Upload folder using huggingface_hub

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/model/mistralai/Mixtral-8x7B-Instruct-v0.1",
+  "_name_or_path": "/model/mistralai/Mixtral-8x7B-Instruct-v0.1-MLCommons",
   "architectures": [
     "MixtralForCausalLM"
   ],
@@ -30,69 +30,37 @@
       "weight_merge_groups": null
     },
     "ignored_layers": [
-      "model.layers.0.self_attn.o_proj",
       "model.layers.0.block_sparse_moe.gate",
-      "model.layers.1.self_attn.o_proj",
       "model.layers.1.block_sparse_moe.gate",
-      "model.layers.2.self_attn.o_proj",
       "model.layers.2.block_sparse_moe.gate",
-      "model.layers.3.self_attn.o_proj",
       "model.layers.3.block_sparse_moe.gate",
-      "model.layers.4.self_attn.o_proj",
       "model.layers.4.block_sparse_moe.gate",
-      "model.layers.5.self_attn.o_proj",
       "model.layers.5.block_sparse_moe.gate",
-      "model.layers.6.self_attn.o_proj",
       "model.layers.6.block_sparse_moe.gate",
-      "model.layers.7.self_attn.o_proj",
       "model.layers.7.block_sparse_moe.gate",
-      "model.layers.8.self_attn.o_proj",
       "model.layers.8.block_sparse_moe.gate",
-      "model.layers.9.self_attn.o_proj",
       "model.layers.9.block_sparse_moe.gate",
-      "model.layers.10.self_attn.o_proj",
       "model.layers.10.block_sparse_moe.gate",
-      "model.layers.11.self_attn.o_proj",
       "model.layers.11.block_sparse_moe.gate",
-      "model.layers.12.self_attn.o_proj",
       "model.layers.12.block_sparse_moe.gate",
-      "model.layers.13.self_attn.o_proj",
       "model.layers.13.block_sparse_moe.gate",
-      "model.layers.14.self_attn.o_proj",
       "model.layers.14.block_sparse_moe.gate",
-      "model.layers.15.self_attn.o_proj",
       "model.layers.15.block_sparse_moe.gate",
-      "model.layers.16.self_attn.o_proj",
       "model.layers.16.block_sparse_moe.gate",
-      "model.layers.17.self_attn.o_proj",
       "model.layers.17.block_sparse_moe.gate",
-      "model.layers.18.self_attn.o_proj",
       "model.layers.18.block_sparse_moe.gate",
-      "model.layers.19.self_attn.o_proj",
       "model.layers.19.block_sparse_moe.gate",
-      "model.layers.20.self_attn.o_proj",
       "model.layers.20.block_sparse_moe.gate",
-      "model.layers.21.self_attn.o_proj",
       "model.layers.21.block_sparse_moe.gate",
-      "model.layers.22.self_attn.o_proj",
       "model.layers.22.block_sparse_moe.gate",
-      "model.layers.23.self_attn.o_proj",
       "model.layers.23.block_sparse_moe.gate",
-      "model.layers.24.self_attn.o_proj",
       "model.layers.24.block_sparse_moe.gate",
-      "model.layers.25.self_attn.o_proj",
       "model.layers.25.block_sparse_moe.gate",
-      "model.layers.26.self_attn.o_proj",
       "model.layers.26.block_sparse_moe.gate",
-      "model.layers.27.self_attn.o_proj",
       "model.layers.27.block_sparse_moe.gate",
-      "model.layers.28.self_attn.o_proj",
       "model.layers.28.block_sparse_moe.gate",
-      "model.layers.29.self_attn.o_proj",
       "model.layers.29.block_sparse_moe.gate",
-      "model.layers.30.self_attn.o_proj",
       "model.layers.30.block_sparse_moe.gate",
-      "model.layers.31.self_attn.o_proj",
       "model.layers.31.block_sparse_moe.gate",
       "lm_head"
     ],

model-00001-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcb950c9534c37a1a23de2cbc4cee35a1d8190f2e85aa2102b8e33242afef858
-size 4960111600
+oid sha256:9ecd14ec5d85f2c066dbb7f51ef8be30e0b08a203265450b45eed2a63acb1ac8
+size 4951724404

model-00002-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d681596f0d5034a261fa558709e8901cc5a5898c5aa9417a8307a47d7c0242d6
-size 4991502916
+oid sha256:3aa6b0680351be68dcee66544094e9ca1639bb00809a922e1eb278d2190b23ae
+size 4999892088

model-00003-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f00b5e2ce10654caf281d8ff1e641b53dd3cc7917bf6f4d8b578d8c6d50bc986
-size 4991519940
+oid sha256:15d66cf16d3f70e368d03a4f14adde83680aab0eb8fa77cf9855df6f7c056b72
+size 4983198624

model-00004-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2292011a9f7aae4705836f87599d765b4b34cf44330ab4ce2ee007a07683f2b9
-size 4991569892
+oid sha256:68a5200086c3543ead430588b88bd9ee6bd733204d2cdeb4a9ab33e216cb00d8
+size 4999892344

model-00005-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9056294f3a654d736cb87a7f6e96e2637d2081891855a83be34c8a69d36a9a7c
-size 4991503324
+oid sha256:b073cb23401fa7aed985e96fca66b69cc33f463d52afb9c7a4027bbd6b07ccf6
+size 4999909308

model-00006-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df81de3e2a20de00ac63c9e12707b4e2caf099a3325b582e3a350056d73ba1ae
-size 4991586796
+oid sha256:02325fcd4cbeead017c342bc0dffc84611bcc1db2d174672e4534efeea72a929
+size 4983181812

model-00007-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e325f381fc0a185a3506e34dd066bab362ecfddaa3626e80c5ec37283f8404d3
-size 4991503204
+oid sha256:2420bbfc5134419522aefe880a730c69ac82bcb7a754cfe63857347debd4f769
+size 4999892472

model-00008-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef36f466071df886a0cac5ea8f338c4699de89cd6d9ff608576bb5a5b1b5d383
-size 4991520228
+oid sha256:6d7e3cb3975f378758fb6a74c41674d694dc60ef62ed7220494b0ef04d4ffe20
+size 4983198840

model-00009-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8bf4c7d74cf9125239b7b32587e4b2fefb7a99e3bd71728cae5c4e80a551f84
-size 4991569892
+oid sha256:0d881a918e94bb35844a2373251643d2c75940078ec9bb7fc345f0361e2434c0
+size 4999892424

model-00010-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35ef3bf088cb3893f98692dbc3504ae848ba3591274d124b3314d6936b718f7c
-size 2611077968
+oid sha256:874b967850a292cc1c0acbbcce7fb48286bea2346ed46567aead9b47948e9ad9
+size 2065815212

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 47503126144
+    "total_size": 46966255232
   },
   "weight_map": {
     "lm_head.weight": "model-00010-of-00010.safetensors",
@@ -84,7 +84,9 @@
     "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
     "model.layers.0.self_attn.k_proj.weight_scale": "model-00001-of-00010.safetensors",
     "model.layers.0.self_attn.k_scale": "model-00001-of-00010.safetensors",
+    "model.layers.0.self_attn.o_proj.input_scale": "model-00001-of-00010.safetensors",
     "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.self_attn.o_proj.weight_scale": "model-00001-of-00010.safetensors",
     "model.layers.0.self_attn.q_proj.input_scale": "model-00001-of-00010.safetensors",
     "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
     "model.layers.0.self_attn.q_proj.weight_scale": "model-00001-of-00010.safetensors",
@@ -171,7 +173,9 @@
     "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
     "model.layers.1.self_attn.k_proj.weight_scale": "model-00001-of-00010.safetensors",
     "model.layers.1.self_attn.k_scale": "model-00001-of-00010.safetensors",
+    "model.layers.1.self_attn.o_proj.input_scale": "model-00001-of-00010.safetensors",
     "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.self_attn.o_proj.weight_scale": "model-00001-of-00010.safetensors",
     "model.layers.1.self_attn.q_proj.input_scale": "model-00001-of-00010.safetensors",
     "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
     "model.layers.1.self_attn.q_proj.weight_scale": "model-00001-of-00010.safetensors",
@@ -179,12 +183,12 @@
     "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
     "model.layers.1.self_attn.v_proj.weight_scale": "model-00001-of-00010.safetensors",
     "model.layers.1.self_attn.v_scale": "model-00001-of-00010.safetensors",
-    "model.layers.10.block_sparse_moe.experts.0.w1.input_scale": "model-00004-of-00010.safetensors",
-    "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00010.safetensors",
-    "model.layers.10.block_sparse_moe.experts.0.w1.weight_scale": "model-00004-of-00010.safetensors",
-    "model.layers.10.block_sparse_moe.experts.0.w2.input_scale": "model-00004-of-00010.safetensors",
-    "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors",
-    "model.layers.10.block_sparse_moe.experts.0.w2.weight_scale": "model-00004-of-00010.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w1.input_scale": "model-00003-of-00010.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w1.weight_scale": "model-00003-of-00010.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w2.input_scale": "model-00003-of-00010.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w2.weight_scale": "model-00003-of-00010.safetensors",
     "model.layers.10.block_sparse_moe.experts.0.w3.input_scale": "model-00004-of-00010.safetensors",
     "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00010.safetensors",
     "model.layers.10.block_sparse_moe.experts.0.w3.weight_scale": "model-00004-of-00010.safetensors",
@@ -251,20 +255,22 @@
     "model.layers.10.block_sparse_moe.experts.7.w3.input_scale": "model-00004-of-00010.safetensors",
     "model.layers.10.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00010.safetensors",
     "model.layers.10.block_sparse_moe.experts.7.w3.weight_scale": "model-00004-of-00010.safetensors",
-    "model.layers.10.block_sparse_moe.gate.weight": "model-00004-of-00010.safetensors",
+    "model.layers.10.block_sparse_moe.gate.weight": "model-00003-of-00010.safetensors",
     "model.layers.10.input_layernorm.weight": "model-00004-of-00010.safetensors",
     "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
-    "model.layers.10.self_attn.k_proj.input_scale": "model-00004-of-00010.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
-    "model.layers.10.self_attn.k_proj.weight_scale": "model-00004-of-00010.safetensors",
+    "model.layers.10.self_attn.k_proj.input_scale": "model-00003-of-00010.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.self_attn.k_proj.weight_scale": "model-00003-of-00010.safetensors",
     "model.layers.10.self_attn.k_scale": "model-00003-of-00010.safetensors",
-    "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
-    "model.layers.10.self_attn.q_proj.input_scale": "model-00004-of-00010.safetensors",
-    "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
-    "model.layers.10.self_attn.q_proj.weight_scale": "model-00004-of-00010.safetensors",
-    "model.layers.10.self_attn.v_proj.input_scale": "model-00004-of-00010.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
-    "model.layers.10.self_attn.v_proj.weight_scale": "model-00004-of-00010.safetensors",
+    "model.layers.10.self_attn.o_proj.input_scale": "model-00003-of-00010.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.self_attn.o_proj.weight_scale": "model-00003-of-00010.safetensors",
+    "model.layers.10.self_attn.q_proj.input_scale": "model-00003-of-00010.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.self_attn.q_proj.weight_scale": "model-00003-of-00010.safetensors",
+    "model.layers.10.self_attn.v_proj.input_scale": "model-00003-of-00010.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.self_attn.v_proj.weight_scale": "model-00003-of-00010.safetensors",
     "model.layers.10.self_attn.v_scale": "model-00003-of-00010.safetensors",
     "model.layers.11.block_sparse_moe.experts.0.w1.input_scale": "model-00004-of-00010.safetensors",
     "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00010.safetensors",
@@ -345,7 +351,9 @@
     "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
     "model.layers.11.self_attn.k_proj.weight_scale": "model-00004-of-00010.safetensors",
     "model.layers.11.self_attn.k_scale": "model-00004-of-00010.safetensors",
+    "model.layers.11.self_attn.o_proj.input_scale": "model-00004-of-00010.safetensors",
     "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.self_attn.o_proj.weight_scale": "model-00004-of-00010.safetensors",
     "model.layers.11.self_attn.q_proj.input_scale": "model-00004-of-00010.safetensors",
     "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
     "model.layers.11.self_attn.q_proj.weight_scale": "model-00004-of-00010.safetensors",
@@ -432,7 +440,9 @@
     "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
     "model.layers.12.self_attn.k_proj.weight_scale": "model-00004-of-00010.safetensors",
     "model.layers.12.self_attn.k_scale": "model-00004-of-00010.safetensors",
+    "model.layers.12.self_attn.o_proj.input_scale": "model-00004-of-00010.safetensors",
     "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.self_attn.o_proj.weight_scale": "model-00004-of-00010.safetensors",
     "model.layers.12.self_attn.q_proj.input_scale": "model-00004-of-00010.safetensors",
     "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
     "model.layers.12.self_attn.q_proj.weight_scale": "model-00004-of-00010.safetensors",
@@ -467,18 +477,18 @@
     "model.layers.13.block_sparse_moe.experts.2.w3.input_scale": "model-00004-of-00010.safetensors",
     "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00010.safetensors",
     "model.layers.13.block_sparse_moe.experts.2.w3.weight_scale": "model-00004-of-00010.safetensors",
-    "model.layers.13.block_sparse_moe.experts.3.w1.input_scale": "model-00005-of-00010.safetensors",
-    "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00010.safetensors",
-    "model.layers.13.block_sparse_moe.experts.3.w1.weight_scale": "model-00005-of-00010.safetensors",
-    "model.layers.13.block_sparse_moe.experts.3.w2.input_scale": "model-00005-of-00010.safetensors",
-    "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors",
-    "model.layers.13.block_sparse_moe.experts.3.w2.weight_scale": "model-00005-of-00010.safetensors",
-    "model.layers.13.block_sparse_moe.experts.3.w3.input_scale": "model-00005-of-00010.safetensors",
-    "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00010.safetensors",
-    "model.layers.13.block_sparse_moe.experts.3.w3.weight_scale": "model-00005-of-00010.safetensors",
-    "model.layers.13.block_sparse_moe.experts.4.w1.input_scale": "model-00005-of-00010.safetensors",
-    "model.layers.13.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00010.safetensors",
-    "model.layers.13.block_sparse_moe.experts.4.w1.weight_scale": "model-00005-of-00010.safetensors",
+    "model.layers.13.block_sparse_moe.experts.3.w1.input_scale": "model-00004-of-00010.safetensors",
+    "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.block_sparse_moe.experts.3.w1.weight_scale": "model-00004-of-00010.safetensors",
+    "model.layers.13.block_sparse_moe.experts.3.w2.input_scale": "model-00004-of-00010.safetensors",
+    "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.block_sparse_moe.experts.3.w2.weight_scale": "model-00004-of-00010.safetensors",
+    "model.layers.13.block_sparse_moe.experts.3.w3.input_scale": "model-00004-of-00010.safetensors",
+    "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.block_sparse_moe.experts.3.w3.weight_scale": "model-00004-of-00010.safetensors",
+    "model.layers.13.block_sparse_moe.experts.4.w1.input_scale": "model-00004-of-00010.safetensors",
+    "model.layers.13.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.block_sparse_moe.experts.4.w1.weight_scale": "model-00004-of-00010.safetensors",
     "model.layers.13.block_sparse_moe.experts.4.w2.input_scale": "model-00005-of-00010.safetensors",
     "model.layers.13.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00010.safetensors",
     "model.layers.13.block_sparse_moe.experts.4.w2.weight_scale": "model-00005-of-00010.safetensors",
@@ -519,7 +529,9 @@
     "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
     "model.layers.13.self_attn.k_proj.weight_scale": "model-00004-of-00010.safetensors",
     "model.layers.13.self_attn.k_scale": "model-00004-of-00010.safetensors",
+    "model.layers.13.self_attn.o_proj.input_scale": "model-00004-of-00010.safetensors",
     "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.self_attn.o_proj.weight_scale": "model-00004-of-00010.safetensors",
     "model.layers.13.self_attn.q_proj.input_scale": "model-00004-of-00010.safetensors",
     "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
     "model.layers.13.self_attn.q_proj.weight_scale": "model-00004-of-00010.safetensors",
@@ -606,7 +618,9 @@
     "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
     "model.layers.14.self_attn.k_proj.weight_scale": "model-00005-of-00010.safetensors",
     "model.layers.14.self_attn.k_scale": "model-00005-of-00010.safetensors",
+    "model.layers.14.self_attn.o_proj.input_scale": "model-00005-of-00010.safetensors",
     "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.14.self_attn.o_proj.weight_scale": "model-00005-of-00010.safetensors",
     "model.layers.14.self_attn.q_proj.input_scale": "model-00005-of-00010.safetensors",
     "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
     "model.layers.14.self_attn.q_proj.weight_scale": "model-00005-of-00010.safetensors",
@@ -693,7 +707,9 @@
     "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
     "model.layers.15.self_attn.k_proj.weight_scale": "model-00005-of-00010.safetensors",
     "model.layers.15.self_attn.k_scale": "model-00005-of-00010.safetensors",
+    "model.layers.15.self_attn.o_proj.input_scale": "model-00005-of-00010.safetensors",
     "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.15.self_attn.o_proj.weight_scale": "model-00005-of-00010.safetensors",
     "model.layers.15.self_attn.q_proj.input_scale": "model-00005-of-00010.safetensors",
     "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
     "model.layers.15.self_attn.q_proj.weight_scale": "model-00005-of-00010.safetensors",
@@ -758,29 +774,31 @@
     "model.layers.16.block_sparse_moe.experts.6.w1.input_scale": "model-00005-of-00010.safetensors",
     "model.layers.16.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00010.safetensors",
     "model.layers.16.block_sparse_moe.experts.6.w1.weight_scale": "model-00005-of-00010.safetensors",
-    "model.layers.16.block_sparse_moe.experts.6.w2.input_scale": "model-00006-of-00010.safetensors",
-    "model.layers.16.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00010.safetensors",
-    "model.layers.16.block_sparse_moe.experts.6.w2.weight_scale": "model-00006-of-00010.safetensors",
-    "model.layers.16.block_sparse_moe.experts.6.w3.input_scale": "model-00006-of-00010.safetensors",
-    "model.layers.16.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00010.safetensors",
-    "model.layers.16.block_sparse_moe.experts.6.w3.weight_scale": "model-00006-of-00010.safetensors",
-    "model.layers.16.block_sparse_moe.experts.7.w1.input_scale": "model-00006-of-00010.safetensors",
-    "model.layers.16.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00010.safetensors",
-    "model.layers.16.block_sparse_moe.experts.7.w1.weight_scale": "model-00006-of-00010.safetensors",
-    "model.layers.16.block_sparse_moe.experts.7.w2.input_scale": "model-00006-of-00010.safetensors",
-    "model.layers.16.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00010.safetensors",
-    "model.layers.16.block_sparse_moe.experts.7.w2.weight_scale": "model-00006-of-00010.safetensors",
-    "model.layers.16.block_sparse_moe.experts.7.w3.input_scale": "model-00006-of-00010.safetensors",
-    "model.layers.16.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00010.safetensors",
-    "model.layers.16.block_sparse_moe.experts.7.w3.weight_scale": "model-00006-of-00010.safetensors",
+    "model.layers.16.block_sparse_moe.experts.6.w2.input_scale": "model-00005-of-00010.safetensors",
+    "model.layers.16.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.block_sparse_moe.experts.6.w2.weight_scale": "model-00005-of-00010.safetensors",
+    "model.layers.16.block_sparse_moe.experts.6.w3.input_scale": "model-00005-of-00010.safetensors",
+    "model.layers.16.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.block_sparse_moe.experts.6.w3.weight_scale": "model-00005-of-00010.safetensors",
+    "model.layers.16.block_sparse_moe.experts.7.w1.input_scale": "model-00005-of-00010.safetensors",
+    "model.layers.16.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.block_sparse_moe.experts.7.w1.weight_scale": "model-00005-of-00010.safetensors",
+    "model.layers.16.block_sparse_moe.experts.7.w2.input_scale": "model-00005-of-00010.safetensors",
+    "model.layers.16.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.block_sparse_moe.experts.7.w2.weight_scale": "model-00005-of-00010.safetensors",
+    "model.layers.16.block_sparse_moe.experts.7.w3.input_scale": "model-00005-of-00010.safetensors",
+    "model.layers.16.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.block_sparse_moe.experts.7.w3.weight_scale": "model-00005-of-00010.safetensors",
     "model.layers.16.block_sparse_moe.gate.weight": "model-00005-of-00010.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00006-of-00010.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
     "model.layers.16.self_attn.k_proj.input_scale": "model-00005-of-00010.safetensors",
     "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
     "model.layers.16.self_attn.k_proj.weight_scale": "model-00005-of-00010.safetensors",
     "model.layers.16.self_attn.k_scale": "model-00005-of-00010.safetensors",
+    "model.layers.16.self_attn.o_proj.input_scale": "model-00005-of-00010.safetensors",
     "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.self_attn.o_proj.weight_scale": "model-00005-of-00010.safetensors",
     "model.layers.16.self_attn.q_proj.input_scale": "model-00005-of-00010.safetensors",
     "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
     "model.layers.16.self_attn.q_proj.weight_scale": "model-00005-of-00010.safetensors",
@@ -866,15 +884,17 @@
     "model.layers.17.self_attn.k_proj.input_scale": "model-00006-of-00010.safetensors",
     "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
     "model.layers.17.self_attn.k_proj.weight_scale": "model-00006-of-00010.safetensors",
-    "model.layers.17.self_attn.k_scale": "model-00006-of-00010.safetensors",
+    "model.layers.17.self_attn.k_scale": "model-00005-of-00010.safetensors",
+    "model.layers.17.self_attn.o_proj.input_scale": "model-00006-of-00010.safetensors",
     "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.17.self_attn.o_proj.weight_scale": "model-00006-of-00010.safetensors",
     "model.layers.17.self_attn.q_proj.input_scale": "model-00006-of-00010.safetensors",
     "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
     "model.layers.17.self_attn.q_proj.weight_scale": "model-00006-of-00010.safetensors",
     "model.layers.17.self_attn.v_proj.input_scale": "model-00006-of-00010.safetensors",
     "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
     "model.layers.17.self_attn.v_proj.weight_scale": "model-00006-of-00010.safetensors",
-    "model.layers.17.self_attn.v_scale": "model-00006-of-00010.safetensors",
+    "model.layers.17.self_attn.v_scale": "model-00005-of-00010.safetensors",
     "model.layers.18.block_sparse_moe.experts.0.w1.input_scale": "model-00006-of-00010.safetensors",
     "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00010.safetensors",
     "model.layers.18.block_sparse_moe.experts.0.w1.weight_scale": "model-00006-of-00010.safetensors",
@@ -954,7 +974,9 @@
     "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
     "model.layers.18.self_attn.k_proj.weight_scale": "model-00006-of-00010.safetensors",
     "model.layers.18.self_attn.k_scale": "model-00006-of-00010.safetensors",
+    "model.layers.18.self_attn.o_proj.input_scale": "model-00006-of-00010.safetensors",
     "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.18.self_attn.o_proj.weight_scale": "model-00006-of-00010.safetensors",
     "model.layers.18.self_attn.q_proj.input_scale": "model-00006-of-00010.safetensors",
     "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
     "model.layers.18.self_attn.q_proj.weight_scale": "model-00006-of-00010.safetensors",
@@ -1041,7 +1063,9 @@
     "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
     "model.layers.19.self_attn.k_proj.weight_scale": "model-00006-of-00010.safetensors",
     "model.layers.19.self_attn.k_scale": "model-00006-of-00010.safetensors",
+    "model.layers.19.self_attn.o_proj.input_scale": "model-00006-of-00010.safetensors",
     "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.19.self_attn.o_proj.weight_scale": "model-00006-of-00010.safetensors",
     "model.layers.19.self_attn.q_proj.input_scale": "model-00006-of-00010.safetensors",
     "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
     "model.layers.19.self_attn.q_proj.weight_scale": "model-00006-of-00010.safetensors",
@@ -1128,7 +1152,9 @@
     "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
     "model.layers.2.self_attn.k_proj.weight_scale": "model-00001-of-00010.safetensors",
     "model.layers.2.self_attn.k_scale": "model-00001-of-00010.safetensors",
+    "model.layers.2.self_attn.o_proj.input_scale": "model-00001-of-00010.safetensors",
     "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.self_attn.o_proj.weight_scale": "model-00001-of-00010.safetensors",
     "model.layers.2.self_attn.q_proj.input_scale": "model-00001-of-00010.safetensors",
     "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
     "model.layers.2.self_attn.q_proj.weight_scale": "model-00001-of-00010.safetensors",
@@ -1148,24 +1174,24 @@
     "model.layers.20.block_sparse_moe.experts.1.w1.input_scale": "model-00006-of-00010.safetensors",
     "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00010.safetensors",
     "model.layers.20.block_sparse_moe.experts.1.w1.weight_scale": "model-00006-of-00010.safetensors",
-    "model.layers.20.block_sparse_moe.experts.1.w2.input_scale": "model-00007-of-00010.safetensors",
-    "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00010.safetensors",
-    "model.layers.20.block_sparse_moe.experts.1.w2.weight_scale": "model-00007-of-00010.safetensors",
-    "model.layers.20.block_sparse_moe.experts.1.w3.input_scale": "model-00007-of-00010.safetensors",
-    "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00010.safetensors",
-    "model.layers.20.block_sparse_moe.experts.1.w3.weight_scale": "model-00007-of-00010.safetensors",
-    "model.layers.20.block_sparse_moe.experts.2.w1.input_scale": "model-00007-of-00010.safetensors",
-    "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors",
-    "model.layers.20.block_sparse_moe.experts.2.w1.weight_scale": "model-00007-of-00010.safetensors",
-    "model.layers.20.block_sparse_moe.experts.2.w2.input_scale": "model-00007-of-00010.safetensors",
-    "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00010.safetensors",
-    "model.layers.20.block_sparse_moe.experts.2.w2.weight_scale": "model-00007-of-00010.safetensors",
-    "model.layers.20.block_sparse_moe.experts.2.w3.input_scale": "model-00007-of-00010.safetensors",
-    "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00010.safetensors",
-    "model.layers.20.block_sparse_moe.experts.2.w3.weight_scale": "model-00007-of-00010.safetensors",
-    "model.layers.20.block_sparse_moe.experts.3.w1.input_scale": "model-00007-of-00010.safetensors",
-    "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors",
-    "model.layers.20.block_sparse_moe.experts.3.w1.weight_scale": "model-00007-of-00010.safetensors",
+    "model.layers.20.block_sparse_moe.experts.1.w2.input_scale": "model-00006-of-00010.safetensors",
+    "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors",
+    "model.layers.20.block_sparse_moe.experts.1.w2.weight_scale": "model-00006-of-00010.safetensors",
+    "model.layers.20.block_sparse_moe.experts.1.w3.input_scale": "model-00006-of-00010.safetensors",
+    "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00010.safetensors",
+    "model.layers.20.block_sparse_moe.experts.1.w3.weight_scale": "model-00006-of-00010.safetensors",
+    "model.layers.20.block_sparse_moe.experts.2.w1.input_scale": "model-00006-of-00010.safetensors",
+    "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00010.safetensors",
+    "model.layers.20.block_sparse_moe.experts.2.w1.weight_scale": "model-00006-of-00010.safetensors",
+    "model.layers.20.block_sparse_moe.experts.2.w2.input_scale": "model-00006-of-00010.safetensors",
+    "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors",
+    "model.layers.20.block_sparse_moe.experts.2.w2.weight_scale": "model-00006-of-00010.safetensors",
+    "model.layers.20.block_sparse_moe.experts.2.w3.input_scale": "model-00006-of-00010.safetensors",
+    "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00010.safetensors",
+    "model.layers.20.block_sparse_moe.experts.2.w3.weight_scale": "model-00006-of-00010.safetensors",
+    "model.layers.20.block_sparse_moe.experts.3.w1.input_scale": "model-00006-of-00010.safetensors",
+    "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00010.safetensors",
+    "model.layers.20.block_sparse_moe.experts.3.w1.weight_scale": "model-00006-of-00010.safetensors",
     "model.layers.20.block_sparse_moe.experts.3.w2.input_scale": "model-00007-of-00010.safetensors",
     "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00010.safetensors",
     "model.layers.20.block_sparse_moe.experts.3.w2.weight_scale": "model-00007-of-00010.safetensors",
@@ -1215,7 +1241,9 @@
     "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
     "model.layers.20.self_attn.k_proj.weight_scale": "model-00006-of-00010.safetensors",
     "model.layers.20.self_attn.k_scale": "model-00006-of-00010.safetensors",
+    "model.layers.20.self_attn.o_proj.input_scale": "model-00006-of-00010.safetensors",
     "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.20.self_attn.o_proj.weight_scale": "model-00006-of-00010.safetensors",
     "model.layers.20.self_attn.q_proj.input_scale": "model-00006-of-00010.safetensors",
     "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
     "model.layers.20.self_attn.q_proj.weight_scale": "model-00006-of-00010.safetensors",
@@ -1302,7 +1330,9 @@
     "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
     "model.layers.21.self_attn.k_proj.weight_scale": "model-00007-of-00010.safetensors",
     "model.layers.21.self_attn.k_scale": "model-00007-of-00010.safetensors",
+    "model.layers.21.self_attn.o_proj.input_scale": "model-00007-of-00010.safetensors",
     "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.21.self_attn.o_proj.weight_scale": "model-00007-of-00010.safetensors",
     "model.layers.21.self_attn.q_proj.input_scale": "model-00007-of-00010.safetensors",
     "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
     "model.layers.21.self_attn.q_proj.weight_scale": "model-00007-of-00010.safetensors",
@@ -1389,7 +1419,9 @@
     "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
     "model.layers.22.self_attn.k_proj.weight_scale": "model-00007-of-00010.safetensors",
     "model.layers.22.self_attn.k_scale": "model-00007-of-00010.safetensors",
+    "model.layers.22.self_attn.o_proj.input_scale": "model-00007-of-00010.safetensors",
     "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.22.self_attn.o_proj.weight_scale": "model-00007-of-00010.safetensors",
     "model.layers.22.self_attn.q_proj.input_scale": "model-00007-of-00010.safetensors",
     "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
     "model.layers.22.self_attn.q_proj.weight_scale": "model-00007-of-00010.safetensors",
@@ -1439,27 +1471,27 @@
     "model.layers.23.block_sparse_moe.experts.4.w2.input_scale": "model-00007-of-00010.safetensors",
     "model.layers.23.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00010.safetensors",
     "model.layers.23.block_sparse_moe.experts.4.w2.weight_scale": "model-00007-of-00010.safetensors",
-    "model.layers.23.block_sparse_moe.experts.4.w3.input_scale": "model-00008-of-00010.safetensors",
-    "model.layers.23.block_sparse_moe.experts.4.w3.weight": "model-00008-of-00010.safetensors",
-    "model.layers.23.block_sparse_moe.experts.4.w3.weight_scale": "model-00008-of-00010.safetensors",
-    "model.layers.23.block_sparse_moe.experts.5.w1.input_scale": "model-00008-of-00010.safetensors",
-    "model.layers.23.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00010.safetensors",
-    "model.layers.23.block_sparse_moe.experts.5.w1.weight_scale": "model-00008-of-00010.safetensors",
-    "model.layers.23.block_sparse_moe.experts.5.w2.input_scale": "model-00008-of-00010.safetensors",
-    "model.layers.23.block_sparse_moe.experts.5.w2.weight": "model-00008-of-00010.safetensors",
-    "model.layers.23.block_sparse_moe.experts.5.w2.weight_scale": "model-00008-of-00010.safetensors",
-    "model.layers.23.block_sparse_moe.experts.5.w3.input_scale": "model-00008-of-00010.safetensors",
-    "model.layers.23.block_sparse_moe.experts.5.w3.weight": "model-00008-of-00010.safetensors",
-    "model.layers.23.block_sparse_moe.experts.5.w3.weight_scale": "model-00008-of-00010.safetensors",
-    "model.layers.23.block_sparse_moe.experts.6.w1.input_scale": "model-00008-of-00010.safetensors",
-    "model.layers.23.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00010.safetensors",
-    "model.layers.23.block_sparse_moe.experts.6.w1.weight_scale": "model-00008-of-00010.safetensors",
-    "model.layers.23.block_sparse_moe.experts.6.w2.input_scale": "model-00008-of-00010.safetensors",
-    "model.layers.23.block_sparse_moe.experts.6.w2.weight": "model-00008-of-00010.safetensors",
-    "model.layers.23.block_sparse_moe.experts.6.w2.weight_scale": "model-00008-of-00010.safetensors",
-    "model.layers.23.block_sparse_moe.experts.6.w3.input_scale": "model-00008-of-00010.safetensors",
-    "model.layers.23.block_sparse_moe.experts.6.w3.weight": "model-00008-of-00010.safetensors",
-    "model.layers.23.block_sparse_moe.experts.6.w3.weight_scale": "model-00008-of-00010.safetensors",
+    "model.layers.23.block_sparse_moe.experts.4.w3.input_scale": "model-00007-of-00010.safetensors",
+    "model.layers.23.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00010.safetensors",
+    "model.layers.23.block_sparse_moe.experts.4.w3.weight_scale": "model-00007-of-00010.safetensors",
+    "model.layers.23.block_sparse_moe.experts.5.w1.input_scale": "model-00007-of-00010.safetensors",
+    "model.layers.23.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00010.safetensors",
+    "model.layers.23.block_sparse_moe.experts.5.w1.weight_scale": "model-00007-of-00010.safetensors",
+    "model.layers.23.block_sparse_moe.experts.5.w2.input_scale": "model-00007-of-00010.safetensors",
+    "model.layers.23.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00010.safetensors",
+    "model.layers.23.block_sparse_moe.experts.5.w2.weight_scale": "model-00007-of-00010.safetensors",
+    "model.layers.23.block_sparse_moe.experts.5.w3.input_scale": "model-00007-of-00010.safetensors",
+    "model.layers.23.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00010.safetensors",
+    "model.layers.23.block_sparse_moe.experts.5.w3.weight_scale": "model-00007-of-00010.safetensors",
+    "model.layers.23.block_sparse_moe.experts.6.w1.input_scale": "model-00007-of-00010.safetensors",
+    "model.layers.23.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00010.safetensors",
+    "model.layers.23.block_sparse_moe.experts.6.w1.weight_scale": "model-00007-of-00010.safetensors",
+    "model.layers.23.block_sparse_moe.experts.6.w2.input_scale": "model-00007-of-00010.safetensors",
+    "model.layers.23.block_sparse_moe.experts.6.w2.weight": "model-00007-of-00010.safetensors",
+    "model.layers.23.block_sparse_moe.experts.6.w2.weight_scale": "model-00007-of-00010.safetensors",
+    "model.layers.23.block_sparse_moe.experts.6.w3.input_scale": "model-00007-of-00010.safetensors",
+    "model.layers.23.block_sparse_moe.experts.6.w3.weight": "model-00007-of-00010.safetensors",
+    "model.layers.23.block_sparse_moe.experts.6.w3.weight_scale": "model-00007-of-00010.safetensors",
     "model.layers.23.block_sparse_moe.experts.7.w1.input_scale": "model-00008-of-00010.safetensors",
     "model.layers.23.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00010.safetensors",
     "model.layers.23.block_sparse_moe.experts.7.w1.weight_scale": "model-00008-of-00010.safetensors",
@@ -1476,7 +1508,9 @@
     "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
     "model.layers.23.self_attn.k_proj.weight_scale": "model-00007-of-00010.safetensors",
     "model.layers.23.self_attn.k_scale": "model-00007-of-00010.safetensors",
+    "model.layers.23.self_attn.o_proj.input_scale": "model-00007-of-00010.safetensors",
     "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.23.self_attn.o_proj.weight_scale": "model-00007-of-00010.safetensors",
     "model.layers.23.self_attn.q_proj.input_scale": "model-00007-of-00010.safetensors",
     "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
     "model.layers.23.self_attn.q_proj.weight_scale": "model-00007-of-00010.safetensors",
@@ -1563,7 +1597,9 @@
     "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
     "model.layers.24.self_attn.k_proj.weight_scale": "model-00008-of-00010.safetensors",
     "model.layers.24.self_attn.k_scale": "model-00008-of-00010.safetensors",
+    "model.layers.24.self_attn.o_proj.input_scale": "model-00008-of-00010.safetensors",
     "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.24.self_attn.o_proj.weight_scale": "model-00008-of-00010.safetensors",
     "model.layers.24.self_attn.q_proj.input_scale": "model-00008-of-00010.safetensors",
     "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
     "model.layers.24.self_attn.q_proj.weight_scale": "model-00008-of-00010.safetensors",
@@ -1650,7 +1686,9 @@
     "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
     "model.layers.25.self_attn.k_proj.weight_scale": "model-00008-of-00010.safetensors",
     "model.layers.25.self_attn.k_scale": "model-00008-of-00010.safetensors",
+    "model.layers.25.self_attn.o_proj.input_scale": "model-00008-of-00010.safetensors",
     "model.layers.25.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.25.self_attn.o_proj.weight_scale": "model-00008-of-00010.safetensors",
     "model.layers.25.self_attn.q_proj.input_scale": "model-00008-of-00010.safetensors",
     "model.layers.25.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
     "model.layers.25.self_attn.q_proj.weight_scale": "model-00008-of-00010.safetensors",
@@ -1737,7 +1775,9 @@
     "model.layers.26.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
     "model.layers.26.self_attn.k_proj.weight_scale": "model-00008-of-00010.safetensors",
     "model.layers.26.self_attn.k_scale": "model-00008-of-00010.safetensors",
+    "model.layers.26.self_attn.o_proj.input_scale": "model-00008-of-00010.safetensors",
     "model.layers.26.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.26.self_attn.o_proj.weight_scale": "model-00008-of-00010.safetensors",
     "model.layers.26.self_attn.q_proj.input_scale": "model-00008-of-00010.safetensors",
     "model.layers.26.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
     "model.layers.26.self_attn.q_proj.weight_scale": "model-00008-of-00010.safetensors",
@@ -1745,27 +1785,27 @@
     "model.layers.26.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
     "model.layers.26.self_attn.v_proj.weight_scale": "model-00008-of-00010.safetensors",
     "model.layers.26.self_attn.v_scale": "model-00008-of-00010.safetensors",
-    "model.layers.27.block_sparse_moe.experts.0.w1.input_scale": "model-00009-of-00010.safetensors",
-    "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors",
-    "model.layers.27.block_sparse_moe.experts.0.w1.weight_scale": "model-00009-of-00010.safetensors",
-    "model.layers.27.block_sparse_moe.experts.0.w2.input_scale": "model-00009-of-00010.safetensors",
-    "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00010.safetensors",
-    "model.layers.27.block_sparse_moe.experts.0.w2.weight_scale": "model-00009-of-00010.safetensors",
-    "model.layers.27.block_sparse_moe.experts.0.w3.input_scale": "model-00009-of-00010.safetensors",
-    "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00010.safetensors",
-    "model.layers.27.block_sparse_moe.experts.0.w3.weight_scale": "model-00009-of-00010.safetensors",
-    "model.layers.27.block_sparse_moe.experts.1.w1.input_scale": "model-00009-of-00010.safetensors",
-    "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors",
-    "model.layers.27.block_sparse_moe.experts.1.w1.weight_scale": "model-00009-of-00010.safetensors",
-    "model.layers.27.block_sparse_moe.experts.1.w2.input_scale": "model-00009-of-00010.safetensors",
-    "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00010.safetensors",
-    "model.layers.27.block_sparse_moe.experts.1.w2.weight_scale": "model-00009-of-00010.safetensors",
-    "model.layers.27.block_sparse_moe.experts.1.w3.input_scale": "model-00009-of-00010.safetensors",
-    "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00010.safetensors",
-    "model.layers.27.block_sparse_moe.experts.1.w3.weight_scale": "model-00009-of-00010.safetensors",
-    "model.layers.27.block_sparse_moe.experts.2.w1.input_scale": "model-00009-of-00010.safetensors",
-    "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors",
-    "model.layers.27.block_sparse_moe.experts.2.w1.weight_scale": "model-00009-of-00010.safetensors",
+    "model.layers.27.block_sparse_moe.experts.0.w1.input_scale": "model-00008-of-00010.safetensors",
+    "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors",
+    "model.layers.27.block_sparse_moe.experts.0.w1.weight_scale": "model-00008-of-00010.safetensors",
+    "model.layers.27.block_sparse_moe.experts.0.w2.input_scale": "model-00008-of-00010.safetensors",
+    "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00010.safetensors",
+    "model.layers.27.block_sparse_moe.experts.0.w2.weight_scale": "model-00008-of-00010.safetensors",
+    "model.layers.27.block_sparse_moe.experts.0.w3.input_scale": "model-00008-of-00010.safetensors",
+    "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00010.safetensors",
+    "model.layers.27.block_sparse_moe.experts.0.w3.weight_scale": "model-00008-of-00010.safetensors",
+    "model.layers.27.block_sparse_moe.experts.1.w1.input_scale": "model-00008-of-00010.safetensors",
+    "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors",
+    "model.layers.27.block_sparse_moe.experts.1.w1.weight_scale": "model-00008-of-00010.safetensors",
+    "model.layers.27.block_sparse_moe.experts.1.w2.input_scale": "model-00008-of-00010.safetensors",
+    "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00010.safetensors",
+    "model.layers.27.block_sparse_moe.experts.1.w2.weight_scale": "model-00008-of-00010.safetensors",
+    "model.layers.27.block_sparse_moe.experts.1.w3.input_scale": "model-00008-of-00010.safetensors",
+    "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00010.safetensors",
+    "model.layers.27.block_sparse_moe.experts.1.w3.weight_scale": "model-00008-of-00010.safetensors",
+    "model.layers.27.block_sparse_moe.experts.2.w1.input_scale": "model-00008-of-00010.safetensors",
+    "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors",
+    "model.layers.27.block_sparse_moe.experts.2.w1.weight_scale": "model-00008-of-00010.safetensors",
     "model.layers.27.block_sparse_moe.experts.2.w2.input_scale": "model-00009-of-00010.safetensors",
     "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00010.safetensors",
     "model.layers.27.block_sparse_moe.experts.2.w2.weight_scale": "model-00009-of-00010.safetensors",
@@ -1817,20 +1857,22 @@
     "model.layers.27.block_sparse_moe.experts.7.w3.input_scale": "model-00009-of-00010.safetensors",
     "model.layers.27.block_sparse_moe.experts.7.w3.weight": "model-00009-of-00010.safetensors",
     "model.layers.27.block_sparse_moe.experts.7.w3.weight_scale": "model-00009-of-00010.safetensors",
-    "model.layers.27.block_sparse_moe.gate.weight": "model-00009-of-00010.safetensors",
+    "model.layers.27.block_sparse_moe.gate.weight": "model-00008-of-00010.safetensors",
     "model.layers.27.input_layernorm.weight": "model-00009-of-00010.safetensors",
     "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
-    "model.layers.27.self_attn.k_proj.input_scale": "model-00009-of-00010.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
-    "model.layers.27.self_attn.k_proj.weight_scale": "model-00009-of-00010.safetensors",
+    "model.layers.27.self_attn.k_proj.input_scale": "model-00008-of-00010.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.27.self_attn.k_proj.weight_scale": "model-00008-of-00010.safetensors",
     "model.layers.27.self_attn.k_scale": "model-00008-of-00010.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
-    "model.layers.27.self_attn.q_proj.input_scale": "model-00009-of-00010.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
-    "model.layers.27.self_attn.q_proj.weight_scale": "model-00009-of-00010.safetensors",
-    "model.layers.27.self_attn.v_proj.input_scale": "model-00009-of-00010.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
-    "model.layers.27.self_attn.v_proj.weight_scale": "model-00009-of-00010.safetensors",
+    "model.layers.27.self_attn.o_proj.input_scale": "model-00008-of-00010.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.27.self_attn.o_proj.weight_scale": "model-00008-of-00010.safetensors",
+    "model.layers.27.self_attn.q_proj.input_scale": "model-00008-of-00010.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.27.self_attn.q_proj.weight_scale": "model-00008-of-00010.safetensors",
+    "model.layers.27.self_attn.v_proj.input_scale": "model-00008-of-00010.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.27.self_attn.v_proj.weight_scale": "model-00008-of-00010.safetensors",
     "model.layers.27.self_attn.v_scale": "model-00008-of-00010.safetensors",
     "model.layers.28.block_sparse_moe.experts.0.w1.input_scale": "model-00009-of-00010.safetensors",
     "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors",
@@ -1911,7 +1953,9 @@
     "model.layers.28.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
     "model.layers.28.self_attn.k_proj.weight_scale": "model-00009-of-00010.safetensors",
     "model.layers.28.self_attn.k_scale": "model-00009-of-00010.safetensors",
+    "model.layers.28.self_attn.o_proj.input_scale": "model-00009-of-00010.safetensors",
     "model.layers.28.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.28.self_attn.o_proj.weight_scale": "model-00009-of-00010.safetensors",
     "model.layers.28.self_attn.q_proj.input_scale": "model-00009-of-00010.safetensors",
     "model.layers.28.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
     "model.layers.28.self_attn.q_proj.weight_scale": "model-00009-of-00010.safetensors",
@@ -1998,7 +2042,9 @@
     "model.layers.29.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
     "model.layers.29.self_attn.k_proj.weight_scale": "model-00009-of-00010.safetensors",
     "model.layers.29.self_attn.k_scale": "model-00009-of-00010.safetensors",
+    "model.layers.29.self_attn.o_proj.input_scale": "model-00009-of-00010.safetensors",
     "model.layers.29.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.29.self_attn.o_proj.weight_scale": "model-00009-of-00010.safetensors",
     "model.layers.29.self_attn.q_proj.input_scale": "model-00009-of-00010.safetensors",
     "model.layers.29.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
     "model.layers.29.self_attn.q_proj.weight_scale": "model-00009-of-00010.safetensors",
@@ -2018,9 +2064,9 @@
     "model.layers.3.block_sparse_moe.experts.1.w1.input_scale": "model-00001-of-00010.safetensors",
     "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00010.safetensors",
     "model.layers.3.block_sparse_moe.experts.1.w1.weight_scale": "model-00001-of-00010.safetensors",
-    "model.layers.3.block_sparse_moe.experts.1.w2.input_scale": "model-00002-of-00010.safetensors",
-    "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00010.safetensors",
-    "model.layers.3.block_sparse_moe.experts.1.w2.weight_scale": "model-00002-of-00010.safetensors",
+    "model.layers.3.block_sparse_moe.experts.1.w2.input_scale": "model-00001-of-00010.safetensors",
+    "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00010.safetensors",
+    "model.layers.3.block_sparse_moe.experts.1.w2.weight_scale": "model-00001-of-00010.safetensors",
     "model.layers.3.block_sparse_moe.experts.1.w3.input_scale": "model-00002-of-00010.safetensors",
     "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors",
     "model.layers.3.block_sparse_moe.experts.1.w3.weight_scale": "model-00002-of-00010.safetensors",
@@ -2085,7 +2131,9 @@
     "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
     "model.layers.3.self_attn.k_proj.weight_scale": "model-00001-of-00010.safetensors",
     "model.layers.3.self_attn.k_scale": "model-00001-of-00010.safetensors",
+    "model.layers.3.self_attn.o_proj.input_scale": "model-00001-of-00010.safetensors",
     "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.3.self_attn.o_proj.weight_scale": "model-00001-of-00010.safetensors",
     "model.layers.3.self_attn.q_proj.input_scale": "model-00001-of-00010.safetensors",
     "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
     "model.layers.3.self_attn.q_proj.weight_scale": "model-00001-of-00010.safetensors",
@@ -2120,33 +2168,33 @@
     "model.layers.30.block_sparse_moe.experts.2.w3.input_scale": "model-00009-of-00010.safetensors",
     "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00010.safetensors",
     "model.layers.30.block_sparse_moe.experts.2.w3.weight_scale": "model-00009-of-00010.safetensors",
-    "model.layers.30.block_sparse_moe.experts.3.w1.input_scale": "model-00010-of-00010.safetensors",
-    "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00010.safetensors",
-    "model.layers.30.block_sparse_moe.experts.3.w1.weight_scale": "model-00010-of-00010.safetensors",
-    "model.layers.30.block_sparse_moe.experts.3.w2.input_scale": "model-00010-of-00010.safetensors",
-    "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00010.safetensors",
-    "model.layers.30.block_sparse_moe.experts.3.w2.weight_scale": "model-00010-of-00010.safetensors",
-    "model.layers.30.block_sparse_moe.experts.3.w3.input_scale": "model-00010-of-00010.safetensors",
-    "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00010.safetensors",
-    "model.layers.30.block_sparse_moe.experts.3.w3.weight_scale": "model-00010-of-00010.safetensors",
-    "model.layers.30.block_sparse_moe.experts.4.w1.input_scale": "model-00010-of-00010.safetensors",
-    "model.layers.30.block_sparse_moe.experts.4.w1.weight": "model-00010-of-00010.safetensors",
-    "model.layers.30.block_sparse_moe.experts.4.w1.weight_scale": "model-00010-of-00010.safetensors",
-    "model.layers.30.block_sparse_moe.experts.4.w2.input_scale": "model-00010-of-00010.safetensors",
-    "model.layers.30.block_sparse_moe.experts.4.w2.weight": "model-00010-of-00010.safetensors",
-    "model.layers.30.block_sparse_moe.experts.4.w2.weight_scale": "model-00010-of-00010.safetensors",
-    "model.layers.30.block_sparse_moe.experts.4.w3.input_scale": "model-00010-of-00010.safetensors",
-    "model.layers.30.block_sparse_moe.experts.4.w3.weight": "model-00010-of-00010.safetensors",
-    "model.layers.30.block_sparse_moe.experts.4.w3.weight_scale": "model-00010-of-00010.safetensors",
-    "model.layers.30.block_sparse_moe.experts.5.w1.input_scale": "model-00010-of-00010.safetensors",
-    "model.layers.30.block_sparse_moe.experts.5.w1.weight": "model-00010-of-00010.safetensors",
-    "model.layers.30.block_sparse_moe.experts.5.w1.weight_scale": "model-00010-of-00010.safetensors",
-    "model.layers.30.block_sparse_moe.experts.5.w2.input_scale": "model-00010-of-00010.safetensors",
-    "model.layers.30.block_sparse_moe.experts.5.w2.weight": "model-00010-of-00010.safetensors",
-    "model.layers.30.block_sparse_moe.experts.5.w2.weight_scale": "model-00010-of-00010.safetensors",
-    "model.layers.30.block_sparse_moe.experts.5.w3.input_scale": "model-00010-of-00010.safetensors",
-    "model.layers.30.block_sparse_moe.experts.5.w3.weight": "model-00010-of-00010.safetensors",
-    "model.layers.30.block_sparse_moe.experts.5.w3.weight_scale": "model-00010-of-00010.safetensors",
+    "model.layers.30.block_sparse_moe.experts.3.w1.input_scale": "model-00009-of-00010.safetensors",
+    "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors",
+    "model.layers.30.block_sparse_moe.experts.3.w1.weight_scale": "model-00009-of-00010.safetensors",
+    "model.layers.30.block_sparse_moe.experts.3.w2.input_scale": "model-00009-of-00010.safetensors",
+    "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00010.safetensors",
+    "model.layers.30.block_sparse_moe.experts.3.w2.weight_scale": "model-00009-of-00010.safetensors",
+    "model.layers.30.block_sparse_moe.experts.3.w3.input_scale": "model-00009-of-00010.safetensors",
+    "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00010.safetensors",
+    "model.layers.30.block_sparse_moe.experts.3.w3.weight_scale": "model-00009-of-00010.safetensors",
+    "model.layers.30.block_sparse_moe.experts.4.w1.input_scale": "model-00009-of-00010.safetensors",
+    "model.layers.30.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00010.safetensors",
+    "model.layers.30.block_sparse_moe.experts.4.w1.weight_scale": "model-00009-of-00010.safetensors",
+    "model.layers.30.block_sparse_moe.experts.4.w2.input_scale": "model-00009-of-00010.safetensors",
+    "model.layers.30.block_sparse_moe.experts.4.w2.weight": "model-00009-of-00010.safetensors",
+    "model.layers.30.block_sparse_moe.experts.4.w2.weight_scale": "model-00009-of-00010.safetensors",
+    "model.layers.30.block_sparse_moe.experts.4.w3.input_scale": "model-00009-of-00010.safetensors",
+    "model.layers.30.block_sparse_moe.experts.4.w3.weight": "model-00009-of-00010.safetensors",
+    "model.layers.30.block_sparse_moe.experts.4.w3.weight_scale": "model-00009-of-00010.safetensors",
+    "model.layers.30.block_sparse_moe.experts.5.w1.input_scale": "model-00009-of-00010.safetensors",
+    "model.layers.30.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00010.safetensors",
+    "model.layers.30.block_sparse_moe.experts.5.w1.weight_scale": "model-00009-of-00010.safetensors",
+    "model.layers.30.block_sparse_moe.experts.5.w2.input_scale": "model-00009-of-00010.safetensors",
+    "model.layers.30.block_sparse_moe.experts.5.w2.weight": "model-00009-of-00010.safetensors",
+    "model.layers.30.block_sparse_moe.experts.5.w2.weight_scale": "model-00009-of-00010.safetensors",
+    "model.layers.30.block_sparse_moe.experts.5.w3.input_scale": "model-00009-of-00010.safetensors",
+    "model.layers.30.block_sparse_moe.experts.5.w3.weight": "model-00009-of-00010.safetensors",
+    "model.layers.30.block_sparse_moe.experts.5.w3.weight_scale": "model-00009-of-00010.safetensors",
     "model.layers.30.block_sparse_moe.experts.6.w1.input_scale": "model-00010-of-00010.safetensors",
     "model.layers.30.block_sparse_moe.experts.6.w1.weight": "model-00010-of-00010.safetensors",
     "model.layers.30.block_sparse_moe.experts.6.w1.weight_scale": "model-00010-of-00010.safetensors",
@@ -2172,7 +2220,9 @@
     "model.layers.30.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
     "model.layers.30.self_attn.k_proj.weight_scale": "model-00009-of-00010.safetensors",
     "model.layers.30.self_attn.k_scale": "model-00009-of-00010.safetensors",
+    "model.layers.30.self_attn.o_proj.input_scale": "model-00009-of-00010.safetensors",
     "model.layers.30.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.30.self_attn.o_proj.weight_scale": "model-00009-of-00010.safetensors",
     "model.layers.30.self_attn.q_proj.input_scale": "model-00009-of-00010.safetensors",
     "model.layers.30.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
     "model.layers.30.self_attn.q_proj.weight_scale": "model-00009-of-00010.safetensors",
@@ -2259,7 +2309,9 @@
     "model.layers.31.self_attn.k_proj.weight": "model-00010-of-00010.safetensors",
     "model.layers.31.self_attn.k_proj.weight_scale": "model-00010-of-00010.safetensors",
     "model.layers.31.self_attn.k_scale": "model-00010-of-00010.safetensors",
+    "model.layers.31.self_attn.o_proj.input_scale": "model-00010-of-00010.safetensors",
     "model.layers.31.self_attn.o_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.31.self_attn.o_proj.weight_scale": "model-00010-of-00010.safetensors",
     "model.layers.31.self_attn.q_proj.input_scale": "model-00010-of-00010.safetensors",
     "model.layers.31.self_attn.q_proj.weight": "model-00010-of-00010.safetensors",
     "model.layers.31.self_attn.q_proj.weight_scale": "model-00010-of-00010.safetensors",
@@ -2346,7 +2398,9 @@
     "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
     "model.layers.4.self_attn.k_proj.weight_scale": "model-00002-of-00010.safetensors",
     "model.layers.4.self_attn.k_scale": "model-00002-of-00010.safetensors",
+    "model.layers.4.self_attn.o_proj.input_scale": "model-00002-of-00010.safetensors",
     "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.self_attn.o_proj.weight_scale": "model-00002-of-00010.safetensors",
     "model.layers.4.self_attn.q_proj.input_scale": "model-00002-of-00010.safetensors",
     "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
     "model.layers.4.self_attn.q_proj.weight_scale": "model-00002-of-00010.safetensors",
@@ -2433,7 +2487,9 @@
     "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
     "model.layers.5.self_attn.k_proj.weight_scale": "model-00002-of-00010.safetensors",
     "model.layers.5.self_attn.k_scale": "model-00002-of-00010.safetensors",
+    "model.layers.5.self_attn.o_proj.input_scale": "model-00002-of-00010.safetensors",
     "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.self_attn.o_proj.weight_scale": "model-00002-of-00010.safetensors",
     "model.layers.5.self_attn.q_proj.input_scale": "model-00002-of-00010.safetensors",
     "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
     "model.layers.5.self_attn.q_proj.weight_scale": "model-00002-of-00010.safetensors",
@@ -2483,12 +2539,12 @@
     "model.layers.6.block_sparse_moe.experts.4.w2.input_scale": "model-00002-of-00010.safetensors",
     "model.layers.6.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00010.safetensors",
     "model.layers.6.block_sparse_moe.experts.4.w2.weight_scale": "model-00002-of-00010.safetensors",
-    "model.layers.6.block_sparse_moe.experts.4.w3.input_scale": "model-00003-of-00010.safetensors",
-    "model.layers.6.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00010.safetensors",
-    "model.layers.6.block_sparse_moe.experts.4.w3.weight_scale": "model-00003-of-00010.safetensors",
-    "model.layers.6.block_sparse_moe.experts.5.w1.input_scale": "model-00003-of-00010.safetensors",
-    "model.layers.6.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00010.safetensors",
-    "model.layers.6.block_sparse_moe.experts.5.w1.weight_scale": "model-00003-of-00010.safetensors",
+    "model.layers.6.block_sparse_moe.experts.4.w3.input_scale": "model-00002-of-00010.safetensors",
+    "model.layers.6.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.block_sparse_moe.experts.4.w3.weight_scale": "model-00002-of-00010.safetensors",
+    "model.layers.6.block_sparse_moe.experts.5.w1.input_scale": "model-00002-of-00010.safetensors",
+    "model.layers.6.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.block_sparse_moe.experts.5.w1.weight_scale": "model-00002-of-00010.safetensors",
     "model.layers.6.block_sparse_moe.experts.5.w2.input_scale": "model-00003-of-00010.safetensors",
     "model.layers.6.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00010.safetensors",
     "model.layers.6.block_sparse_moe.experts.5.w2.weight_scale": "model-00003-of-00010.safetensors",
@@ -2520,7 +2576,9 @@
     "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
     "model.layers.6.self_attn.k_proj.weight_scale": "model-00002-of-00010.safetensors",
     "model.layers.6.self_attn.k_scale": "model-00002-of-00010.safetensors",
+    "model.layers.6.self_attn.o_proj.input_scale": "model-00002-of-00010.safetensors",
     "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.self_attn.o_proj.weight_scale": "model-00002-of-00010.safetensors",
     "model.layers.6.self_attn.q_proj.input_scale": "model-00002-of-00010.safetensors",
     "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
     "model.layers.6.self_attn.q_proj.weight_scale": "model-00002-of-00010.safetensors",
@@ -2607,7 +2665,9 @@
     "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
     "model.layers.7.self_attn.k_proj.weight_scale": "model-00003-of-00010.safetensors",
     "model.layers.7.self_attn.k_scale": "model-00003-of-00010.safetensors",
+    "model.layers.7.self_attn.o_proj.input_scale": "model-00003-of-00010.safetensors",
     "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.self_attn.o_proj.weight_scale": "model-00003-of-00010.safetensors",
     "model.layers.7.self_attn.q_proj.input_scale": "model-00003-of-00010.safetensors",
     "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
     "model.layers.7.self_attn.q_proj.weight_scale": "model-00003-of-00010.safetensors",
@@ -2694,7 +2754,9 @@
     "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
     "model.layers.8.self_attn.k_proj.weight_scale": "model-00003-of-00010.safetensors",
     "model.layers.8.self_attn.k_scale": "model-00003-of-00010.safetensors",
+    "model.layers.8.self_attn.o_proj.input_scale": "model-00003-of-00010.safetensors",
     "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.self_attn.o_proj.weight_scale": "model-00003-of-00010.safetensors",
     "model.layers.8.self_attn.q_proj.input_scale": "model-00003-of-00010.safetensors",
     "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
     "model.layers.8.self_attn.q_proj.weight_scale": "model-00003-of-00010.safetensors",
@@ -2781,7 +2843,9 @@
     "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
     "model.layers.9.self_attn.k_proj.weight_scale": "model-00003-of-00010.safetensors",
     "model.layers.9.self_attn.k_scale": "model-00003-of-00010.safetensors",
+    "model.layers.9.self_attn.o_proj.input_scale": "model-00003-of-00010.safetensors",
     "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.self_attn.o_proj.weight_scale": "model-00003-of-00010.safetensors",
     "model.layers.9.self_attn.q_proj.input_scale": "model-00003-of-00010.safetensors",
     "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
     "model.layers.9.self_attn.q_proj.weight_scale": "model-00003-of-00010.safetensors",

tokenizer_config.json

@@ -1,7 +1,7 @@
 {
   "add_bos_token": true,
   "add_eos_token": false,
-  "add_prefix_space": null,
+  "add_prefix_space": true,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -30,10 +30,10 @@
   },
   "additional_special_tokens": [],
   "bos_token": "<s>",
-  "chat_template": "{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content'] %}\n    {%- set loop_messages = messages[1:] %}\n{%- else %}\n    {%- set loop_messages = messages %}\n{%- endif %}\n\n{{- bos_token }}\n{%- for message in loop_messages %}\n    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}\n        {{- raise_exception('After the optional system message, conversation roles must alternate user/assistant/user/assistant/...') }}\n    {%- endif %}\n    {%- if message['role'] == 'user' %}\n        {%- if loop.first and system_message is defined %}\n            {{- ' [INST] ' + system_message + '\\n\\n' + message['content'] + ' [/INST]' }}\n        {%- else %}\n            {{- ' [INST] ' + message['content'] + ' [/INST]' }}\n        {%- endif %}\n    {%- elif message['role'] == 'assistant' %}\n        {{- ' ' + message['content'] + eos_token}}\n    {%- else %}\n        {{- raise_exception('Only user and assistant roles are supported, with the exception of an initial optional system message!') }}\n    {%- endif %}\n{%- endfor %}\n",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
-  "legacy": false,
+  "legacy": true,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": null,
   "sp_model_kwargs": {},