Update model

config.json

@@ -24,7 +24,7 @@
   "original_max_position_embeddings": 4096,
   "pad_token_id": null,
   "quantization_config": {
-    "activation_scheme": "dynamic",
+    "activation_scheme": "static",
     "ignored_layers": [
       "lm_head"
     ],

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aca135578e521bc2946e8c934ef3f99751a216ca77196dd5616e1c7a543ba1de
-size 4824386304
+oid sha256:bc219dabe70ed5de6f9dc898d9ff87f25644bff5eb1ba1b21aed095224e59d02
+size 4824391816

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5857d650f729c5cd79206d229babab6d5f237bfbf93a6202effb7c41a6c09ce3
-size 4954824124
+oid sha256:ff3186fa48bdfbfb566504499a1d433f6b1000e205fe616800433fa88d82491b
+size 4954829984

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:461c319fa3abf285743b7585b9b2f42ac8dff66824db3db07d6052ff32b3c8f5
-size 4509822788
+oid sha256:1a291be4958ccd08c21a15535d62e0c33a13a4a9723be34cf4cd577435dc8f8e
+size 4509827824

model.safetensors.index.json

@@ -1,408 +1,568 @@
 {
   "metadata": {
-    "total_size": 14288988800
+    "total_size": 14288989440
   },
   "weight_map": {
     "lm_head.weight": "model-00003-of-00003.safetensors",
     "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
     "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.0.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_up_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.0.mlp.gate_up_proj.weight_scale": "model-00001-of-00003.safetensors",
     "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.0.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.qkv_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.0.self_attn.qkv_proj.weight_scale": "model-00001-of-00003.safetensors",
     "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.1.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_up_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.1.mlp.gate_up_proj.weight_scale": "model-00001-of-00003.safetensors",
     "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.1.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.qkv_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.1.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.1.self_attn.qkv_proj.weight_scale": "model-00001-of-00003.safetensors",
     "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.10.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.gate_up_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.10.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.10.mlp.gate_up_proj.weight_scale": "model-00001-of-00003.safetensors",
     "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.10.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.qkv_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.10.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.10.self_attn.qkv_proj.weight_scale": "model-00001-of-00003.safetensors",
     "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.11.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.gate_up_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.11.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.11.mlp.gate_up_proj.weight_scale": "model-00001-of-00003.safetensors",
     "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.11.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.qkv_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.11.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.11.self_attn.qkv_proj.weight_scale": "model-00001-of-00003.safetensors",
     "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.12.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.gate_up_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.12.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.12.mlp.gate_up_proj.weight_scale": "model-00001-of-00003.safetensors",
     "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.12.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.qkv_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.12.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.12.self_attn.qkv_proj.weight_scale": "model-00001-of-00003.safetensors",
     "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.13.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_up_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.13.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.13.mlp.gate_up_proj.weight_scale": "model-00002-of-00003.safetensors",
     "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.13.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.qkv_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.13.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.13.self_attn.qkv_proj.weight_scale": "model-00001-of-00003.safetensors",
     "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.14.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_up_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.14.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.14.mlp.gate_up_proj.weight_scale": "model-00002-of-00003.safetensors",
     "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.14.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.qkv_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.14.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.14.self_attn.qkv_proj.weight_scale": "model-00002-of-00003.safetensors",
     "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.15.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_up_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.15.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.15.mlp.gate_up_proj.weight_scale": "model-00002-of-00003.safetensors",
     "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.15.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.qkv_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.15.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.15.self_attn.qkv_proj.weight_scale": "model-00002-of-00003.safetensors",
     "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.16.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_up_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.16.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.16.mlp.gate_up_proj.weight_scale": "model-00002-of-00003.safetensors",
     "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.16.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.qkv_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.16.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.16.self_attn.qkv_proj.weight_scale": "model-00002-of-00003.safetensors",
     "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.17.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_up_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.17.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.17.mlp.gate_up_proj.weight_scale": "model-00002-of-00003.safetensors",
     "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.17.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.qkv_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.17.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.17.self_attn.qkv_proj.weight_scale": "model-00002-of-00003.safetensors",
     "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.18.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_up_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.18.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.18.mlp.gate_up_proj.weight_scale": "model-00002-of-00003.safetensors",
     "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.18.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.qkv_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.18.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.18.self_attn.qkv_proj.weight_scale": "model-00002-of-00003.safetensors",
     "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.19.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_up_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.19.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.19.mlp.gate_up_proj.weight_scale": "model-00002-of-00003.safetensors",
     "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.19.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.qkv_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.19.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.19.self_attn.qkv_proj.weight_scale": "model-00002-of-00003.safetensors",
     "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.2.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_up_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.2.mlp.gate_up_proj.weight_scale": "model-00001-of-00003.safetensors",
     "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.2.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.qkv_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.2.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.2.self_attn.qkv_proj.weight_scale": "model-00001-of-00003.safetensors",
     "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.20.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_up_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.20.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.20.mlp.gate_up_proj.weight_scale": "model-00002-of-00003.safetensors",
     "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.20.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.qkv_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.20.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.20.self_attn.qkv_proj.weight_scale": "model-00002-of-00003.safetensors",
     "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.21.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_up_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.21.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.21.mlp.gate_up_proj.weight_scale": "model-00002-of-00003.safetensors",
     "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.21.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.qkv_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.21.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.21.self_attn.qkv_proj.weight_scale": "model-00002-of-00003.safetensors",
     "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.22.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.gate_up_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.22.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.22.mlp.gate_up_proj.weight_scale": "model-00002-of-00003.safetensors",
     "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.22.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.qkv_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.22.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.22.self_attn.qkv_proj.weight_scale": "model-00002-of-00003.safetensors",
     "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.23.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.gate_up_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.23.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.23.mlp.gate_up_proj.weight_scale": "model-00002-of-00003.safetensors",
     "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.23.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.qkv_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.23.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.23.self_attn.qkv_proj.weight_scale": "model-00002-of-00003.safetensors",
     "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.24.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.gate_up_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.24.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.24.mlp.gate_up_proj.weight_scale": "model-00002-of-00003.safetensors",
     "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.24.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.qkv_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.24.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.24.self_attn.qkv_proj.weight_scale": "model-00002-of-00003.safetensors",
     "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.25.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.gate_up_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.25.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.25.mlp.gate_up_proj.weight_scale": "model-00002-of-00003.safetensors",
     "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.25.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.qkv_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.25.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.25.self_attn.qkv_proj.weight_scale": "model-00002-of-00003.safetensors",
     "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.26.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.gate_up_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.26.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.26.mlp.gate_up_proj.weight_scale": "model-00002-of-00003.safetensors",
     "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.26.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.qkv_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.26.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.26.self_attn.qkv_proj.weight_scale": "model-00002-of-00003.safetensors",
     "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.27.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_up_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.27.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.27.mlp.gate_up_proj.weight_scale": "model-00002-of-00003.safetensors",
     "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.27.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.qkv_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.27.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.27.self_attn.qkv_proj.weight_scale": "model-00002-of-00003.safetensors",
     "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.28.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_up_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.28.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.28.mlp.gate_up_proj.weight_scale": "model-00003-of-00003.safetensors",
     "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.28.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.qkv_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.28.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.28.self_attn.qkv_proj.weight_scale": "model-00003-of-00003.safetensors",
     "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.29.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_up_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.29.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.29.mlp.gate_up_proj.weight_scale": "model-00003-of-00003.safetensors",
     "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.29.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.qkv_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.29.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.29.self_attn.qkv_proj.weight_scale": "model-00003-of-00003.safetensors",
     "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.3.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_up_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.3.mlp.gate_up_proj.weight_scale": "model-00001-of-00003.safetensors",
     "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.3.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.qkv_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.3.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.3.self_attn.qkv_proj.weight_scale": "model-00001-of-00003.safetensors",
     "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.30.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_up_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.30.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.30.mlp.gate_up_proj.weight_scale": "model-00003-of-00003.safetensors",
     "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.30.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.qkv_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.30.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.30.self_attn.qkv_proj.weight_scale": "model-00003-of-00003.safetensors",
     "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.31.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_up_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.31.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.31.mlp.gate_up_proj.weight_scale": "model-00003-of-00003.safetensors",
     "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.31.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.qkv_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.31.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.31.self_attn.qkv_proj.weight_scale": "model-00003-of-00003.safetensors",
     "model.layers.32.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.mlp.down_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.32.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.32.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.32.mlp.gate_up_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.32.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.32.mlp.gate_up_proj.weight_scale": "model-00003-of-00003.safetensors",
     "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.o_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.32.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.qkv_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.32.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.32.self_attn.qkv_proj.weight_scale": "model-00003-of-00003.safetensors",
     "model.layers.33.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.mlp.down_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.33.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.33.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.33.mlp.gate_up_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.33.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.33.mlp.gate_up_proj.weight_scale": "model-00003-of-00003.safetensors",
     "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.o_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.33.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.qkv_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.33.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.33.self_attn.qkv_proj.weight_scale": "model-00003-of-00003.safetensors",
     "model.layers.34.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.mlp.down_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.34.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.34.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.34.mlp.gate_up_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.34.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.34.mlp.gate_up_proj.weight_scale": "model-00003-of-00003.safetensors",
     "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.o_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.34.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.qkv_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.34.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.34.self_attn.qkv_proj.weight_scale": "model-00003-of-00003.safetensors",
     "model.layers.35.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.mlp.down_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.35.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.35.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.35.mlp.gate_up_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.35.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.35.mlp.gate_up_proj.weight_scale": "model-00003-of-00003.safetensors",
     "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.o_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.35.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.qkv_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.35.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.35.self_attn.qkv_proj.weight_scale": "model-00003-of-00003.safetensors",
     "model.layers.36.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.36.mlp.down_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.36.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.36.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.36.mlp.gate_up_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.36.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.36.mlp.gate_up_proj.weight_scale": "model-00003-of-00003.safetensors",
     "model.layers.36.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.36.self_attn.o_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.36.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.36.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.36.self_attn.qkv_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.36.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.36.self_attn.qkv_proj.weight_scale": "model-00003-of-00003.safetensors",
     "model.layers.37.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.37.mlp.down_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.37.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.37.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.37.mlp.gate_up_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.37.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.37.mlp.gate_up_proj.weight_scale": "model-00003-of-00003.safetensors",
     "model.layers.37.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.37.self_attn.o_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.37.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.37.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.37.self_attn.qkv_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.37.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.37.self_attn.qkv_proj.weight_scale": "model-00003-of-00003.safetensors",
     "model.layers.38.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.38.mlp.down_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.38.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.38.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.38.mlp.gate_up_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.38.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.38.mlp.gate_up_proj.weight_scale": "model-00003-of-00003.safetensors",
     "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.38.self_attn.o_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.38.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.38.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.38.self_attn.qkv_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.38.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.38.self_attn.qkv_proj.weight_scale": "model-00003-of-00003.safetensors",
     "model.layers.39.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.39.mlp.down_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.39.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.39.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.39.mlp.gate_up_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.39.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.39.mlp.gate_up_proj.weight_scale": "model-00003-of-00003.safetensors",
     "model.layers.39.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.39.self_attn.o_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.39.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.39.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.39.self_attn.qkv_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.39.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.39.self_attn.qkv_proj.weight_scale": "model-00003-of-00003.safetensors",
     "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.4.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_up_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.4.mlp.gate_up_proj.weight_scale": "model-00001-of-00003.safetensors",
     "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.4.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.qkv_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.4.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.4.self_attn.qkv_proj.weight_scale": "model-00001-of-00003.safetensors",
     "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.5.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_up_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.5.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.5.mlp.gate_up_proj.weight_scale": "model-00001-of-00003.safetensors",
     "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.5.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.qkv_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.5.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.5.self_attn.qkv_proj.weight_scale": "model-00001-of-00003.safetensors",
     "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.6.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_up_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.6.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.6.mlp.gate_up_proj.weight_scale": "model-00001-of-00003.safetensors",
     "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.6.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.qkv_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.6.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.6.self_attn.qkv_proj.weight_scale": "model-00001-of-00003.safetensors",
     "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.7.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_up_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.7.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.7.mlp.gate_up_proj.weight_scale": "model-00001-of-00003.safetensors",
     "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.7.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.qkv_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.7.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.7.self_attn.qkv_proj.weight_scale": "model-00001-of-00003.safetensors",
     "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.8.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_up_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.8.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.8.mlp.gate_up_proj.weight_scale": "model-00001-of-00003.safetensors",
     "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.8.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.qkv_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.8.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.8.self_attn.qkv_proj.weight_scale": "model-00001-of-00003.safetensors",
     "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.9.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_up_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.9.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.9.mlp.gate_up_proj.weight_scale": "model-00001-of-00003.safetensors",
     "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.9.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.qkv_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.9.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.9.self_attn.qkv_proj.weight_scale": "model-00001-of-00003.safetensors",
     "model.norm.weight": "model-00003-of-00003.safetensors"