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 sha256:980ca234cf7aa1b286b4b24811b5705bc88acb2b374bdfd9035700f4395d43bd
+size 4892838376

pytorch_model-00002-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4487f2b699da838ce64d1b9cb1e304d2ead439f18057a8289c106f24a7fd422
+size 4983017380

pytorch_model-00003-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24e7bc5e627da5bf27f89b1b26092bc65dd78a0621e3411e59cc0f0daf7ba097
+size 4983017464

pytorch_model-00004-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdd04cea3f9e1079c1a443625b0677f366441a9dea7faeab7c47193a56c4f73a
+size 4899046886

pytorch_model-00005-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff558d01500c187e62f2b44792bd7476b7208013d18f1671308f65acc9e55fe4
+size 4983017416

pytorch_model-00006-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab5ff4db5d11002b370ef01e9d81229cc51c844f69c122c5135423c152a58cf4
+size 4983017380

pytorch_model-00007-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57a75a1c8176c1ed890beda0efab2f077ffcf24042894ca6fd3103a02b4698b6
+size 4899046950

pytorch_model-00008-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d68cb23514b05b55b8a7169f672b031317736b1c471f2054c706fa71a47583d8
+size 4983017440

pytorch_model-00009-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98ee825b671a3b296aac3668031cbb487ae364079d4215839a72734d40722ce9
+size 4983017380

pytorch_model-00010-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3088a15b8643dc96f92f11b3836e771c483ba9edb487b03891f2c95d502a32f
+size 4899046950

pytorch_model-00011-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d3a608a6813343d0dce0c193072b2f59e570efbb7ac26d2e5ce2875605d6ea8
+size 4983017404

pytorch_model-00012-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65ac6f37f9a64aadf1668fc861093efcce40151c36a61f28a41b84d5f2c4f0ad
+size 4983017404

pytorch_model-00013-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b74712cc0662971810b41b1d64298d406256f3b37e3001079482027545ac879
+size 4983017380

pytorch_model-00014-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10319d94248fa18b4c50b46c81d86ce422bf804d056c97a85d00b7be07ab4f88
+size 4899046950

pytorch_model-00015-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3dc5c0d2d07e9a297aebd41a50fd516e6cbb8b086790775c20986aaf9310642
+size 4983017440

pytorch_model-00016-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a87dc458fecd9b0ac206b37d9b5691c069e44115ab9e74abeeb04a64e652031f
+size 4983017380

pytorch_model-00017-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f5f47711682f7e6e15051f967938c7cc1fdfa1fdf82fb0bffc2f7153613f831
+size 4899046950

pytorch_model-00018-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e52b956ab2c3cd977447f67b38201192587dad5e750247758a5ef23bd1cd1178
+size 4983017416

pytorch_model-00019-of-00019.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7e8da9ea48aa38e7c2a1e2a99712ac3c7517932ba4e5b58b8289ce42f126bee
+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"
+  }
+}