Upload folder using huggingface_hub

config.json

@@ -18,20 +18,6 @@
   "num_key_value_heads": 8,
   "num_local_experts": 8,
   "output_router_logits": false,
-  "quantization_config": {
-    "_load_in_4bit": true,
-    "_load_in_8bit": false,
-    "bnb_4bit_compute_dtype": "bfloat16",
-    "bnb_4bit_quant_type": "nf4",
-    "bnb_4bit_use_double_quant": true,
-    "llm_int8_enable_fp32_cpu_offload": false,
-    "llm_int8_has_fp16_weight": false,
-    "llm_int8_skip_modules": null,
-    "llm_int8_threshold": 6.0,
-    "load_in_4bit": true,
-    "load_in_8bit": false,
-    "quant_method": "bitsandbytes"
-  },
   "rms_norm_eps": 1e-05,
   "rope_theta": 1000000.0,
   "router_aux_loss_coef": 0.02,

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 32000,
+  "transformers_version": "4.38.0.dev0"
+}

pytorch_model-00001-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51c5a71a812457040929a55bb96800bcfce41994813bb45cf6c25cdb8951a06d
+size 4892838376

pytorch_model-00002-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3816cd5f4e156bf9a910c72dc988ea8e8b704948729b5d4c3ecf1545a345124a
+size 4983017380

pytorch_model-00003-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4feff333b36bf4d41b148530ca5e56c0b6a1ccb5c54784798b0f59488f6e3bb9
+size 4983017464

pytorch_model-00004-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d92f90fa919c696d1bb9e3eefe01c2385c64eb6384ef3caa94052595b5f811d6
+size 4899046886

pytorch_model-00005-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08d0b5234ae97f6dc3463d80547ecb01e77c2f257385955fc571eeb8d7460722
+size 4983017416

pytorch_model-00006-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef1b3e7b9dfaa98760a632305df27390f92c881bd5ad5f33901f25968abf2c21
+size 4983017380

pytorch_model-00007-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f43c80e6419f5a7b6967313c5255b0999798cd87ee720e76adc2edf245b26c2c
+size 4899046950

pytorch_model-00008-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:809b2026dc9622d36afa07b15704ede41cd952bd63115e0b0848db703fd5ba92
+size 4983017440

pytorch_model-00009-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edb7d624227fde26673281e9921440dd209e2ee4c4e2093acd6e089c4f510c71
+size 4983017380

pytorch_model-00010-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5efee6b83ddfe0de30d3f864565125c59245bba509111904b0386463cf62b7f
+size 4899046950

pytorch_model-00011-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc0cd738b018c3f4e5f1b29026343b4234012e45c7727bf9235c22e4eb1b8910
+size 4983017404

pytorch_model-00012-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f9b5c320b508d0ec6801e931ae85303025297223fc3dfe908c4573b5f747d49
+size 4983017404

pytorch_model-00013-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62b997f9e9935c0478ebd05a196da9738c0abe19ff0c801ddf9ac27e9f5a11cc
+size 4983017380

pytorch_model-00014-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0818dc2b70b504b44bdbb9e30d79740acec60c0c5c8bf896019e63b0fc3575c9
+size 4899046950

pytorch_model-00015-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:170495365bb626c8674889dd54bfe2e1f8edf49a2925ccf7df5a4e0abe694bc0
+size 4983017440

pytorch_model-00016-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ebc63933525cc6d46aa5cacd355666f597d1565514c3549ddf2c0f1d8f2a3d8
+size 4983017380

pytorch_model-00017-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2682b768ad72d6afee2f2dca054de66b8ab3d4354ab6b5be25e0a9d320dbd901
+size 4899046950

pytorch_model-00018-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e16d5bf94bde88a8c768978ead09bf90988539580728385333ce10fae621863
+size 4983017416

pytorch_model-00019-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9196a70e7ef3cc2e3c780014129e8c673785672711cb05d4c474e500c8ed179d
+size 4221706114

pytorch_model.bin.index.json

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