Adding `safetensors` variant of this model

model-00001-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5588eee1b63f2b868cd8b6aa220c37b207f8ad83ee61f66d178b66a90d0ea50b
+size 4892825968

model-00002-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3a24079f8cb9e2045c6ac5ccc57447bd225fecacef57d3e028fb851371cf473
+size 4983004016

model-00003-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b385867bbc3ee8e6f38fd2ef09bd878eb453e5ee116bcf8dc5079f0623143ded
+size 4983004016

model-00004-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6799943b99065adf9640f1e949e0647e7a519561deda25e7f4389ce15a316d3b
+size 4899035200

model-00005-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d03e46681f2588d2408baa520bd8c758de2617575f3cfc0f18e7e300075981b4
+size 4983004016

model-00006-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55ce2155c147deee4d3218e148b976190161f165d8761d0037068456b7e63573
+size 4983004016

model-00007-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96a430fd723c6caa43810b8266bb95999033f5e233bfd2042f3d92edb07da4cb
+size 4899035248

model-00008-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9626c049efd93476a7c9e0290f5f416b2691874ddbea119a27b3af48ff5334fc
+size 4983004072

model-00009-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b356ecf8142f66b21c88ee1c13868462c439ee72b4d06eafbcc108c5f6180ae3
+size 4983004072

model-00010-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96e8a58d9a3ba88cffbbceeaeda6c008f488dc5c1b34ad55c75253571dd5f5e3
+size 4899035248

model-00011-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fb8b0cc5812475aa56bc722d9a0c2f4d84f3ade47a7f04a75fd05ef2033e365
+size 4983004072

model-00012-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42dc1ca2682e336fb773fcdf29d5449c1819cc7bb447b5c53c3a6c5d8a942c1f
+size 4983004072

model-00013-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b2d153e1ed07a26c8d64a71e4df8343fa85946f9d54855d22cdb854fdcfee03
+size 4983004072

model-00014-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee12b9e0481d1351efdac096f022aaa47a39bf0b455a8b74c59697030e2e60ae
+size 4899035248

model-00015-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dae9d2a822fdf455c6fc8df74e9f939cd2b87f88af55051a0e370ac3057726cf
+size 4983004072

model-00016-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9f5a9725d355bb619831493300c14dc3a58b1bd5dcd4eb2407af0cdfb7849ef
+size 4983004072

model-00017-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bb5ae70bd87886a20ab4ae8e49a061f8545d8fdbdef34e84b2209ae7809cf8c
+size 4899035248

model-00018-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40d5413d05ffb71fbf4715bc74fbd8212dedeb0471ac0e4af062912cdd62c1d6
+size 4983004072

model-00019-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:957dab2185356a5794ea1ff8e1e27c9249fe2075bc8e750111c959218a82fd7c
+size 4221695472

model.safetensors.index.json

@@ -0,0 +1,1002 @@
+{
+    "metadata": {
+        "total_size": 93405618176
+    },
+    "weight_map": {
+        "lm_head.weight": "model-00019-of-00019.safetensors",
+        "model.embed_tokens.weight": "model-00001-of-00019.safetensors",
+        "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00019.safetensors",
+        "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00019.safetensors",
+        "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00019.safetensors",
+        "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00019.safetensors",
+        "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00019.safetensors",
+        "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00019.safetensors",
+        "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00019.safetensors",
+        "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00019.safetensors",
+        "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00019.safetensors",
+        "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00019.safetensors",
+        "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00019.safetensors",
+        "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00019.safetensors",
+        "model.layers.0.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00019.safetensors",
+        "model.layers.0.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00019.safetensors",
+        "model.layers.0.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00019.safetensors",
+        "model.layers.0.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00019.safetensors",
+        "model.layers.0.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00019.safetensors",
+        "model.layers.0.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00019.safetensors",
+        "model.layers.0.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00019.safetensors",
+        "model.layers.0.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00019.safetensors",
+        "model.layers.0.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00019.safetensors",
+        "model.layers.0.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00019.safetensors",
+        "model.layers.0.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00019.safetensors",
+        "model.layers.0.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00019.safetensors",
+        "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00019.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00001-of-00019.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00019.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00019.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00019.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00019.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00019.safetensors",
+        "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00019.safetensors",
+        "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00019.safetensors",
+        "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00019.safetensors",
+        "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00019.safetensors",
+        "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00019.safetensors",
+        "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00019.safetensors",
+        "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00019.safetensors",
+        "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00019.safetensors",
+        "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00019.safetensors",
+        "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00019.safetensors",
+        "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00019.safetensors",
+        "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00019.safetensors",
+        "model.layers.1.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00019.safetensors",
+        "model.layers.1.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00019.safetensors",
+        "model.layers.1.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00019.safetensors",
+        "model.layers.1.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00019.safetensors",
+        "model.layers.1.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00019.safetensors",
+        "model.layers.1.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00019.safetensors",
+        "model.layers.1.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00019.safetensors",
+        "model.layers.1.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00019.safetensors",
+        "model.layers.1.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00019.safetensors",
+        "model.layers.1.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00019.safetensors",
+        "model.layers.1.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00019.safetensors",
+        "model.layers.1.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00019.safetensors",
+        "model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00019.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00002-of-00019.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00019.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00019.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00019.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00019.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00019.safetensors",
+        "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00019.safetensors",
+        "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00019.safetensors",
+        "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00019.safetensors",
+        "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00019.safetensors",
+        "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00019.safetensors",
+        "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00019.safetensors",
+        "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00019.safetensors",
+        "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00019.safetensors",
+        "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00019.safetensors",
+        "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00019.safetensors",
+        "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00019.safetensors",
+        "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00019.safetensors",
+        "model.layers.10.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00019.safetensors",
+        "model.layers.10.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00019.safetensors",
+        "model.layers.10.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00019.safetensors",
+        "model.layers.10.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00019.safetensors",
+        "model.layers.10.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00019.safetensors",
+        "model.layers.10.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00019.safetensors",
+        "model.layers.10.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00019.safetensors",
+        "model.layers.10.block_sparse_moe.experts.6.w2.weight": "model-00007-of-00019.safetensors",
+        "model.layers.10.block_sparse_moe.experts.6.w3.weight": "model-00007-of-00019.safetensors",
+        "model.layers.10.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00019.safetensors",
+        "model.layers.10.block_sparse_moe.experts.7.w2.weight": "model-00007-of-00019.safetensors",
+        "model.layers.10.block_sparse_moe.experts.7.w3.weight": "model-00007-of-00019.safetensors",
+        "model.layers.10.block_sparse_moe.gate.weight": "model-00006-of-00019.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00007-of-00019.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model-00007-of-00019.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model-00006-of-00019.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model-00006-of-00019.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model-00006-of-00019.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model-00006-of-00019.safetensors",
+        "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00019.safetensors",
+        "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00019.safetensors",
+        "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00019.safetensors",
+        "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00019.safetensors",
+        "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00019.safetensors",
+        "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00019.safetensors",
+        "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00019.safetensors",
+        "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00019.safetensors",
+        "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00019.safetensors",
+        "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00019.safetensors",
+        "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00019.safetensors",
+        "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00019.safetensors",
+        "model.layers.11.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00019.safetensors",
+        "model.layers.11.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00019.safetensors",
+        "model.layers.11.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00019.safetensors",
+        "model.layers.11.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00019.safetensors",
+        "model.layers.11.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00019.safetensors",
+        "model.layers.11.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00019.safetensors",
+        "model.layers.11.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00019.safetensors",
+        "model.layers.11.block_sparse_moe.experts.6.w2.weight": "model-00007-of-00019.safetensors",
+        "model.layers.11.block_sparse_moe.experts.6.w3.weight": "model-00008-of-00019.safetensors",
+        "model.layers.11.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00019.safetensors",
+        "model.layers.11.block_sparse_moe.experts.7.w2.weight": "model-00008-of-00019.safetensors",
+        "model.layers.11.block_sparse_moe.experts.7.w3.weight": "model-00008-of-00019.safetensors",
+        "model.layers.11.block_sparse_moe.gate.weight": "model-00007-of-00019.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00008-of-00019.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model-00008-of-00019.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model-00007-of-00019.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model-00007-of-00019.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model-00007-of-00019.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model-00007-of-00019.safetensors",
+        "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00019.safetensors",
+        "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00019.safetensors",
+        "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00019.safetensors",
+        "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00019.safetensors",
+        "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00019.safetensors",
+        "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00019.safetensors",
+        "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00019.safetensors",
+        "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00019.safetensors",
+        "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00019.safetensors",
+        "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00019.safetensors",
+        "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00019.safetensors",
+        "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00019.safetensors",
+        "model.layers.12.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00019.safetensors",
+        "model.layers.12.block_sparse_moe.experts.4.w2.weight": "model-00008-of-00019.safetensors",
+        "model.layers.12.block_sparse_moe.experts.4.w3.weight": "model-00008-of-00019.safetensors",
+        "model.layers.12.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00019.safetensors",
+        "model.layers.12.block_sparse_moe.experts.5.w2.weight": "model-00008-of-00019.safetensors",
+        "model.layers.12.block_sparse_moe.experts.5.w3.weight": "model-00008-of-00019.safetensors",
+        "model.layers.12.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00019.safetensors",
+        "model.layers.12.block_sparse_moe.experts.6.w2.weight": "model-00008-of-00019.safetensors",
+        "model.layers.12.block_sparse_moe.experts.6.w3.weight": "model-00008-of-00019.safetensors",
+        "model.layers.12.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00019.safetensors",
+        "model.layers.12.block_sparse_moe.experts.7.w2.weight": "model-00008-of-00019.safetensors",
+        "model.layers.12.block_sparse_moe.experts.7.w3.weight": "model-00008-of-00019.safetensors",
+        "model.layers.12.block_sparse_moe.gate.weight": "model-00008-of-00019.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00008-of-00019.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model-00008-of-00019.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model-00008-of-00019.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model-00008-of-00019.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model-00008-of-00019.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model-00008-of-00019.safetensors",
+        "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00019.safetensors",
+        "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00019.safetensors",
+        "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00019.safetensors",
+        "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00019.safetensors",
+        "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00019.safetensors",
+        "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00019.safetensors",
+        "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00019.safetensors",
+        "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00019.safetensors",
+        "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00019.safetensors",
+        "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00019.safetensors",
+        "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00019.safetensors",
+        "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00019.safetensors",
+        "model.layers.13.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00019.safetensors",
+        "model.layers.13.block_sparse_moe.experts.4.w2.weight": "model-00009-of-00019.safetensors",
+        "model.layers.13.block_sparse_moe.experts.4.w3.weight": "model-00009-of-00019.safetensors",
+        "model.layers.13.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00019.safetensors",
+        "model.layers.13.block_sparse_moe.experts.5.w2.weight": "model-00009-of-00019.safetensors",
+        "model.layers.13.block_sparse_moe.experts.5.w3.weight": "model-00009-of-00019.safetensors",
+        "model.layers.13.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00019.safetensors",
+        "model.layers.13.block_sparse_moe.experts.6.w2.weight": "model-00009-of-00019.safetensors",
+        "model.layers.13.block_sparse_moe.experts.6.w3.weight": "model-00009-of-00019.safetensors",
+        "model.layers.13.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00019.safetensors",
+        "model.layers.13.block_sparse_moe.experts.7.w2.weight": "model-00009-of-00019.safetensors",
+        "model.layers.13.block_sparse_moe.experts.7.w3.weight": "model-00009-of-00019.safetensors",
+        "model.layers.13.block_sparse_moe.gate.weight": "model-00008-of-00019.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00009-of-00019.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model-00009-of-00019.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model-00008-of-00019.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model-00008-of-00019.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model-00008-of-00019.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model-00008-of-00019.safetensors",
+        "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00019.safetensors",
+        "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00019.safetensors",
+        "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00019.safetensors",
+        "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00019.safetensors",
+        "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00019.safetensors",
+        "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00019.safetensors",
+        "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00019.safetensors",
+        "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00019.safetensors",
+        "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00019.safetensors",
+        "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00019.safetensors",
+        "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00019.safetensors",
+        "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00019.safetensors",
+        "model.layers.14.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00019.safetensors",
+        "model.layers.14.block_sparse_moe.experts.4.w2.weight": "model-00009-of-00019.safetensors",
+        "model.layers.14.block_sparse_moe.experts.4.w3.weight": "model-00009-of-00019.safetensors",
+        "model.layers.14.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00019.safetensors",
+        "model.layers.14.block_sparse_moe.experts.5.w2.weight": "model-00009-of-00019.safetensors",
+        "model.layers.14.block_sparse_moe.experts.5.w3.weight": "model-00009-of-00019.safetensors",
+        "model.layers.14.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00019.safetensors",
+        "model.layers.14.block_sparse_moe.experts.6.w2.weight": "model-00009-of-00019.safetensors",
+        "model.layers.14.block_sparse_moe.experts.6.w3.weight": "model-00009-of-00019.safetensors",
+        "model.layers.14.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00019.safetensors",
+        "model.layers.14.block_sparse_moe.experts.7.w2.weight": "model-00009-of-00019.safetensors",
+        "model.layers.14.block_sparse_moe.experts.7.w3.weight": "model-00009-of-00019.safetensors",
+        "model.layers.14.block_sparse_moe.gate.weight": "model-00009-of-00019.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00009-of-00019.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00009-of-00019.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00009-of-00019.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00009-of-00019.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00009-of-00019.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00009-of-00019.safetensors",
+        "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00019.safetensors",
+        "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00019.safetensors",
+        "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00019.safetensors",
+        "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00019.safetensors",
+        "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00019.safetensors",
+        "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00019.safetensors",
+        "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00019.safetensors",
+        "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00019.safetensors",
+        "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00019.safetensors",
+        "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00019.safetensors",
+        "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00019.safetensors",
+        "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00019.safetensors",
+        "model.layers.15.block_sparse_moe.experts.4.w1.weight": "model-00010-of-00019.safetensors",
+        "model.layers.15.block_sparse_moe.experts.4.w2.weight": "model-00010-of-00019.safetensors",
+        "model.layers.15.block_sparse_moe.experts.4.w3.weight": "model-00010-of-00019.safetensors",
+        "model.layers.15.block_sparse_moe.experts.5.w1.weight": "model-00010-of-00019.safetensors",
+        "model.layers.15.block_sparse_moe.experts.5.w2.weight": "model-00010-of-00019.safetensors",
+        "model.layers.15.block_sparse_moe.experts.5.w3.weight": "model-00010-of-00019.safetensors",
+        "model.layers.15.block_sparse_moe.experts.6.w1.weight": "model-00010-of-00019.safetensors",
+        "model.layers.15.block_sparse_moe.experts.6.w2.weight": "model-00010-of-00019.safetensors",
+        "model.layers.15.block_sparse_moe.experts.6.w3.weight": "model-00010-of-00019.safetensors",
+        "model.layers.15.block_sparse_moe.experts.7.w1.weight": "model-00010-of-00019.safetensors",
+        "model.layers.15.block_sparse_moe.experts.7.w2.weight": "model-00010-of-00019.safetensors",
+        "model.layers.15.block_sparse_moe.experts.7.w3.weight": "model-00010-of-00019.safetensors",
+        "model.layers.15.block_sparse_moe.gate.weight": "model-00009-of-00019.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00010-of-00019.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model-00010-of-00019.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00009-of-00019.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00009-of-00019.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00009-of-00019.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00009-of-00019.safetensors",
+        "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00019.safetensors",
+        "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00019.safetensors",
+        "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00019.safetensors",
+        "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00019.safetensors",
+        "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00019.safetensors",
+        "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00019.safetensors",
+        "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00019.safetensors",
+        "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00019.safetensors",
+        "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00019.safetensors",
+        "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00019.safetensors",
+        "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00019.safetensors",
+        "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00019.safetensors",
+        "model.layers.16.block_sparse_moe.experts.4.w1.weight": "model-00010-of-00019.safetensors",
+        "model.layers.16.block_sparse_moe.experts.4.w2.weight": "model-00010-of-00019.safetensors",
+        "model.layers.16.block_sparse_moe.experts.4.w3.weight": "model-00010-of-00019.safetensors",
+        "model.layers.16.block_sparse_moe.experts.5.w1.weight": "model-00010-of-00019.safetensors",
+        "model.layers.16.block_sparse_moe.experts.5.w2.weight": "model-00010-of-00019.safetensors",
+        "model.layers.16.block_sparse_moe.experts.5.w3.weight": "model-00010-of-00019.safetensors",
+        "model.layers.16.block_sparse_moe.experts.6.w1.weight": "model-00010-of-00019.safetensors",
+        "model.layers.16.block_sparse_moe.experts.6.w2.weight": "model-00010-of-00019.safetensors",
+        "model.layers.16.block_sparse_moe.experts.6.w3.weight": "model-00010-of-00019.safetensors",
+        "model.layers.16.block_sparse_moe.experts.7.w1.weight": "model-00010-of-00019.safetensors",
+        "model.layers.16.block_sparse_moe.experts.7.w2.weight": "model-00010-of-00019.safetensors",
+        "model.layers.16.block_sparse_moe.experts.7.w3.weight": "model-00011-of-00019.safetensors",
+        "model.layers.16.block_sparse_moe.gate.weight": "model-00010-of-00019.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00011-of-00019.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model-00011-of-00019.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model-00010-of-00019.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model-00010-of-00019.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model-00010-of-00019.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model-00010-of-00019.safetensors",
+        "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00019.safetensors",
+        "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00019.safetensors",
+        "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00019.safetensors",
+        "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00019.safetensors",
+        "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00019.safetensors",
+        "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00019.safetensors",
+        "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00019.safetensors",
+        "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00019.safetensors",
+        "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00019.safetensors",
+        "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00019.safetensors",
+        "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00019.safetensors",
+        "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00019.safetensors",
+        "model.layers.17.block_sparse_moe.experts.4.w1.weight": "model-00011-of-00019.safetensors",
+        "model.layers.17.block_sparse_moe.experts.4.w2.weight": "model-00011-of-00019.safetensors",
+        "model.layers.17.block_sparse_moe.experts.4.w3.weight": "model-00011-of-00019.safetensors",
+        "model.layers.17.block_sparse_moe.experts.5.w1.weight": "model-00011-of-00019.safetensors",
+        "model.layers.17.block_sparse_moe.experts.5.w2.weight": "model-00011-of-00019.safetensors",
+        "model.layers.17.block_sparse_moe.experts.5.w3.weight": "model-00011-of-00019.safetensors",
+        "model.layers.17.block_sparse_moe.experts.6.w1.weight": "model-00011-of-00019.safetensors",
+        "model.layers.17.block_sparse_moe.experts.6.w2.weight": "model-00011-of-00019.safetensors",
+        "model.layers.17.block_sparse_moe.experts.6.w3.weight": "model-00011-of-00019.safetensors",
+        "model.layers.17.block_sparse_moe.experts.7.w1.weight": "model-00011-of-00019.safetensors",
+        "model.layers.17.block_sparse_moe.experts.7.w2.weight": "model-00011-of-00019.safetensors",
+        "model.layers.17.block_sparse_moe.experts.7.w3.weight": "model-00011-of-00019.safetensors",
+        "model.layers.17.block_sparse_moe.gate.weight": "model-00011-of-00019.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00011-of-00019.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model-00011-of-00019.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model-00011-of-00019.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model-00011-of-00019.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model-00011-of-00019.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model-00011-of-00019.safetensors",
+        "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00019.safetensors",
+        "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00019.safetensors",
+        "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00019.safetensors",
+        "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00019.safetensors",
+        "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00019.safetensors",
+        "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00019.safetensors",
+        "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00019.safetensors",
+        "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00019.safetensors",
+        "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00019.safetensors",
+        "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00019.safetensors",
+        "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00019.safetensors",
+        "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00019.safetensors",
+        "model.layers.18.block_sparse_moe.experts.4.w1.weight": "model-00011-of-00019.safetensors",
+        "model.layers.18.block_sparse_moe.experts.4.w2.weight": "model-00011-of-00019.safetensors",
+        "model.layers.18.block_sparse_moe.experts.4.w3.weight": "model-00011-of-00019.safetensors",
+        "model.layers.18.block_sparse_moe.experts.5.w1.weight": "model-00011-of-00019.safetensors",
+        "model.layers.18.block_sparse_moe.experts.5.w2.weight": "model-00012-of-00019.safetensors",
+        "model.layers.18.block_sparse_moe.experts.5.w3.weight": "model-00012-of-00019.safetensors",
+        "model.layers.18.block_sparse_moe.experts.6.w1.weight": "model-00012-of-00019.safetensors",
+        "model.layers.18.block_sparse_moe.experts.6.w2.weight": "model-00012-of-00019.safetensors",
+        "model.layers.18.block_sparse_moe.experts.6.w3.weight": "model-00012-of-00019.safetensors",
+        "model.layers.18.block_sparse_moe.experts.7.w1.weight": "model-00012-of-00019.safetensors",
+        "model.layers.18.block_sparse_moe.experts.7.w2.weight": "model-00012-of-00019.safetensors",
+        "model.layers.18.block_sparse_moe.experts.7.w3.weight": "model-00012-of-00019.safetensors",
+        "model.layers.18.block_sparse_moe.gate.weight": "model-00011-of-00019.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00012-of-00019.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model-00012-of-00019.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model-00011-of-00019.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model-00011-of-00019.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model-00011-of-00019.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model-00011-of-00019.safetensors",
+        "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00019.safetensors",
+        "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00019.safetensors",
+        "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00019.safetensors",
+        "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00019.safetensors",
+        "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00019.safetensors",
+        "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00019.safetensors",
+        "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00019.safetensors",
+        "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00019.safetensors",
+        "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00019.safetensors",
+        "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00019.safetensors",
+        "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00019.safetensors",
+        "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00012-of-00019.safetensors",
+        "model.layers.19.block_sparse_moe.experts.4.w1.weight": "model-00012-of-00019.safetensors",
+        "model.layers.19.block_sparse_moe.experts.4.w2.weight": "model-00012-of-00019.safetensors",
+        "model.layers.19.block_sparse_moe.experts.4.w3.weight": "model-00012-of-00019.safetensors",
+        "model.layers.19.block_sparse_moe.experts.5.w1.weight": "model-00012-of-00019.safetensors",
+        "model.layers.19.block_sparse_moe.experts.5.w2.weight": "model-00012-of-00019.safetensors",
+        "model.layers.19.block_sparse_moe.experts.5.w3.weight": "model-00012-of-00019.safetensors",
+        "model.layers.19.block_sparse_moe.experts.6.w1.weight": "model-00012-of-00019.safetensors",
+        "model.layers.19.block_sparse_moe.experts.6.w2.weight": "model-00012-of-00019.safetensors",
+        "model.layers.19.block_sparse_moe.experts.6.w3.weight": "model-00012-of-00019.safetensors",
+        "model.layers.19.block_sparse_moe.experts.7.w1.weight": "model-00012-of-00019.safetensors",
+        "model.layers.19.block_sparse_moe.experts.7.w2.weight": "model-00012-of-00019.safetensors",
+        "model.layers.19.block_sparse_moe.experts.7.w3.weight": "model-00012-of-00019.safetensors",
+        "model.layers.19.block_sparse_moe.gate.weight": "model-00012-of-00019.safetensors",
+        "model.layers.19.input_layernorm.weight": "model-00012-of-00019.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model-00012-of-00019.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model-00012-of-00019.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model-00012-of-00019.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model-00012-of-00019.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model-00012-of-00019.safetensors",
+        "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00019.safetensors",
+        "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00019.safetensors",
+        "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00019.safetensors",
+        "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00019.safetensors",
+        "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00019.safetensors",
+        "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00019.safetensors",
+        "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00019.safetensors",
+        "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00019.safetensors",
+        "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00019.safetensors",
+        "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00019.safetensors",
+        "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00019.safetensors",
+        "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00019.safetensors",
+        "model.layers.2.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00019.safetensors",
+        "model.layers.2.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00019.safetensors",
+        "model.layers.2.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00019.safetensors",
+        "model.layers.2.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00019.safetensors",
+        "model.layers.2.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00019.safetensors",
+        "model.layers.2.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00019.safetensors",
+        "model.layers.2.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00019.safetensors",
+        "model.layers.2.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00019.safetensors",
+        "model.layers.2.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00019.safetensors",
+        "model.layers.2.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00019.safetensors",
+        "model.layers.2.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00019.safetensors",
+        "model.layers.2.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00019.safetensors",
+        "model.layers.2.block_sparse_moe.gate.weight": "model-00002-of-00019.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00002-of-00019.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00019.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00019.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00019.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00019.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00019.safetensors",
+        "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00019.safetensors",
+        "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00019.safetensors",
+        "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00019.safetensors",
+        "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00019.safetensors",
+        "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00019.safetensors",
+        "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00019.safetensors",
+        "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00019.safetensors",
+        "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00019.safetensors",
+        "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00019.safetensors",
+        "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00013-of-00019.safetensors",
+        "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00019.safetensors",
+        "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00019.safetensors",
+        "model.layers.20.block_sparse_moe.experts.4.w1.weight": "model-00013-of-00019.safetensors",
+        "model.layers.20.block_sparse_moe.experts.4.w2.weight": "model-00013-of-00019.safetensors",
+        "model.layers.20.block_sparse_moe.experts.4.w3.weight": "model-00013-of-00019.safetensors",
+        "model.layers.20.block_sparse_moe.experts.5.w1.weight": "model-00013-of-00019.safetensors",
+        "model.layers.20.block_sparse_moe.experts.5.w2.weight": "model-00013-of-00019.safetensors",
+        "model.layers.20.block_sparse_moe.experts.5.w3.weight": "model-00013-of-00019.safetensors",
+        "model.layers.20.block_sparse_moe.experts.6.w1.weight": "model-00013-of-00019.safetensors",
+        "model.layers.20.block_sparse_moe.experts.6.w2.weight": "model-00013-of-00019.safetensors",
+        "model.layers.20.block_sparse_moe.experts.6.w3.weight": "model-00013-of-00019.safetensors",
+        "model.layers.20.block_sparse_moe.experts.7.w1.weight": "model-00013-of-00019.safetensors",
+        "model.layers.20.block_sparse_moe.experts.7.w2.weight": "model-00013-of-00019.safetensors",
+        "model.layers.20.block_sparse_moe.experts.7.w3.weight": "model-00013-of-00019.safetensors",
+        "model.layers.20.block_sparse_moe.gate.weight": "model-00012-of-00019.safetensors",
+        "model.layers.20.input_layernorm.weight": "model-00013-of-00019.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model-00013-of-00019.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model-00012-of-00019.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model-00012-of-00019.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model-00012-of-00019.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model-00012-of-00019.safetensors",
+        "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00019.safetensors",
+        "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00019.safetensors",
+        "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00019.safetensors",
+        "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00019.safetensors",
+        "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00019.safetensors",
+        "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00019.safetensors",
+        "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00019.safetensors",
+        "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00019.safetensors",
+        "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00013-of-00019.safetensors",
+        "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00013-of-00019.safetensors",
+        "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00019.safetensors",
+        "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00019.safetensors",
+        "model.layers.21.block_sparse_moe.experts.4.w1.weight": "model-00013-of-00019.safetensors",
+        "model.layers.21.block_sparse_moe.experts.4.w2.weight": "model-00013-of-00019.safetensors",
+        "model.layers.21.block_sparse_moe.experts.4.w3.weight": "model-00013-of-00019.safetensors",
+        "model.layers.21.block_sparse_moe.experts.5.w1.weight": "model-00013-of-00019.safetensors",
+        "model.layers.21.block_sparse_moe.experts.5.w2.weight": "model-00013-of-00019.safetensors",
+        "model.layers.21.block_sparse_moe.experts.5.w3.weight": "model-00013-of-00019.safetensors",
+        "model.layers.21.block_sparse_moe.experts.6.w1.weight": "model-00013-of-00019.safetensors",
+        "model.layers.21.block_sparse_moe.experts.6.w2.weight": "model-00013-of-00019.safetensors",
+        "model.layers.21.block_sparse_moe.experts.6.w3.weight": "model-00013-of-00019.safetensors",
+        "model.layers.21.block_sparse_moe.experts.7.w1.weight": "model-00013-of-00019.safetensors",
+        "model.layers.21.block_sparse_moe.experts.7.w2.weight": "model-00013-of-00019.safetensors",
+        "model.layers.21.block_sparse_moe.experts.7.w3.weight": "model-00013-of-00019.safetensors",
+        "model.layers.21.block_sparse_moe.gate.weight": "model-00013-of-00019.safetensors",
+        "model.layers.21.input_layernorm.weight": "model-00013-of-00019.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model-00013-of-00019.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model-00013-of-00019.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model-00013-of-00019.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model-00013-of-00019.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model-00013-of-00019.safetensors",
+        "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00019.safetensors",
+        "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00019.safetensors",
+        "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00019.safetensors",
+        "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00019.safetensors",
+        "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00019.safetensors",
+        "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00019.safetensors",
+        "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00019.safetensors",
+        "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00019.safetensors",
+        "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00014-of-00019.safetensors",
+        "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00019.safetensors",
+        "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00019.safetensors",
+        "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00014-of-00019.safetensors",
+        "model.layers.22.block_sparse_moe.experts.4.w1.weight": "model-00014-of-00019.safetensors",
+        "model.layers.22.block_sparse_moe.experts.4.w2.weight": "model-00014-of-00019.safetensors",
+        "model.layers.22.block_sparse_moe.experts.4.w3.weight": "model-00014-of-00019.safetensors",
+        "model.layers.22.block_sparse_moe.experts.5.w1.weight": "model-00014-of-00019.safetensors",
+        "model.layers.22.block_sparse_moe.experts.5.w2.weight": "model-00014-of-00019.safetensors",
+        "model.layers.22.block_sparse_moe.experts.5.w3.weight": "model-00014-of-00019.safetensors",
+        "model.layers.22.block_sparse_moe.experts.6.w1.weight": "model-00014-of-00019.safetensors",
+        "model.layers.22.block_sparse_moe.experts.6.w2.weight": "model-00014-of-00019.safetensors",
+        "model.layers.22.block_sparse_moe.experts.6.w3.weight": "model-00014-of-00019.safetensors",
+        "model.layers.22.block_sparse_moe.experts.7.w1.weight": "model-00014-of-00019.safetensors",
+        "model.layers.22.block_sparse_moe.experts.7.w2.weight": "model-00014-of-00019.safetensors",
+        "model.layers.22.block_sparse_moe.experts.7.w3.weight": "model-00014-of-00019.safetensors",
+        "model.layers.22.block_sparse_moe.gate.weight": "model-00013-of-00019.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00014-of-00019.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model-00014-of-00019.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model-00013-of-00019.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model-00013-of-00019.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model-00013-of-00019.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model-00013-of-00019.safetensors",
+        "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00019.safetensors",
+        "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00019.safetensors",
+        "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00019.safetensors",
+        "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00019.safetensors",
+        "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00019.safetensors",
+        "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00019.safetensors",
+        "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00019.safetensors",
+        "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00019.safetensors",
+        "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00014-of-00019.safetensors",
+        "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00019.safetensors",
+        "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00019.safetensors",
+        "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00014-of-00019.safetensors",
+        "model.layers.23.block_sparse_moe.experts.4.w1.weight": "model-00014-of-00019.safetensors",
+        "model.layers.23.block_sparse_moe.experts.4.w2.weight": "model-00014-of-00019.safetensors",
+        "model.layers.23.block_sparse_moe.experts.4.w3.weight": "model-00014-of-00019.safetensors",
+        "model.layers.23.block_sparse_moe.experts.5.w1.weight": "model-00014-of-00019.safetensors",
+        "model.layers.23.block_sparse_moe.experts.5.w2.weight": "model-00014-of-00019.safetensors",
+        "model.layers.23.block_sparse_moe.experts.5.w3.weight": "model-00014-of-00019.safetensors",
+        "model.layers.23.block_sparse_moe.experts.6.w1.weight": "model-00014-of-00019.safetensors",
+        "model.layers.23.block_sparse_moe.experts.6.w2.weight": "model-00015-of-00019.safetensors",
+        "model.layers.23.block_sparse_moe.experts.6.w3.weight": "model-00015-of-00019.safetensors",
+        "model.layers.23.block_sparse_moe.experts.7.w1.weight": "model-00015-of-00019.safetensors",
+        "model.layers.23.block_sparse_moe.experts.7.w2.weight": "model-00015-of-00019.safetensors",
+        "model.layers.23.block_sparse_moe.experts.7.w3.weight": "model-00015-of-00019.safetensors",
+        "model.layers.23.block_sparse_moe.gate.weight": "model-00014-of-00019.safetensors",
+        "model.layers.23.input_layernorm.weight": "model-00015-of-00019.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model-00015-of-00019.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model-00014-of-00019.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model-00014-of-00019.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model-00014-of-00019.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model-00014-of-00019.safetensors",
+        "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00019.safetensors",
+        "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00019.safetensors",
+        "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00019.safetensors",
+        "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00019.safetensors",
+        "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00019.safetensors",
+        "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00019.safetensors",
+        "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00019.safetensors",
+        "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00019.safetensors",
+        "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00019.safetensors",
+        "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00015-of-00019.safetensors",
+        "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00019.safetensors",
+        "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00015-of-00019.safetensors",
+        "model.layers.24.block_sparse_moe.experts.4.w1.weight": "model-00015-of-00019.safetensors",
+        "model.layers.24.block_sparse_moe.experts.4.w2.weight": "model-00015-of-00019.safetensors",
+        "model.layers.24.block_sparse_moe.experts.4.w3.weight": "model-00015-of-00019.safetensors",
+        "model.layers.24.block_sparse_moe.experts.5.w1.weight": "model-00015-of-00019.safetensors",
+        "model.layers.24.block_sparse_moe.experts.5.w2.weight": "model-00015-of-00019.safetensors",
+        "model.layers.24.block_sparse_moe.experts.5.w3.weight": "model-00015-of-00019.safetensors",
+        "model.layers.24.block_sparse_moe.experts.6.w1.weight": "model-00015-of-00019.safetensors",
+        "model.layers.24.block_sparse_moe.experts.6.w2.weight": "model-00015-of-00019.safetensors",
+        "model.layers.24.block_sparse_moe.experts.6.w3.weight": "model-00015-of-00019.safetensors",
+        "model.layers.24.block_sparse_moe.experts.7.w1.weight": "model-00015-of-00019.safetensors",
+        "model.layers.24.block_sparse_moe.experts.7.w2.weight": "model-00015-of-00019.safetensors",
+        "model.layers.24.block_sparse_moe.experts.7.w3.weight": "model-00015-of-00019.safetensors",
+        "model.layers.24.block_sparse_moe.gate.weight": "model-00015-of-00019.safetensors",
+        "model.layers.24.input_layernorm.weight": "model-00015-of-00019.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model-00015-of-00019.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model-00015-of-00019.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model-00015-of-00019.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model-00015-of-00019.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model-00015-of-00019.safetensors",
+        "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00019.safetensors",
+        "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00019.safetensors",
+        "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00019.safetensors",
+        "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00019.safetensors",
+        "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00019.safetensors",
+        "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00019.safetensors",
+        "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00019.safetensors",
+        "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00019.safetensors",
+        "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00019.safetensors",
+        "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00015-of-00019.safetensors",
+        "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00019.safetensors",
+        "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00015-of-00019.safetensors",
+        "model.layers.25.block_sparse_moe.experts.4.w1.weight": "model-00016-of-00019.safetensors",
+        "model.layers.25.block_sparse_moe.experts.4.w2.weight": "model-00016-of-00019.safetensors",
+        "model.layers.25.block_sparse_moe.experts.4.w3.weight": "model-00016-of-00019.safetensors",
+        "model.layers.25.block_sparse_moe.experts.5.w1.weight": "model-00016-of-00019.safetensors",
+        "model.layers.25.block_sparse_moe.experts.5.w2.weight": "model-00016-of-00019.safetensors",
+        "model.layers.25.block_sparse_moe.experts.5.w3.weight": "model-00016-of-00019.safetensors",
+        "model.layers.25.block_sparse_moe.experts.6.w1.weight": "model-00016-of-00019.safetensors",
+        "model.layers.25.block_sparse_moe.experts.6.w2.weight": "model-00016-of-00019.safetensors",
+        "model.layers.25.block_sparse_moe.experts.6.w3.weight": "model-00016-of-00019.safetensors",
+        "model.layers.25.block_sparse_moe.experts.7.w1.weight": "model-00016-of-00019.safetensors",
+        "model.layers.25.block_sparse_moe.experts.7.w2.weight": "model-00016-of-00019.safetensors",
+        "model.layers.25.block_sparse_moe.experts.7.w3.weight": "model-00016-of-00019.safetensors",
+        "model.layers.25.block_sparse_moe.gate.weight": "model-00015-of-00019.safetensors",
+        "model.layers.25.input_layernorm.weight": "model-00016-of-00019.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model-00016-of-00019.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model-00015-of-00019.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model-00015-of-00019.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model-00015-of-00019.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model-00015-of-00019.safetensors",
+        "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00019.safetensors",
+        "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00019.safetensors",
+        "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00019.safetensors",
+        "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00019.safetensors",
+        "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00019.safetensors",
+        "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00019.safetensors",
+        "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00019.safetensors",
+        "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00016-of-00019.safetensors",
+        "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00016-of-00019.safetensors",
+        "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00016-of-00019.safetensors",
+        "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00016-of-00019.safetensors",
+        "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00016-of-00019.safetensors",
+        "model.layers.26.block_sparse_moe.experts.4.w1.weight": "model-00016-of-00019.safetensors",
+        "model.layers.26.block_sparse_moe.experts.4.w2.weight": "model-00016-of-00019.safetensors",
+        "model.layers.26.block_sparse_moe.experts.4.w3.weight": "model-00016-of-00019.safetensors",
+        "model.layers.26.block_sparse_moe.experts.5.w1.weight": "model-00016-of-00019.safetensors",
+        "model.layers.26.block_sparse_moe.experts.5.w2.weight": "model-00016-of-00019.safetensors",
+        "model.layers.26.block_sparse_moe.experts.5.w3.weight": "model-00016-of-00019.safetensors",
+        "model.layers.26.block_sparse_moe.experts.6.w1.weight": "model-00016-of-00019.safetensors",
+        "model.layers.26.block_sparse_moe.experts.6.w2.weight": "model-00016-of-00019.safetensors",
+        "model.layers.26.block_sparse_moe.experts.6.w3.weight": "model-00016-of-00019.safetensors",
+        "model.layers.26.block_sparse_moe.experts.7.w1.weight": "model-00016-of-00019.safetensors",
+        "model.layers.26.block_sparse_moe.experts.7.w2.weight": "model-00016-of-00019.safetensors",
+        "model.layers.26.block_sparse_moe.experts.7.w3.weight": "model-00016-of-00019.safetensors",
+        "model.layers.26.block_sparse_moe.gate.weight": "model-00016-of-00019.safetensors",
+        "model.layers.26.input_layernorm.weight": "model-00016-of-00019.safetensors",
+        "model.layers.26.post_attention_layernorm.weight": "model-00016-of-00019.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model-00016-of-00019.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model-00016-of-00019.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model-00016-of-00019.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model-00016-of-00019.safetensors",
+        "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00019.safetensors",
+        "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00019.safetensors",
+        "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00019.safetensors",
+        "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00019.safetensors",
+        "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00019.safetensors",
+        "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00019.safetensors",
+        "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00019.safetensors",
+        "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00017-of-00019.safetensors",
+        "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00017-of-00019.safetensors",
+        "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00019.safetensors",
+        "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00017-of-00019.safetensors",
+        "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00017-of-00019.safetensors",
+        "model.layers.27.block_sparse_moe.experts.4.w1.weight": "model-00017-of-00019.safetensors",
+        "model.layers.27.block_sparse_moe.experts.4.w2.weight": "model-00017-of-00019.safetensors",
+        "model.layers.27.block_sparse_moe.experts.4.w3.weight": "model-00017-of-00019.safetensors",
+        "model.layers.27.block_sparse_moe.experts.5.w1.weight": "model-00017-of-00019.safetensors",
+        "model.layers.27.block_sparse_moe.experts.5.w2.weight": "model-00017-of-00019.safetensors",
+        "model.layers.27.block_sparse_moe.experts.5.w3.weight": "model-00017-of-00019.safetensors",
+        "model.layers.27.block_sparse_moe.experts.6.w1.weight": "model-00017-of-00019.safetensors",
+        "model.layers.27.block_sparse_moe.experts.6.w2.weight": "model-00017-of-00019.safetensors",
+        "model.layers.27.block_sparse_moe.experts.6.w3.weight": "model-00017-of-00019.safetensors",
+        "model.layers.27.block_sparse_moe.experts.7.w1.weight": "model-00017-of-00019.safetensors",
+        "model.layers.27.block_sparse_moe.experts.7.w2.weight": "model-00017-of-00019.safetensors",
+        "model.layers.27.block_sparse_moe.experts.7.w3.weight": "model-00017-of-00019.safetensors",
+        "model.layers.27.block_sparse_moe.gate.weight": "model-00016-of-00019.safetensors",
+        "model.layers.27.input_layernorm.weight": "model-00017-of-00019.safetensors",
+        "model.layers.27.post_attention_layernorm.weight": "model-00017-of-00019.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model-00016-of-00019.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model-00016-of-00019.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model-00016-of-00019.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model-00016-of-00019.safetensors",
+        "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00019.safetensors",
+        "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00019.safetensors",
+        "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00019.safetensors",
+        "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00019.safetensors",
+        "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00019.safetensors",
+        "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00019.safetensors",
+        "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00019.safetensors",
+        "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00017-of-00019.safetensors",
+        "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00017-of-00019.safetensors",
+        "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00019.safetensors",
+        "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00017-of-00019.safetensors",
+        "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00017-of-00019.safetensors",
+        "model.layers.28.block_sparse_moe.experts.4.w1.weight": "model-00017-of-00019.safetensors",
+        "model.layers.28.block_sparse_moe.experts.4.w2.weight": "model-00017-of-00019.safetensors",
+        "model.layers.28.block_sparse_moe.experts.4.w3.weight": "model-00017-of-00019.safetensors",
+        "model.layers.28.block_sparse_moe.experts.5.w1.weight": "model-00017-of-00019.safetensors",
+        "model.layers.28.block_sparse_moe.experts.5.w2.weight": "model-00017-of-00019.safetensors",
+        "model.layers.28.block_sparse_moe.experts.5.w3.weight": "model-00017-of-00019.safetensors",
+        "model.layers.28.block_sparse_moe.experts.6.w1.weight": "model-00017-of-00019.safetensors",
+        "model.layers.28.block_sparse_moe.experts.6.w2.weight": "model-00017-of-00019.safetensors",
+        "model.layers.28.block_sparse_moe.experts.6.w3.weight": "model-00017-of-00019.safetensors",
+        "model.layers.28.block_sparse_moe.experts.7.w1.weight": "model-00017-of-00019.safetensors",
+        "model.layers.28.block_sparse_moe.experts.7.w2.weight": "model-00018-of-00019.safetensors",
+        "model.layers.28.block_sparse_moe.experts.7.w3.weight": "model-00018-of-00019.safetensors",
+        "model.layers.28.block_sparse_moe.gate.weight": "model-00017-of-00019.safetensors",
+        "model.layers.28.input_layernorm.weight": "model-00018-of-00019.safetensors",
+        "model.layers.28.post_attention_layernorm.weight": "model-00018-of-00019.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "model-00017-of-00019.safetensors",
+        "model.layers.28.self_attn.o_proj.weight": "model-00017-of-00019.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "model-00017-of-00019.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "model-00017-of-00019.safetensors",
+        "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00019.safetensors",
+        "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00019.safetensors",
+        "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00019.safetensors",
+        "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00019.safetensors",
+        "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00019.safetensors",
+        "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00019.safetensors",
+        "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00019.safetensors",
+        "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00018-of-00019.safetensors",
+        "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00018-of-00019.safetensors",
+        "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00019.safetensors",
+        "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00018-of-00019.safetensors",
+        "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00018-of-00019.safetensors",
+        "model.layers.29.block_sparse_moe.experts.4.w1.weight": "model-00018-of-00019.safetensors",
+        "model.layers.29.block_sparse_moe.experts.4.w2.weight": "model-00018-of-00019.safetensors",
+        "model.layers.29.block_sparse_moe.experts.4.w3.weight": "model-00018-of-00019.safetensors",
+        "model.layers.29.block_sparse_moe.experts.5.w1.weight": "model-00018-of-00019.safetensors",
+        "model.layers.29.block_sparse_moe.experts.5.w2.weight": "model-00018-of-00019.safetensors",
+        "model.layers.29.block_sparse_moe.experts.5.w3.weight": "model-00018-of-00019.safetensors",
+        "model.layers.29.block_sparse_moe.experts.6.w1.weight": "model-00018-of-00019.safetensors",
+        "model.layers.29.block_sparse_moe.experts.6.w2.weight": "model-00018-of-00019.safetensors",
+        "model.layers.29.block_sparse_moe.experts.6.w3.weight": "model-00018-of-00019.safetensors",
+        "model.layers.29.block_sparse_moe.experts.7.w1.weight": "model-00018-of-00019.safetensors",
+        "model.layers.29.block_sparse_moe.experts.7.w2.weight": "model-00018-of-00019.safetensors",
+        "model.layers.29.block_sparse_moe.experts.7.w3.weight": "model-00018-of-00019.safetensors",
+        "model.layers.29.block_sparse_moe.gate.weight": "model-00018-of-00019.safetensors",
+        "model.layers.29.input_layernorm.weight": "model-00018-of-00019.safetensors",
+        "model.layers.29.post_attention_layernorm.weight": "model-00018-of-00019.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "model-00018-of-00019.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "model-00018-of-00019.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model-00018-of-00019.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model-00018-of-00019.safetensors",
+        "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00019.safetensors",
+        "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00019.safetensors",
+        "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00019.safetensors",
+        "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00019.safetensors",
+        "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00019.safetensors",
+        "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00019.safetensors",
+        "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00019.safetensors",
+        "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00019.safetensors",
+        "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00019.safetensors",
+        "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00019.safetensors",
+        "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00019.safetensors",
+        "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00019.safetensors",
+        "model.layers.3.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00019.safetensors",
+        "model.layers.3.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00019.safetensors",
+        "model.layers.3.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00019.safetensors",
+        "model.layers.3.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00019.safetensors",
+        "model.layers.3.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00019.safetensors",
+        "model.layers.3.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00019.safetensors",
+        "model.layers.3.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00019.safetensors",
+        "model.layers.3.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00019.safetensors",
+        "model.layers.3.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00019.safetensors",
+        "model.layers.3.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00019.safetensors",
+        "model.layers.3.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00019.safetensors",
+        "model.layers.3.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00019.safetensors",
+        "model.layers.3.block_sparse_moe.gate.weight": "model-00002-of-00019.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00003-of-00019.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00019.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00019.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00019.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00019.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00019.safetensors",
+        "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00019.safetensors",
+        "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00019.safetensors",
+        "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00019.safetensors",
+        "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00019.safetensors",
+        "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00019.safetensors",
+        "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00019.safetensors",
+        "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00019.safetensors",
+        "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00018-of-00019.safetensors",
+        "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00018-of-00019.safetensors",
+        "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00019.safetensors",
+        "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00018-of-00019.safetensors",
+        "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00018-of-00019.safetensors",
+        "model.layers.30.block_sparse_moe.experts.4.w1.weight": "model-00018-of-00019.safetensors",
+        "model.layers.30.block_sparse_moe.experts.4.w2.weight": "model-00018-of-00019.safetensors",
+        "model.layers.30.block_sparse_moe.experts.4.w3.weight": "model-00018-of-00019.safetensors",
+        "model.layers.30.block_sparse_moe.experts.5.w1.weight": "model-00019-of-00019.safetensors",
+        "model.layers.30.block_sparse_moe.experts.5.w2.weight": "model-00019-of-00019.safetensors",
+        "model.layers.30.block_sparse_moe.experts.5.w3.weight": "model-00019-of-00019.safetensors",
+        "model.layers.30.block_sparse_moe.experts.6.w1.weight": "model-00019-of-00019.safetensors",
+        "model.layers.30.block_sparse_moe.experts.6.w2.weight": "model-00019-of-00019.safetensors",
+        "model.layers.30.block_sparse_moe.experts.6.w3.weight": "model-00019-of-00019.safetensors",
+        "model.layers.30.block_sparse_moe.experts.7.w1.weight": "model-00019-of-00019.safetensors",
+        "model.layers.30.block_sparse_moe.experts.7.w2.weight": "model-00019-of-00019.safetensors",
+        "model.layers.30.block_sparse_moe.experts.7.w3.weight": "model-00019-of-00019.safetensors",
+        "model.layers.30.block_sparse_moe.gate.weight": "model-00018-of-00019.safetensors",
+        "model.layers.30.input_layernorm.weight": "model-00019-of-00019.safetensors",
+        "model.layers.30.post_attention_layernorm.weight": "model-00019-of-00019.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "model-00018-of-00019.safetensors",
+        "model.layers.30.self_attn.o_proj.weight": "model-00018-of-00019.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "model-00018-of-00019.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "model-00018-of-00019.safetensors",
+        "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00019.safetensors",
+        "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00019.safetensors",
+        "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00019-of-00019.safetensors",
+        "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00019.safetensors",
+        "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00019-of-00019.safetensors",
+        "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00019.safetensors",
+        "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00019-of-00019.safetensors",
+        "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00019-of-00019.safetensors",
+        "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00019-of-00019.safetensors",
+        "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00019-of-00019.safetensors",
+        "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00019-of-00019.safetensors",
+        "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00019-of-00019.safetensors",
+        "model.layers.31.block_sparse_moe.experts.4.w1.weight": "model-00019-of-00019.safetensors",
+        "model.layers.31.block_sparse_moe.experts.4.w2.weight": "model-00019-of-00019.safetensors",
+        "model.layers.31.block_sparse_moe.experts.4.w3.weight": "model-00019-of-00019.safetensors",
+        "model.layers.31.block_sparse_moe.experts.5.w1.weight": "model-00019-of-00019.safetensors",
+        "model.layers.31.block_sparse_moe.experts.5.w2.weight": "model-00019-of-00019.safetensors",
+        "model.layers.31.block_sparse_moe.experts.5.w3.weight": "model-00019-of-00019.safetensors",
+        "model.layers.31.block_sparse_moe.experts.6.w1.weight": "model-00019-of-00019.safetensors",
+        "model.layers.31.block_sparse_moe.experts.6.w2.weight": "model-00019-of-00019.safetensors",
+        "model.layers.31.block_sparse_moe.experts.6.w3.weight": "model-00019-of-00019.safetensors",
+        "model.layers.31.block_sparse_moe.experts.7.w1.weight": "model-00019-of-00019.safetensors",
+        "model.layers.31.block_sparse_moe.experts.7.w2.weight": "model-00019-of-00019.safetensors",
+        "model.layers.31.block_sparse_moe.experts.7.w3.weight": "model-00019-of-00019.safetensors",
+        "model.layers.31.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors",
+        "model.layers.31.input_layernorm.weight": "model-00019-of-00019.safetensors",
+        "model.layers.31.post_attention_layernorm.weight": "model-00019-of-00019.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "model-00019-of-00019.safetensors",
+        "model.layers.31.self_attn.o_proj.weight": "model-00019-of-00019.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "model-00019-of-00019.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "model-00019-of-00019.safetensors",
+        "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00019.safetensors",
+        "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00019.safetensors",
+        "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00019.safetensors",
+        "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00019.safetensors",
+        "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00019.safetensors",
+        "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00019.safetensors",
+        "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00019.safetensors",
+        "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00019.safetensors",
+        "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00019.safetensors",
+        "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00019.safetensors",
+        "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00019.safetensors",
+        "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00019.safetensors",
+        "model.layers.4.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00019.safetensors",
+        "model.layers.4.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00019.safetensors",
+        "model.layers.4.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00019.safetensors",
+        "model.layers.4.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00019.safetensors",
+        "model.layers.4.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00019.safetensors",
+        "model.layers.4.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00019.safetensors",
+        "model.layers.4.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00019.safetensors",
+        "model.layers.4.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00019.safetensors",
+        "model.layers.4.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00019.safetensors",
+        "model.layers.4.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00019.safetensors",
+        "model.layers.4.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00019.safetensors",
+        "model.layers.4.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00019.safetensors",
+        "model.layers.4.block_sparse_moe.gate.weight": "model-00003-of-00019.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00003-of-00019.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00019.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00019.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00019.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00019.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00019.safetensors",
+        "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00019.safetensors",
+        "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00019.safetensors",
+        "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00019.safetensors",
+        "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00019.safetensors",
+        "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00019.safetensors",
+        "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00019.safetensors",
+        "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00019.safetensors",
+        "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00019.safetensors",
+        "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00019.safetensors",
+        "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00019.safetensors",
+        "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00019.safetensors",
+        "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00019.safetensors",
+        "model.layers.5.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00019.safetensors",
+        "model.layers.5.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00019.safetensors",
+        "model.layers.5.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00019.safetensors",
+        "model.layers.5.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00019.safetensors",
+        "model.layers.5.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00019.safetensors",
+        "model.layers.5.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00019.safetensors",
+        "model.layers.5.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00019.safetensors",
+        "model.layers.5.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00019.safetensors",
+        "model.layers.5.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00019.safetensors",
+        "model.layers.5.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00019.safetensors",
+        "model.layers.5.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00019.safetensors",
+        "model.layers.5.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00019.safetensors",
+        "model.layers.5.block_sparse_moe.gate.weight": "model-00003-of-00019.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00004-of-00019.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00019.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00019.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00019.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00019.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00019.safetensors",
+        "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00019.safetensors",
+        "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00019.safetensors",
+        "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00019.safetensors",
+        "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00019.safetensors",
+        "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00019.safetensors",
+        "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00019.safetensors",
+        "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00019.safetensors",
+        "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00019.safetensors",
+        "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00019.safetensors",
+        "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00019.safetensors",
+        "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00019.safetensors",
+        "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00019.safetensors",
+        "model.layers.6.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00019.safetensors",
+        "model.layers.6.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00019.safetensors",
+        "model.layers.6.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00019.safetensors",
+        "model.layers.6.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00019.safetensors",
+        "model.layers.6.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00019.safetensors",
+        "model.layers.6.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00019.safetensors",
+        "model.layers.6.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00019.safetensors",
+        "model.layers.6.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00019.safetensors",
+        "model.layers.6.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00019.safetensors",
+        "model.layers.6.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00019.safetensors",
+        "model.layers.6.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00019.safetensors",
+        "model.layers.6.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00019.safetensors",
+        "model.layers.6.block_sparse_moe.gate.weight": "model-00004-of-00019.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00005-of-00019.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00019.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00019.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00019.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00019.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00019.safetensors",
+        "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00019.safetensors",
+        "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00019.safetensors",
+        "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00019.safetensors",
+        "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00019.safetensors",
+        "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00019.safetensors",
+        "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00019.safetensors",
+        "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00019.safetensors",
+        "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00019.safetensors",
+        "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00019.safetensors",
+        "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00019.safetensors",
+        "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00019.safetensors",
+        "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00019.safetensors",
+        "model.layers.7.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00019.safetensors",
+        "model.layers.7.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00019.safetensors",
+        "model.layers.7.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00019.safetensors",
+        "model.layers.7.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00019.safetensors",
+        "model.layers.7.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00019.safetensors",
+        "model.layers.7.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00019.safetensors",
+        "model.layers.7.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00019.safetensors",
+        "model.layers.7.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00019.safetensors",
+        "model.layers.7.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00019.safetensors",
+        "model.layers.7.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00019.safetensors",
+        "model.layers.7.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00019.safetensors",
+        "model.layers.7.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00019.safetensors",
+        "model.layers.7.block_sparse_moe.gate.weight": "model-00005-of-00019.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00005-of-00019.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00019.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model-00005-of-00019.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00005-of-00019.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00019.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model-00005-of-00019.safetensors",
+        "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00019.safetensors",
+        "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00019.safetensors",
+        "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00019.safetensors",
+        "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00019.safetensors",
+        "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00019.safetensors",
+        "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00019.safetensors",
+        "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00019.safetensors",
+        "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00019.safetensors",
+        "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00019.safetensors",
+        "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00019.safetensors",
+        "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00019.safetensors",
+        "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00019.safetensors",
+        "model.layers.8.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00019.safetensors",
+        "model.layers.8.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00019.safetensors",
+        "model.layers.8.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00019.safetensors",
+        "model.layers.8.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00019.safetensors",
+        "model.layers.8.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00019.safetensors",
+        "model.layers.8.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00019.safetensors",
+        "model.layers.8.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00019.safetensors",
+        "model.layers.8.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00019.safetensors",
+        "model.layers.8.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00019.safetensors",
+        "model.layers.8.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00019.safetensors",
+        "model.layers.8.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00019.safetensors",
+        "model.layers.8.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00019.safetensors",
+        "model.layers.8.block_sparse_moe.gate.weight": "model-00005-of-00019.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00006-of-00019.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model-00006-of-00019.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00019.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00019.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00019.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00019.safetensors",
+        "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00019.safetensors",
+        "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00019.safetensors",
+        "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00019.safetensors",
+        "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00019.safetensors",
+        "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00019.safetensors",
+        "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00019.safetensors",
+        "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00019.safetensors",
+        "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00019.safetensors",
+        "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00019.safetensors",
+        "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00019.safetensors",
+        "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00019.safetensors",
+        "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00019.safetensors",
+        "model.layers.9.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00019.safetensors",
+        "model.layers.9.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00019.safetensors",
+        "model.layers.9.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00019.safetensors",
+        "model.layers.9.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00019.safetensors",
+        "model.layers.9.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00019.safetensors",
+        "model.layers.9.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00019.safetensors",
+        "model.layers.9.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00019.safetensors",
+        "model.layers.9.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00019.safetensors",
+        "model.layers.9.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00019.safetensors",
+        "model.layers.9.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00019.safetensors",
+        "model.layers.9.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00019.safetensors",
+        "model.layers.9.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00019.safetensors",
+        "model.layers.9.block_sparse_moe.gate.weight": "model-00006-of-00019.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00006-of-00019.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model-00006-of-00019.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model-00006-of-00019.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00006-of-00019.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model-00006-of-00019.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model-00006-of-00019.safetensors",
+        "model.norm.weight": "model-00019-of-00019.safetensors"
+    }
+}