d324050aca7f391f7a21a3b8f
+size 5354513565

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbc1df0432c8f120d7dcd89c55da5274ee93c3e8a30fbb18c2d5da06d706673e
-size 5350492553
+oid sha256:4d0231fd2874758cdcadc01047d89a7b9aa15c266c057eee7c0514fc7530c160
+size 3848262656

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e752f5dcf0582c9f0b0b78939cf0e26fa979f25e0c56ac257b563cbe521455cb
-size 3159071730
+oid sha256:d2751216179c89b12f0fa5ea78f7f409d47fd6564e32f8cb4d2b59069085a5df
+size 1555824767

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
     "metadata": {
-        "total_size": 13873930240
+        "total_size": 10758420480
     },
     "weight_map": {
         "lm_head.weight": "model-00003-of-00003.safetensors",
@@ -161,35 +161,35 @@
         "model.layers.11.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
         "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.11.self_attn.v_proj.zeros": "model-00001-of-00003.safetensors",
-        "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.12.mlp.down_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.12.mlp.down_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.12.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.12.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.12.mlp.down_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.12.mlp.gate_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.12.mlp.gate_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.12.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.12.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.12.mlp.gate_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.12.mlp.up_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.12.mlp.up_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.12.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.12.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.12.mlp.up_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.12.mlp.down_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.12.mlp.down_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.12.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.12.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.12.mlp.down_proj.zeros": "model-00001-of-00003.safetensors",
+        "model.layers.12.mlp.gate_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.12.mlp.gate_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.12.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.12.mlp.gate_proj.zeros": "model-00001-of-00003.safetensors",
+        "model.layers.12.mlp.up_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.12.mlp.up_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.12.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.12.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.12.mlp.up_proj.zeros": "model-00001-of-00003.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
         "model.layers.12.self_attn.k_proj.channel_scale": "model-00001-of-00003.safetensors",
         "model.layers.12.self_attn.k_proj.q_perm": "model-00001-of-00003.safetensors",
         "model.layers.12.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
         "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.12.self_attn.k_proj.zeros": "model-00001-of-00003.safetensors",
-        "model.layers.12.self_attn.o_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.12.self_attn.o_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.12.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.12.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.12.self_attn.o_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.12.self_attn.o_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.12.self_attn.o_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.12.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.12.self_attn.o_proj.zeros": "model-00001-of-00003.safetensors",
+        "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
         "model.layers.12.self_attn.q_proj.channel_scale": "model-00001-of-00003.safetensors",
         "model.layers.12.self_attn.q_proj.q_perm": "model-00001-of-00003.safetensors",
         "model.layers.12.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
@@ -200,279 +200,279 @@
         "model.layers.12.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
         "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.12.self_attn.v_proj.zeros": "model-00001-of-00003.safetensors",
-        "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.13.mlp.down_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.13.mlp.down_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.13.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.13.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.13.mlp.down_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.13.mlp.gate_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.13.mlp.gate_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.13.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.13.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.13.mlp.gate_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.13.mlp.up_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.13.mlp.up_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.13.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.13.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.13.mlp.up_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.13.self_attn.k_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.13.self_attn.k_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.13.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.13.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.13.self_attn.k_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.13.self_attn.o_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.13.self_attn.o_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.13.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.13.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.13.self_attn.o_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.13.self_attn.q_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.13.self_attn.q_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.13.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.13.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.13.self_attn.q_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.13.self_attn.v_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.13.self_attn.v_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.13.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.13.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.13.self_attn.v_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.14.mlp.down_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.14.mlp.down_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.14.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.14.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.14.mlp.down_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.14.mlp.gate_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.14.mlp.gate_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.14.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.14.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.14.mlp.gate_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.14.mlp.up_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.14.mlp.up_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.14.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.14.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.14.mlp.up_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.14.self_attn.k_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.14.self_attn.k_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.14.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.14.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.14.self_attn.k_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.14.self_attn.o_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.14.self_attn.o_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.14.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.14.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.14.self_attn.o_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.14.self_attn.q_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.14.self_attn.q_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.14.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.14.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.14.self_attn.q_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.14.self_attn.v_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.14.self_attn.v_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.14.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.14.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.14.self_attn.v_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.15.mlp.down_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.15.mlp.down_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.15.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.15.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.15.mlp.down_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.15.mlp.gate_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.15.mlp.gate_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.15.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.15.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.15.mlp.gate_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.15.mlp.up_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.15.mlp.up_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.15.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.15.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.15.mlp.up_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.15.self_attn.k_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.15.self_attn.k_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.15.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.15.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.15.self_attn.k_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.15.self_attn.o_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.15.self_attn.o_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.15.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.15.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.15.self_attn.o_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.15.self_attn.q_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.15.self_attn.q_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.15.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.15.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.15.self_attn.q_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.15.self_attn.v_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.15.self_attn.v_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.15.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.15.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.15.self_attn.v_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.16.mlp.down_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.16.mlp.down_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.16.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.16.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.16.mlp.down_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.16.mlp.gate_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.16.mlp.gate_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.16.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.16.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.16.mlp.gate_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.16.mlp.up_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.16.mlp.up_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.16.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.16.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.16.mlp.up_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.16.self_attn.k_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.16.self_attn.k_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.16.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.16.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.16.self_attn.k_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.16.self_attn.o_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.16.self_attn.o_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.16.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.16.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.16.self_attn.o_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.16.self_attn.q_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.16.self_attn.q_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.16.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.16.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.16.self_attn.q_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.16.self_attn.v_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.16.self_attn.v_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.16.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.16.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.16.self_attn.v_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.17.mlp.down_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.17.mlp.down_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.17.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.17.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.17.mlp.down_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.17.mlp.gate_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.17.mlp.gate_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.17.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.17.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.17.mlp.gate_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.17.mlp.up_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.17.mlp.up_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.17.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.17.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.17.mlp.up_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.17.self_attn.k_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.17.self_attn.k_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.17.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.17.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.17.self_attn.k_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.17.self_attn.o_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.17.self_attn.o_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.17.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.17.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.17.self_attn.o_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.17.self_attn.q_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.17.self_attn.q_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.17.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.17.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.17.self_attn.q_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.17.self_attn.v_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.17.self_attn.v_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.17.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.17.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.17.self_attn.v_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.18.mlp.down_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.18.mlp.down_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.18.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.18.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.18.mlp.down_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.18.mlp.gate_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.18.mlp.gate_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.18.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.18.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.18.mlp.gate_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.18.mlp.up_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.18.mlp.up_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.18.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.18.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.18.mlp.up_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.18.self_attn.k_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.18.self_attn.k_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.18.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.18.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.18.self_attn.k_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.18.self_attn.o_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.18.self_attn.o_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.18.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.18.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.18.self_attn.o_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.18.self_attn.q_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.18.self_attn.q_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.18.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.18.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.18.self_attn.q_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.18.self_attn.v_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.18.self_attn.v_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.18.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.18.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.18.self_attn.v_proj.zeros": "model-00002-of-00003.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.13.mlp.down_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.13.mlp.down_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.13.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.13.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.13.mlp.down_proj.zeros": "model-00001-of-00003.safetensors",
+        "model.layers.13.mlp.gate_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.13.mlp.gate_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.13.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.13.mlp.gate_proj.zeros": "model-00001-of-00003.safetensors",
+        "model.layers.13.mlp.up_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.13.mlp.up_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.13.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.13.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.13.mlp.up_proj.zeros": "model-00001-of-00003.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.13.self_attn.k_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.13.self_attn.k_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.13.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.13.self_attn.k_proj.zeros": "model-00001-of-00003.safetensors",
+        "model.layers.13.self_attn.o_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.13.self_attn.o_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.13.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.13.self_attn.o_proj.zeros": "model-00001-of-00003.safetensors",
+        "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.13.self_attn.q_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.13.self_attn.q_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.13.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.13.self_attn.q_proj.zeros": "model-00001-of-00003.safetensors",
+        "model.layers.13.self_attn.v_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.13.self_attn.v_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.13.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.13.self_attn.v_proj.zeros": "model-00001-of-00003.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.14.mlp.down_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.14.mlp.down_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.14.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.14.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.14.mlp.down_proj.zeros": "model-00001-of-00003.safetensors",
+        "model.layers.14.mlp.gate_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.14.mlp.gate_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.14.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.14.mlp.gate_proj.zeros": "model-00001-of-00003.safetensors",
+        "model.layers.14.mlp.up_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.14.mlp.up_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.14.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.14.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.14.mlp.up_proj.zeros": "model-00001-of-00003.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.k_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.k_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.k_proj.zeros": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.o_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.o_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.o_proj.zeros": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.q_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.q_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.q_proj.zeros": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.v_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.v_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.14.self_attn.v_proj.zeros": "model-00001-of-00003.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.15.mlp.down_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.15.mlp.down_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.15.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.15.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.15.mlp.down_proj.zeros": "model-00001-of-00003.safetensors",
+        "model.layers.15.mlp.gate_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.15.mlp.gate_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.15.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.15.mlp.gate_proj.zeros": "model-00001-of-00003.safetensors",
+        "model.layers.15.mlp.up_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.15.mlp.up_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.15.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.15.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.15.mlp.up_proj.zeros": "model-00001-of-00003.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.15.self_attn.k_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.15.self_attn.k_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.15.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.15.self_attn.k_proj.zeros": "model-00001-of-00003.safetensors",
+        "model.layers.15.self_attn.o_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.15.self_attn.o_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.15.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.15.self_attn.o_proj.zeros": "model-00001-of-00003.safetensors",
+        "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.15.self_attn.q_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.15.self_attn.q_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.15.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.15.self_attn.q_proj.zeros": "model-00001-of-00003.safetensors",
+        "model.layers.15.self_attn.v_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.15.self_attn.v_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.15.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.15.self_attn.v_proj.zeros": "model-00001-of-00003.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.16.mlp.down_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.16.mlp.down_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.16.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.16.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.16.mlp.down_proj.zeros": "model-00001-of-00003.safetensors",
+        "model.layers.16.mlp.gate_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.16.mlp.gate_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.16.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.16.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.16.mlp.gate_proj.zeros": "model-00001-of-00003.safetensors",
+        "model.layers.16.mlp.up_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.16.mlp.up_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.16.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.16.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.16.mlp.up_proj.zeros": "model-00001-of-00003.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.16.self_attn.k_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.16.self_attn.k_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.16.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.16.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.16.self_attn.k_proj.zeros": "model-00001-of-00003.safetensors",
+        "model.layers.16.self_attn.o_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.16.self_attn.o_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.16.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.16.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.16.self_attn.o_proj.zeros": "model-00001-of-00003.safetensors",
+        "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.16.self_attn.q_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.16.self_attn.q_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.16.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.16.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.16.self_attn.q_proj.zeros": "model-00001-of-00003.safetensors",
+        "model.layers.16.self_attn.v_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.16.self_attn.v_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.16.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.16.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.16.self_attn.v_proj.zeros": "model-00001-of-00003.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.17.mlp.down_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.17.mlp.down_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.17.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.17.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.17.mlp.down_proj.zeros": "model-00001-of-00003.safetensors",
+        "model.layers.17.mlp.gate_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.17.mlp.gate_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.17.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.17.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.17.mlp.gate_proj.zeros": "model-00001-of-00003.safetensors",
+        "model.layers.17.mlp.up_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.17.mlp.up_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.17.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.17.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.17.mlp.up_proj.zeros": "model-00001-of-00003.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.17.self_attn.k_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.17.self_attn.k_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.17.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.17.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.17.self_attn.k_proj.zeros": "model-00001-of-00003.safetensors",
+        "model.layers.17.self_attn.o_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.17.self_attn.o_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.17.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.17.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.17.self_attn.o_proj.zeros": "model-00001-of-00003.safetensors",
+        "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.17.self_attn.q_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.17.self_attn.q_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.17.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.17.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.17.self_attn.q_proj.zeros": "model-00001-of-00003.safetensors",
+        "model.layers.17.self_attn.v_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.17.self_attn.v_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.17.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.17.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.17.self_attn.v_proj.zeros": "model-00001-of-00003.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.18.mlp.down_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.18.mlp.down_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.18.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.18.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.18.mlp.down_proj.zeros": "model-00001-of-00003.safetensors",
+        "model.layers.18.mlp.gate_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.18.mlp.gate_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.18.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.18.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.18.mlp.gate_proj.zeros": "model-00001-of-00003.safetensors",
+        "model.layers.18.mlp.up_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.18.mlp.up_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.18.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.18.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.18.mlp.up_proj.zeros": "model-00001-of-00003.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.18.self_attn.k_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.18.self_attn.k_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.18.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.18.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.18.self_attn.k_proj.zeros": "model-00001-of-00003.safetensors",
+        "model.layers.18.self_attn.o_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.18.self_attn.o_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.18.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.18.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.18.self_attn.o_proj.zeros": "model-00001-of-00003.safetensors",
+        "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.18.self_attn.q_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.18.self_attn.q_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.18.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.18.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.18.self_attn.q_proj.zeros": "model-00001-of-00003.safetensors",
+        "model.layers.18.self_attn.v_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.18.self_attn.v_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.18.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.18.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.18.self_attn.v_proj.zeros": "model-00001-of-00003.safetensors",
         "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.19.mlp.down_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.19.mlp.down_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.19.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.19.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.19.mlp.down_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.19.mlp.gate_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.19.mlp.gate_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.19.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.19.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.19.mlp.gate_proj.zeros": "model-00002-of-00003.safetensors",
+        "model.layers.19.mlp.down_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.19.mlp.down_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.19.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.19.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.19.mlp.down_proj.zeros": "model-00001-of-00003.safetensors",
+        "model.layers.19.mlp.gate_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.19.mlp.gate_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.19.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.19.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.19.mlp.gate_proj.zeros": "model-00001-of-00003.safetensors",
         "model.layers.19.mlp.up_proj.channel_scale": "model-00002-of-00003.safetensors",
         "model.layers.19.mlp.up_proj.q_perm": "model-00002-of-00003.safetensors",
         "model.layers.19.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
         "model.layers.19.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.19.mlp.up_proj.zeros": "model-00002-of-00003.safetensors",
         "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.19.self_attn.k_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.19.self_attn.k_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.19.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.19.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.19.self_attn.k_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.19.self_attn.o_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.19.self_attn.o_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.19.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.19.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.19.self_attn.o_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
-        "model.layers.19.self_attn.q_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.19.self_attn.q_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.19.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.19.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.19.self_attn.q_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.19.self_attn.v_proj.channel_scale": "model-00002-of-00003.safetensors",
-        "model.layers.19.self_attn.v_proj.q_perm": "model-00002-of-00003.safetensors",
-        "model.layers.19.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
-        "model.layers.19.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
-        "model.layers.19.self_attn.v_proj.zeros": "model-00002-of-00003.safetensors",
+        "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.19.self_attn.k_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.19.self_attn.k_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.19.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.19.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.19.self_attn.k_proj.zeros": "model-00001-of-00003.safetensors",
+        "model.layers.19.self_attn.o_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.19.self_attn.o_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.19.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.19.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.19.self_attn.o_proj.zeros": "model-00001-of-00003.safetensors",
+        "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.19.self_attn.q_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.19.self_attn.q_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.19.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.19.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.19.self_attn.q_proj.zeros": "model-00001-of-00003.safetensors",
+        "model.layers.19.self_attn.v_proj.channel_scale": "model-00001-of-00003.safetensors",
+        "model.layers.19.self_attn.v_proj.q_perm": "model-00001-of-00003.safetensors",
+        "model.layers.19.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
+        "model.layers.19.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+        "model.layers.19.self_attn.v_proj.zeros": "model-00001-of-00003.safetensors",
         "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
         "model.layers.2.mlp.down_proj.channel_scale": "model-00001-of-00003.safetensors",
         "model.layers.2.mlp.down_proj.q_perm": "model-00001-of-00003.safetensors",
@@ -1292,7 +1292,7 @@
         "model.layers.38.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
         "model.layers.38.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.38.self_attn.v_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.39.input_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.39.input_layernorm.weight": "model-00002-of-00003.safetensors",
         "model.layers.39.mlp.down_proj.channel_scale": "model-00002-of-00003.safetensors",
         "model.layers.39.mlp.down_proj.q_perm": "model-00002-of-00003.safetensors",
         "model.layers.39.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
@@ -1303,12 +1303,12 @@
         "model.layers.39.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
         "model.layers.39.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
         "model.layers.39.mlp.gate_proj.zeros": "model-00002-of-00003.safetensors",
-        "model.layers.39.mlp.up_proj.channel_scale": "model-00003-of-00003.safetensors",
-        "model.layers.39.mlp.up_proj.q_perm": "model-00003-of-00003.safetensors",
-        "model.layers.39.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
-        "model.layers.39.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
-        "model.layers.39.mlp.up_proj.zeros": "model-00003-of-00003.safetensors",
-        "model.layers.39.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.39.mlp.up_proj.channel_scale": "model-00002-of-00003.safetensors",
+        "model.layers.39.mlp.up_proj.q_perm": "model-00002-of-00003.safetensors",
+        "model.layers.39.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
+        "model.layers.39.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+        "model.layers.39.mlp.up_proj.zeros": "model-00002-of-00003.safetensors",
+        "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
         "model.layers.39.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
         "model.layers.39.self_attn.k_proj.channel_scale": "model-00002-of-00003.safetensors",
         "model.layers.39.self_attn.k_proj.q_perm": "model-00002-of-00003.safetensors",
@@ -1565,6 +1565,6 @@
         "model.layers.9.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
         "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
         "model.layers.9.self_attn.v_proj.zeros": "model-00001-of-00003.safetensors",
-        "model.norm.weight": "model-00003-of-00003.safetensors"
+        "model.norm.weight": "model-00002-of-00003.safetensors"
     }
 }