Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "Crystalcareai/GemMoE-Beta",
+  "architectures": [
+    "GemmaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "head_dim": 256,
+  "hidden_act": "gelu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 24576,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma",
+  "num_attention_heads": 16,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 16,
+  "num_local_experts": 8,
+  "output_router_logits": false,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "use_cache": false,
+  "vocab_size": 256000
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "do_sample": true,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.38.2"
+}

pytorch_model-00001-of-00024.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe619042db418828e414d53c449ed3fa73c1ef469303774532cf4db2f37fcebd
+size 4995475862

pytorch_model-00002-of-00024.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a059458d6b0aed6bd258cbd2dc3660886b7a8d16cbf1ca27588f7fc7c108c7f5
+size 4982922912

pytorch_model-00003-of-00024.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e3ed441cedf660403a48936b304b08fb2957bd7a5749eda928a626a7f84e5e7
+size 4982959290

pytorch_model-00004-of-00024.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccc48bf0b2b528739f00f8ef7af158a7e74a31af80674a1f8b273c22f27d2354
+size 4932577464

pytorch_model-00005-of-00024.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22d4441caab9e2733e6220d881b49b96c5035cbdf16099c1932037bbd1ea3140
+size 4932577464

pytorch_model-00006-of-00024.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75f3bb146adb83f21b10266d80d473433215eb10761fc96a3f0c237978ecf244
+size 4932577464

pytorch_model-00007-of-00024.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:029a656af03a5785efd7399840ff942bc750ebf980333d7b780cc81e346ee1fd
+size 4932577500

pytorch_model-00008-of-00024.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76ba1441583ab91800a5e26838426584dd835e81f736e73ff9a9a8db47dfeb60
+size 4882259882

pytorch_model-00009-of-00024.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6404744577e49a93fcef8f0b1f0d75f24fd235de5080005e335a551bfbc86d8e
+size 4932626954

pytorch_model-00010-of-00024.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78bb4223d2239ef8cee60236a1e86410b89d916390d128a7a41035c6d98fba89
+size 4932577528

pytorch_model-00011-of-00024.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f8fdb6ccb0f9652053a0a3ae916dbb6e4afb8cfdff679835673c2d8f2ebdb81
+size 4932577528

pytorch_model-00012-of-00024.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80965c534885cdafb6fd9b97352da7d71f8810b79dc6bbdc8fc441497b997e95
+size 4932577528

pytorch_model-00013-of-00024.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6aaf40d38771279866cd9b482ed381eea82fba204d193b4cd0c0068599c0d4cd
+size 4982922976

pytorch_model-00014-of-00024.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f58aeada8a5bb2d91a3725b7755231b65ddcf89ba71477c0b7e6c5e7f5e03c5f
+size 4982959354

pytorch_model-00015-of-00024.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09ab7afed2af77fba598a697869aee3aad7274e751bfde0576c9cf61f83a9714
+size 4932577528

pytorch_model-00016-of-00024.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2efc12d0ae9a9e203fe9c026c095b3b2fc1787be3109a5fe86506ac0854fe1ac
+size 4932577528

pytorch_model-00017-of-00024.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfb70ca36d2fa15f9473f6f8b4018ce812924748de158409cb7bd9b2e952c40a
+size 4932577528

pytorch_model-00018-of-00024.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16b5bce795e5923105dac36666ea92d0bcf24e5da5111a7172a4e3d48374b0d1
+size 4932577564

pytorch_model-00019-of-00024.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3a8cd85b6465de9042a29a0bf1ba0c0e4ba2c2f3183776dba5e817597f237b1
+size 4882259882

pytorch_model-00020-of-00024.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8fa2528417945c3864e047bd41f0941d0442461eb992f4dc89cbb9dfcb5678c
+size 4932627018

pytorch_model-00021-of-00024.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:017b6458a160c25099f7a356029ea9bfbca62af54c1039cb535798af6b13b78c
+size 4932577528

pytorch_model-00022-of-00024.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:718fba3e3c0e5b3836db1dcdebd6867b72f487a5c4d42e26e79d18ee6465f3bf
+size 4932577528

pytorch_model-00023-of-00024.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dff502b54989059c3c46879d7ea2db4dd7b9b2c3ef24743dd9198723baca1da
+size 4932577528

pytorch_model-00024-of-00024.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fed1ba303191dbd1249c9da97120d81754f1511c634ba705a49889bb5c49e424
+size 4932597058

pytorch_model.bin.index.json

@@ -0,0 +1,962 @@
+{
+  "metadata": {
+    "total_size": 118545340416
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00001-of-00024.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00024.bin",
+    "model.layers.0.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00024.bin",
+    "model.layers.0.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00024.bin",
+    "model.layers.0.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00024.bin",
+    "model.layers.0.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00024.bin",
+    "model.layers.0.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00024.bin",
+    "model.layers.0.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00024.bin",
+    "model.layers.0.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00024.bin",
+    "model.layers.0.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00024.bin",
+    "model.layers.0.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00024.bin",
+    "model.layers.0.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00001-of-00024.bin",
+    "model.layers.0.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00001-of-00024.bin",
+    "model.layers.0.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00001-of-00024.bin",
+    "model.layers.0.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00001-of-00024.bin",
+    "model.layers.0.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00001-of-00024.bin",
+    "model.layers.0.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00001-of-00024.bin",
+    "model.layers.0.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00001-of-00024.bin",
+    "model.layers.0.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00001-of-00024.bin",
+    "model.layers.0.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00001-of-00024.bin",
+    "model.layers.0.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00001-of-00024.bin",
+    "model.layers.0.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00002-of-00024.bin",
+    "model.layers.0.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00002-of-00024.bin",
+    "model.layers.0.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00002-of-00024.bin",
+    "model.layers.0.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00002-of-00024.bin",
+    "model.layers.0.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00002-of-00024.bin",
+    "model.layers.0.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00024.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00002-of-00024.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00024.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00024.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00024.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00002-of-00024.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00024.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00024.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00024.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00024.bin",
+    "model.layers.1.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00024.bin",
+    "model.layers.1.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00024.bin",
+    "model.layers.1.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00024.bin",
+    "model.layers.1.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00024.bin",
+    "model.layers.1.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00024.bin",
+    "model.layers.1.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00024.bin",
+    "model.layers.1.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00024.bin",
+    "model.layers.1.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00024.bin",
+    "model.layers.1.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00024.bin",
+    "model.layers.1.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00002-of-00024.bin",
+    "model.layers.1.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00002-of-00024.bin",
+    "model.layers.1.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00002-of-00024.bin",
+    "model.layers.1.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00002-of-00024.bin",
+    "model.layers.1.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00002-of-00024.bin",
+    "model.layers.1.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00002-of-00024.bin",
+    "model.layers.1.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00002-of-00024.bin",
+    "model.layers.1.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00002-of-00024.bin",
+    "model.layers.1.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00002-of-00024.bin",
+    "model.layers.1.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00002-of-00024.bin",
+    "model.layers.1.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00002-of-00024.bin",
+    "model.layers.1.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00002-of-00024.bin",
+    "model.layers.1.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00002-of-00024.bin",
+    "model.layers.1.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00002-of-00024.bin",
+    "model.layers.1.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00002-of-00024.bin",
+    "model.layers.1.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00024.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00002-of-00024.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00002-of-00024.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00002-of-00024.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00002-of-00024.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00002-of-00024.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00024.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00002-of-00024.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00024.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00024.bin",
+    "model.layers.10.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00009-of-00024.bin",
+    "model.layers.10.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00009-of-00024.bin",
+    "model.layers.10.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00009-of-00024.bin",
+    "model.layers.10.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00009-of-00024.bin",
+    "model.layers.10.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00010-of-00024.bin",
+    "model.layers.10.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00010-of-00024.bin",
+    "model.layers.10.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00010-of-00024.bin",
+    "model.layers.10.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00010-of-00024.bin",
+    "model.layers.10.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00010-of-00024.bin",
+    "model.layers.10.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00010-of-00024.bin",
+    "model.layers.10.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00010-of-00024.bin",
+    "model.layers.10.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00010-of-00024.bin",
+    "model.layers.10.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00010-of-00024.bin",
+    "model.layers.10.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00010-of-00024.bin",
+    "model.layers.10.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00010-of-00024.bin",
+    "model.layers.10.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00010-of-00024.bin",
+    "model.layers.10.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00010-of-00024.bin",
+    "model.layers.10.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00010-of-00024.bin",
+    "model.layers.10.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00010-of-00024.bin",
+    "model.layers.10.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00010-of-00024.bin",
+    "model.layers.10.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00010-of-00024.bin",
+    "model.layers.10.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00010-of-00024.bin",
+    "model.layers.10.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00010-of-00024.bin",
+    "model.layers.10.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00010-of-00024.bin",
+    "model.layers.10.block_sparse_moe.gate.weight": "pytorch_model-00009-of-00024.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00010-of-00024.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00009-of-00024.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00009-of-00024.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00009-of-00024.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00010-of-00024.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00009-of-00024.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00009-of-00024.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00009-of-00024.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00009-of-00024.bin",
+    "model.layers.11.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00010-of-00024.bin",
+    "model.layers.11.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00010-of-00024.bin",
+    "model.layers.11.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00010-of-00024.bin",
+    "model.layers.11.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00010-of-00024.bin",
+    "model.layers.11.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00010-of-00024.bin",
+    "model.layers.11.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00010-of-00024.bin",
+    "model.layers.11.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00010-of-00024.bin",
+    "model.layers.11.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00010-of-00024.bin",
+    "model.layers.11.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00010-of-00024.bin",
+    "model.layers.11.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00011-of-00024.bin",
+    "model.layers.11.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00011-of-00024.bin",
+    "model.layers.11.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00011-of-00024.bin",
+    "model.layers.11.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00011-of-00024.bin",
+    "model.layers.11.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00011-of-00024.bin",
+    "model.layers.11.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00011-of-00024.bin",
+    "model.layers.11.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00011-of-00024.bin",
+    "model.layers.11.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00011-of-00024.bin",
+    "model.layers.11.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00011-of-00024.bin",
+    "model.layers.11.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00011-of-00024.bin",
+    "model.layers.11.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00011-of-00024.bin",
+    "model.layers.11.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00011-of-00024.bin",
+    "model.layers.11.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00011-of-00024.bin",
+    "model.layers.11.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00011-of-00024.bin",
+    "model.layers.11.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00011-of-00024.bin",
+    "model.layers.11.block_sparse_moe.gate.weight": "pytorch_model-00010-of-00024.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00011-of-00024.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00010-of-00024.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00010-of-00024.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00010-of-00024.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00011-of-00024.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00010-of-00024.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00010-of-00024.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00010-of-00024.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00010-of-00024.bin",
+    "model.layers.12.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00011-of-00024.bin",
+    "model.layers.12.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00011-of-00024.bin",
+    "model.layers.12.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00011-of-00024.bin",
+    "model.layers.12.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00011-of-00024.bin",
+    "model.layers.12.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00011-of-00024.bin",
+    "model.layers.12.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00011-of-00024.bin",
+    "model.layers.12.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00011-of-00024.bin",
+    "model.layers.12.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00011-of-00024.bin",
+    "model.layers.12.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00011-of-00024.bin",
+    "model.layers.12.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00011-of-00024.bin",
+    "model.layers.12.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00011-of-00024.bin",
+    "model.layers.12.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00011-of-00024.bin",
+    "model.layers.12.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00011-of-00024.bin",
+    "model.layers.12.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00011-of-00024.bin",
+    "model.layers.12.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00012-of-00024.bin",
+    "model.layers.12.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00012-of-00024.bin",
+    "model.layers.12.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00012-of-00024.bin",
+    "model.layers.12.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00012-of-00024.bin",
+    "model.layers.12.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00012-of-00024.bin",
+    "model.layers.12.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00012-of-00024.bin",
+    "model.layers.12.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00012-of-00024.bin",
+    "model.layers.12.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00012-of-00024.bin",
+    "model.layers.12.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00012-of-00024.bin",
+    "model.layers.12.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00012-of-00024.bin",
+    "model.layers.12.block_sparse_moe.gate.weight": "pytorch_model-00011-of-00024.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00012-of-00024.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00011-of-00024.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00011-of-00024.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00011-of-00024.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00012-of-00024.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00011-of-00024.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00011-of-00024.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00011-of-00024.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00011-of-00024.bin",
+    "model.layers.13.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00012-of-00024.bin",
+    "model.layers.13.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00012-of-00024.bin",
+    "model.layers.13.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00012-of-00024.bin",
+    "model.layers.13.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00012-of-00024.bin",
+    "model.layers.13.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00012-of-00024.bin",
+    "model.layers.13.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00012-of-00024.bin",
+    "model.layers.13.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00012-of-00024.bin",
+    "model.layers.13.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00012-of-00024.bin",
+    "model.layers.13.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00012-of-00024.bin",
+    "model.layers.13.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00012-of-00024.bin",
+    "model.layers.13.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00012-of-00024.bin",
+    "model.layers.13.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00012-of-00024.bin",
+    "model.layers.13.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00012-of-00024.bin",
+    "model.layers.13.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00012-of-00024.bin",
+    "model.layers.13.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00012-of-00024.bin",
+    "model.layers.13.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00012-of-00024.bin",
+    "model.layers.13.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00012-of-00024.bin",
+    "model.layers.13.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00012-of-00024.bin",
+    "model.layers.13.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00012-of-00024.bin",
+    "model.layers.13.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00013-of-00024.bin",
+    "model.layers.13.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00013-of-00024.bin",
+    "model.layers.13.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00013-of-00024.bin",
+    "model.layers.13.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00013-of-00024.bin",
+    "model.layers.13.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00013-of-00024.bin",
+    "model.layers.13.block_sparse_moe.gate.weight": "pytorch_model-00012-of-00024.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00013-of-00024.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00012-of-00024.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00012-of-00024.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00012-of-00024.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00013-of-00024.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00012-of-00024.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00012-of-00024.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00012-of-00024.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00012-of-00024.bin",
+    "model.layers.14.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00013-of-00024.bin",
+    "model.layers.14.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00013-of-00024.bin",
+    "model.layers.14.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00013-of-00024.bin",
+    "model.layers.14.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00013-of-00024.bin",
+    "model.layers.14.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00013-of-00024.bin",
+    "model.layers.14.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00013-of-00024.bin",
+    "model.layers.14.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00013-of-00024.bin",
+    "model.layers.14.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00013-of-00024.bin",
+    "model.layers.14.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00013-of-00024.bin",
+    "model.layers.14.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00013-of-00024.bin",
+    "model.layers.14.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00013-of-00024.bin",
+    "model.layers.14.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00013-of-00024.bin",
+    "model.layers.14.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00013-of-00024.bin",
+    "model.layers.14.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00013-of-00024.bin",
+    "model.layers.14.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00013-of-00024.bin",
+    "model.layers.14.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00013-of-00024.bin",
+    "model.layers.14.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00013-of-00024.bin",
+    "model.layers.14.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00013-of-00024.bin",
+    "model.layers.14.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00013-of-00024.bin",
+    "model.layers.14.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00013-of-00024.bin",
+    "model.layers.14.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00013-of-00024.bin",
+    "model.layers.14.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00013-of-00024.bin",
+    "model.layers.14.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00013-of-00024.bin",
+    "model.layers.14.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00013-of-00024.bin",
+    "model.layers.14.block_sparse_moe.gate.weight": "pytorch_model-00013-of-00024.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00013-of-00024.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00013-of-00024.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00013-of-00024.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00013-of-00024.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00013-of-00024.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00013-of-00024.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00013-of-00024.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00013-of-00024.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00013-of-00024.bin",
+    "model.layers.15.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00014-of-00024.bin",
+    "model.layers.15.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00014-of-00024.bin",
+    "model.layers.15.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00014-of-00024.bin",
+    "model.layers.15.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00014-of-00024.bin",
+    "model.layers.15.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00014-of-00024.bin",
+    "model.layers.15.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00014-of-00024.bin",
+    "model.layers.15.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00014-of-00024.bin",
+    "model.layers.15.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00014-of-00024.bin",
+    "model.layers.15.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00014-of-00024.bin",
+    "model.layers.15.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00014-of-00024.bin",
+    "model.layers.15.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00014-of-00024.bin",
+    "model.layers.15.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00014-of-00024.bin",
+    "model.layers.15.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00014-of-00024.bin",
+    "model.layers.15.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00014-of-00024.bin",
+    "model.layers.15.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00014-of-00024.bin",
+    "model.layers.15.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00014-of-00024.bin",
+    "model.layers.15.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00014-of-00024.bin",
+    "model.layers.15.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00014-of-00024.bin",
+    "model.layers.15.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00014-of-00024.bin",
+    "model.layers.15.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00014-of-00024.bin",
+    "model.layers.15.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00014-of-00024.bin",
+    "model.layers.15.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00014-of-00024.bin",
+    "model.layers.15.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00014-of-00024.bin",
+    "model.layers.15.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00014-of-00024.bin",
+    "model.layers.15.block_sparse_moe.gate.weight": "pytorch_model-00014-of-00024.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00014-of-00024.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00014-of-00024.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00014-of-00024.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00014-of-00024.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00014-of-00024.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00013-of-00024.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00014-of-00024.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00013-of-00024.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00014-of-00024.bin",
+    "model.layers.16.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00014-of-00024.bin",
+    "model.layers.16.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00014-of-00024.bin",
+    "model.layers.16.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00015-of-00024.bin",
+    "model.layers.16.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00015-of-00024.bin",
+    "model.layers.16.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00015-of-00024.bin",
+    "model.layers.16.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00015-of-00024.bin",
+    "model.layers.16.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00015-of-00024.bin",
+    "model.layers.16.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00015-of-00024.bin",
+    "model.layers.16.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00015-of-00024.bin",
+    "model.layers.16.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00015-of-00024.bin",
+    "model.layers.16.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00015-of-00024.bin",
+    "model.layers.16.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00015-of-00024.bin",
+    "model.layers.16.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00015-of-00024.bin",
+    "model.layers.16.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00015-of-00024.bin",
+    "model.layers.16.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00015-of-00024.bin",
+    "model.layers.16.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00015-of-00024.bin",
+    "model.layers.16.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00015-of-00024.bin",
+    "model.layers.16.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00015-of-00024.bin",
+    "model.layers.16.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00015-of-00024.bin",
+    "model.layers.16.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00015-of-00024.bin",
+    "model.layers.16.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00015-of-00024.bin",
+    "model.layers.16.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00015-of-00024.bin",
+    "model.layers.16.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00015-of-00024.bin",
+    "model.layers.16.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00015-of-00024.bin",
+    "model.layers.16.block_sparse_moe.gate.weight": "pytorch_model-00014-of-00024.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00015-of-00024.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00014-of-00024.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00014-of-00024.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00014-of-00024.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00015-of-00024.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00014-of-00024.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00014-of-00024.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00014-of-00024.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00014-of-00024.bin",
+    "model.layers.17.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00015-of-00024.bin",
+    "model.layers.17.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00015-of-00024.bin",
+    "model.layers.17.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00015-of-00024.bin",
+    "model.layers.17.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00015-of-00024.bin",
+    "model.layers.17.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00015-of-00024.bin",
+    "model.layers.17.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00015-of-00024.bin",
+    "model.layers.17.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00015-of-00024.bin",
+    "model.layers.17.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00016-of-00024.bin",
+    "model.layers.17.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00016-of-00024.bin",
+    "model.layers.17.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00016-of-00024.bin",
+    "model.layers.17.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00016-of-00024.bin",
+    "model.layers.17.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00016-of-00024.bin",
+    "model.layers.17.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00016-of-00024.bin",
+    "model.layers.17.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00016-of-00024.bin",
+    "model.layers.17.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00016-of-00024.bin",
+    "model.layers.17.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00016-of-00024.bin",
+    "model.layers.17.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00016-of-00024.bin",
+    "model.layers.17.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00016-of-00024.bin",
+    "model.layers.17.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00016-of-00024.bin",
+    "model.layers.17.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00016-of-00024.bin",
+    "model.layers.17.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00016-of-00024.bin",
+    "model.layers.17.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00016-of-00024.bin",
+    "model.layers.17.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00016-of-00024.bin",
+    "model.layers.17.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00016-of-00024.bin",
+    "model.layers.17.block_sparse_moe.gate.weight": "pytorch_model-00015-of-00024.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00016-of-00024.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00015-of-00024.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00015-of-00024.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00015-of-00024.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00016-of-00024.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00015-of-00024.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00015-of-00024.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00015-of-00024.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00015-of-00024.bin",
+    "model.layers.18.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00016-of-00024.bin",
+    "model.layers.18.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00016-of-00024.bin",
+    "model.layers.18.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00016-of-00024.bin",
+    "model.layers.18.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00016-of-00024.bin",
+    "model.layers.18.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00016-of-00024.bin",
+    "model.layers.18.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00016-of-00024.bin",
+    "model.layers.18.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00016-of-00024.bin",
+    "model.layers.18.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00016-of-00024.bin",
+    "model.layers.18.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00016-of-00024.bin",
+    "model.layers.18.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00016-of-00024.bin",
+    "model.layers.18.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00016-of-00024.bin",
+    "model.layers.18.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00016-of-00024.bin",
+    "model.layers.18.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00017-of-00024.bin",
+    "model.layers.18.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00017-of-00024.bin",
+    "model.layers.18.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00017-of-00024.bin",
+    "model.layers.18.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00017-of-00024.bin",
+    "model.layers.18.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00017-of-00024.bin",
+    "model.layers.18.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00017-of-00024.bin",
+    "model.layers.18.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00017-of-00024.bin",
+    "model.layers.18.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00017-of-00024.bin",
+    "model.layers.18.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00017-of-00024.bin",
+    "model.layers.18.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00017-of-00024.bin",
+    "model.layers.18.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00017-of-00024.bin",
+    "model.layers.18.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00017-of-00024.bin",
+    "model.layers.18.block_sparse_moe.gate.weight": "pytorch_model-00016-of-00024.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00017-of-00024.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00016-of-00024.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00016-of-00024.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00016-of-00024.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00017-of-00024.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00016-of-00024.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00016-of-00024.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00016-of-00024.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00016-of-00024.bin",
+    "model.layers.19.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00017-of-00024.bin",
+    "model.layers.19.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00017-of-00024.bin",
+    "model.layers.19.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00017-of-00024.bin",
+    "model.layers.19.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00017-of-00024.bin",
+    "model.layers.19.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00017-of-00024.bin",
+    "model.layers.19.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00017-of-00024.bin",
+    "model.layers.19.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00017-of-00024.bin",
+    "model.layers.19.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00017-of-00024.bin",
+    "model.layers.19.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00017-of-00024.bin",
+    "model.layers.19.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00017-of-00024.bin",
+    "model.layers.19.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00017-of-00024.bin",
+    "model.layers.19.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00017-of-00024.bin",
+    "model.layers.19.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00017-of-00024.bin",
+    "model.layers.19.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00017-of-00024.bin",
+    "model.layers.19.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00017-of-00024.bin",
+    "model.layers.19.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00017-of-00024.bin",
+    "model.layers.19.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00017-of-00024.bin",
+    "model.layers.19.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00018-of-00024.bin",
+    "model.layers.19.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00018-of-00024.bin",
+    "model.layers.19.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00018-of-00024.bin",
+    "model.layers.19.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00018-of-00024.bin",
+    "model.layers.19.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00018-of-00024.bin",
+    "model.layers.19.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00018-of-00024.bin",
+    "model.layers.19.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00018-of-00024.bin",
+    "model.layers.19.block_sparse_moe.gate.weight": "pytorch_model-00017-of-00024.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00018-of-00024.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00017-of-00024.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00017-of-00024.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00017-of-00024.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00018-of-00024.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00017-of-00024.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00017-of-00024.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00017-of-00024.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00017-of-00024.bin",
+    "model.layers.2.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00003-of-00024.bin",
+    "model.layers.2.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00003-of-00024.bin",
+    "model.layers.2.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00003-of-00024.bin",
+    "model.layers.2.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00003-of-00024.bin",
+    "model.layers.2.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00003-of-00024.bin",
+    "model.layers.2.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00003-of-00024.bin",
+    "model.layers.2.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003-of-00024.bin",
+    "model.layers.2.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00024.bin",
+    "model.layers.2.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00003-of-00024.bin",
+    "model.layers.2.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00003-of-00024.bin",
+    "model.layers.2.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00003-of-00024.bin",
+    "model.layers.2.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00003-of-00024.bin",
+    "model.layers.2.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00003-of-00024.bin",
+    "model.layers.2.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00003-of-00024.bin",
+    "model.layers.2.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00003-of-00024.bin",
+    "model.layers.2.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00003-of-00024.bin",
+    "model.layers.2.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00003-of-00024.bin",
+    "model.layers.2.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00003-of-00024.bin",
+    "model.layers.2.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00003-of-00024.bin",
+    "model.layers.2.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00003-of-00024.bin",
+    "model.layers.2.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00003-of-00024.bin",
+    "model.layers.2.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00003-of-00024.bin",
+    "model.layers.2.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00003-of-00024.bin",
+    "model.layers.2.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00003-of-00024.bin",
+    "model.layers.2.block_sparse_moe.gate.weight": "pytorch_model-00003-of-00024.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00003-of-00024.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00003-of-00024.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00003-of-00024.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00003-of-00024.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00003-of-00024.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00024.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00003-of-00024.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00024.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00003-of-00024.bin",
+    "model.layers.20.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00018-of-00024.bin",
+    "model.layers.20.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00018-of-00024.bin",
+    "model.layers.20.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00018-of-00024.bin",
+    "model.layers.20.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00018-of-00024.bin",
+    "model.layers.20.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00018-of-00024.bin",
+    "model.layers.20.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00018-of-00024.bin",
+    "model.layers.20.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00018-of-00024.bin",
+    "model.layers.20.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00018-of-00024.bin",
+    "model.layers.20.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00018-of-00024.bin",
+    "model.layers.20.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00018-of-00024.bin",
+    "model.layers.20.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00018-of-00024.bin",
+    "model.layers.20.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00018-of-00024.bin",
+    "model.layers.20.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00018-of-00024.bin",
+    "model.layers.20.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00018-of-00024.bin",
+    "model.layers.20.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00018-of-00024.bin",
+    "model.layers.20.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00018-of-00024.bin",
+    "model.layers.20.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00018-of-00024.bin",
+    "model.layers.20.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00018-of-00024.bin",
+    "model.layers.20.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00018-of-00024.bin",
+    "model.layers.20.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00018-of-00024.bin",
+    "model.layers.20.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00018-of-00024.bin",
+    "model.layers.20.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00018-of-00024.bin",
+    "model.layers.20.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00019-of-00024.bin",
+    "model.layers.20.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00019-of-00024.bin",
+    "model.layers.20.block_sparse_moe.gate.weight": "pytorch_model-00018-of-00024.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00019-of-00024.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00018-of-00024.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00018-of-00024.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00018-of-00024.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00019-of-00024.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00018-of-00024.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00018-of-00024.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00018-of-00024.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00018-of-00024.bin",
+    "model.layers.21.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00019-of-00024.bin",
+    "model.layers.21.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00019-of-00024.bin",
+    "model.layers.21.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00019-of-00024.bin",
+    "model.layers.21.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00019-of-00024.bin",
+    "model.layers.21.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00019-of-00024.bin",
+    "model.layers.21.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00019-of-00024.bin",
+    "model.layers.21.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00019-of-00024.bin",
+    "model.layers.21.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00019-of-00024.bin",
+    "model.layers.21.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00019-of-00024.bin",
+    "model.layers.21.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00019-of-00024.bin",
+    "model.layers.21.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00019-of-00024.bin",
+    "model.layers.21.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00019-of-00024.bin",
+    "model.layers.21.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00019-of-00024.bin",
+    "model.layers.21.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00019-of-00024.bin",
+    "model.layers.21.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00019-of-00024.bin",
+    "model.layers.21.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00019-of-00024.bin",
+    "model.layers.21.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00019-of-00024.bin",
+    "model.layers.21.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00019-of-00024.bin",
+    "model.layers.21.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00019-of-00024.bin",
+    "model.layers.21.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00019-of-00024.bin",
+    "model.layers.21.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00019-of-00024.bin",
+    "model.layers.21.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00019-of-00024.bin",
+    "model.layers.21.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00019-of-00024.bin",
+    "model.layers.21.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00019-of-00024.bin",
+    "model.layers.21.block_sparse_moe.gate.weight": "pytorch_model-00019-of-00024.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00019-of-00024.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00019-of-00024.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00019-of-00024.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00019-of-00024.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00019-of-00024.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00019-of-00024.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00019-of-00024.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00019-of-00024.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00019-of-00024.bin",
+    "model.layers.22.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00020-of-00024.bin",
+    "model.layers.22.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00020-of-00024.bin",
+    "model.layers.22.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00020-of-00024.bin",
+    "model.layers.22.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00020-of-00024.bin",
+    "model.layers.22.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00020-of-00024.bin",
+    "model.layers.22.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00020-of-00024.bin",
+    "model.layers.22.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00020-of-00024.bin",
+    "model.layers.22.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00020-of-00024.bin",
+    "model.layers.22.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00020-of-00024.bin",
+    "model.layers.22.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00020-of-00024.bin",
+    "model.layers.22.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00020-of-00024.bin",
+    "model.layers.22.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00020-of-00024.bin",
+    "model.layers.22.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00020-of-00024.bin",
+    "model.layers.22.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00020-of-00024.bin",
+    "model.layers.22.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00020-of-00024.bin",
+    "model.layers.22.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00020-of-00024.bin",
+    "model.layers.22.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00020-of-00024.bin",
+    "model.layers.22.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00020-of-00024.bin",
+    "model.layers.22.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00020-of-00024.bin",
+    "model.layers.22.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00020-of-00024.bin",
+    "model.layers.22.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00020-of-00024.bin",
+    "model.layers.22.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00020-of-00024.bin",
+    "model.layers.22.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00020-of-00024.bin",
+    "model.layers.22.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00020-of-00024.bin",
+    "model.layers.22.block_sparse_moe.gate.weight": "pytorch_model-00020-of-00024.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00020-of-00024.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00020-of-00024.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00019-of-00024.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00019-of-00024.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00020-of-00024.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00019-of-00024.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00019-of-00024.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00019-of-00024.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00019-of-00024.bin",
+    "model.layers.23.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00020-of-00024.bin",
+    "model.layers.23.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00020-of-00024.bin",
+    "model.layers.23.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00020-of-00024.bin",
+    "model.layers.23.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00020-of-00024.bin",
+    "model.layers.23.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00021-of-00024.bin",
+    "model.layers.23.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00021-of-00024.bin",
+    "model.layers.23.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00021-of-00024.bin",
+    "model.layers.23.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00021-of-00024.bin",
+    "model.layers.23.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00021-of-00024.bin",
+    "model.layers.23.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00021-of-00024.bin",
+    "model.layers.23.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00021-of-00024.bin",
+    "model.layers.23.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00021-of-00024.bin",
+    "model.layers.23.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00021-of-00024.bin",
+    "model.layers.23.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00021-of-00024.bin",
+    "model.layers.23.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00021-of-00024.bin",
+    "model.layers.23.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00021-of-00024.bin",
+    "model.layers.23.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00021-of-00024.bin",
+    "model.layers.23.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00021-of-00024.bin",
+    "model.layers.23.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00021-of-00024.bin",
+    "model.layers.23.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00021-of-00024.bin",
+    "model.layers.23.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00021-of-00024.bin",
+    "model.layers.23.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00021-of-00024.bin",
+    "model.layers.23.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00021-of-00024.bin",
+    "model.layers.23.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00021-of-00024.bin",
+    "model.layers.23.block_sparse_moe.gate.weight": "pytorch_model-00020-of-00024.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00021-of-00024.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00020-of-00024.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00020-of-00024.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00020-of-00024.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00021-of-00024.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00020-of-00024.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00020-of-00024.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00020-of-00024.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00020-of-00024.bin",
+    "model.layers.24.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00021-of-00024.bin",
+    "model.layers.24.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00021-of-00024.bin",
+    "model.layers.24.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00021-of-00024.bin",
+    "model.layers.24.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00021-of-00024.bin",
+    "model.layers.24.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00021-of-00024.bin",
+    "model.layers.24.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00021-of-00024.bin",
+    "model.layers.24.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00021-of-00024.bin",
+    "model.layers.24.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00021-of-00024.bin",
+    "model.layers.24.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00021-of-00024.bin",
+    "model.layers.24.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00022-of-00024.bin",
+    "model.layers.24.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00022-of-00024.bin",
+    "model.layers.24.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00022-of-00024.bin",
+    "model.layers.24.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00022-of-00024.bin",
+    "model.layers.24.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00022-of-00024.bin",
+    "model.layers.24.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00022-of-00024.bin",
+    "model.layers.24.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00022-of-00024.bin",
+    "model.layers.24.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00022-of-00024.bin",
+    "model.layers.24.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00022-of-00024.bin",
+    "model.layers.24.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00022-of-00024.bin",
+    "model.layers.24.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00022-of-00024.bin",
+    "model.layers.24.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00022-of-00024.bin",
+    "model.layers.24.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00022-of-00024.bin",
+    "model.layers.24.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00022-of-00024.bin",
+    "model.layers.24.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00022-of-00024.bin",
+    "model.layers.24.block_sparse_moe.gate.weight": "pytorch_model-00021-of-00024.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00022-of-00024.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00021-of-00024.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00021-of-00024.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00021-of-00024.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00022-of-00024.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00021-of-00024.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00021-of-00024.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00021-of-00024.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00021-of-00024.bin",
+    "model.layers.25.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00022-of-00024.bin",
+    "model.layers.25.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00022-of-00024.bin",
+    "model.layers.25.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00022-of-00024.bin",
+    "model.layers.25.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00022-of-00024.bin",
+    "model.layers.25.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00022-of-00024.bin",
+    "model.layers.25.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00022-of-00024.bin",
+    "model.layers.25.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00022-of-00024.bin",
+    "model.layers.25.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00022-of-00024.bin",
+    "model.layers.25.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00022-of-00024.bin",
+    "model.layers.25.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00022-of-00024.bin",
+    "model.layers.25.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00022-of-00024.bin",
+    "model.layers.25.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00022-of-00024.bin",
+    "model.layers.25.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00022-of-00024.bin",
+    "model.layers.25.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00022-of-00024.bin",
+    "model.layers.25.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00023-of-00024.bin",
+    "model.layers.25.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00023-of-00024.bin",
+    "model.layers.25.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00023-of-00024.bin",
+    "model.layers.25.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00023-of-00024.bin",
+    "model.layers.25.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00023-of-00024.bin",
+    "model.layers.25.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00023-of-00024.bin",
+    "model.layers.25.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00023-of-00024.bin",
+    "model.layers.25.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00023-of-00024.bin",
+    "model.layers.25.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00023-of-00024.bin",
+    "model.layers.25.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00023-of-00024.bin",
+    "model.layers.25.block_sparse_moe.gate.weight": "pytorch_model-00022-of-00024.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00023-of-00024.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00022-of-00024.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00022-of-00024.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00022-of-00024.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00023-of-00024.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00022-of-00024.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00022-of-00024.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00022-of-00024.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00022-of-00024.bin",
+    "model.layers.26.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00023-of-00024.bin",
+    "model.layers.26.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00023-of-00024.bin",
+    "model.layers.26.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00023-of-00024.bin",
+    "model.layers.26.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00023-of-00024.bin",
+    "model.layers.26.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00023-of-00024.bin",
+    "model.layers.26.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00023-of-00024.bin",
+    "model.layers.26.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00023-of-00024.bin",
+    "model.layers.26.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00023-of-00024.bin",
+    "model.layers.26.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00023-of-00024.bin",
+    "model.layers.26.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00023-of-00024.bin",
+    "model.layers.26.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00023-of-00024.bin",
+    "model.layers.26.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00023-of-00024.bin",
+    "model.layers.26.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00023-of-00024.bin",
+    "model.layers.26.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00023-of-00024.bin",
+    "model.layers.26.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00023-of-00024.bin",
+    "model.layers.26.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00023-of-00024.bin",
+    "model.layers.26.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00023-of-00024.bin",
+    "model.layers.26.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00023-of-00024.bin",
+    "model.layers.26.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00023-of-00024.bin",
+    "model.layers.26.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00024-of-00024.bin",
+    "model.layers.26.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00024-of-00024.bin",
+    "model.layers.26.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00024-of-00024.bin",
+    "model.layers.26.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00024-of-00024.bin",
+    "model.layers.26.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00024-of-00024.bin",
+    "model.layers.26.block_sparse_moe.gate.weight": "pytorch_model-00023-of-00024.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00024-of-00024.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00023-of-00024.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00023-of-00024.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00023-of-00024.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00024-of-00024.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00023-of-00024.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00023-of-00024.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00023-of-00024.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00023-of-00024.bin",
+    "model.layers.27.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00024-of-00024.bin",
+    "model.layers.27.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00024-of-00024.bin",
+    "model.layers.27.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00024-of-00024.bin",
+    "model.layers.27.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00024-of-00024.bin",
+    "model.layers.27.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00024-of-00024.bin",
+    "model.layers.27.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00024-of-00024.bin",
+    "model.layers.27.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00024-of-00024.bin",
+    "model.layers.27.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00024-of-00024.bin",
+    "model.layers.27.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00024-of-00024.bin",
+    "model.layers.27.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00024-of-00024.bin",
+    "model.layers.27.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00024-of-00024.bin",
+    "model.layers.27.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00024-of-00024.bin",
+    "model.layers.27.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00024-of-00024.bin",
+    "model.layers.27.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00024-of-00024.bin",
+    "model.layers.27.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00024-of-00024.bin",
+    "model.layers.27.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00024-of-00024.bin",
+    "model.layers.27.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00024-of-00024.bin",
+    "model.layers.27.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00024-of-00024.bin",
+    "model.layers.27.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00024-of-00024.bin",
+    "model.layers.27.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00024-of-00024.bin",
+    "model.layers.27.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00024-of-00024.bin",
+    "model.layers.27.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00024-of-00024.bin",
+    "model.layers.27.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00024-of-00024.bin",
+    "model.layers.27.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00024-of-00024.bin",
+    "model.layers.27.block_sparse_moe.gate.weight": "pytorch_model-00024-of-00024.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00024-of-00024.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00024-of-00024.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00024-of-00024.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00024-of-00024.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00024-of-00024.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00024-of-00024.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00024-of-00024.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00024-of-00024.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00024-of-00024.bin",
+    "model.layers.3.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00003-of-00024.bin",
+    "model.layers.3.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00003-of-00024.bin",
+    "model.layers.3.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00004-of-00024.bin",
+    "model.layers.3.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00004-of-00024.bin",
+    "model.layers.3.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00004-of-00024.bin",
+    "model.layers.3.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00004-of-00024.bin",
+    "model.layers.3.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00004-of-00024.bin",
+    "model.layers.3.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00004-of-00024.bin",
+    "model.layers.3.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00004-of-00024.bin",
+    "model.layers.3.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00004-of-00024.bin",
+    "model.layers.3.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00004-of-00024.bin",
+    "model.layers.3.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00004-of-00024.bin",
+    "model.layers.3.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00004-of-00024.bin",
+    "model.layers.3.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00004-of-00024.bin",
+    "model.layers.3.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00004-of-00024.bin",
+    "model.layers.3.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00004-of-00024.bin",
+    "model.layers.3.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00004-of-00024.bin",
+    "model.layers.3.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00004-of-00024.bin",
+    "model.layers.3.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00004-of-00024.bin",
+    "model.layers.3.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00004-of-00024.bin",
+    "model.layers.3.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00004-of-00024.bin",
+    "model.layers.3.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00004-of-00024.bin",
+    "model.layers.3.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00004-of-00024.bin",
+    "model.layers.3.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00004-of-00024.bin",
+    "model.layers.3.block_sparse_moe.gate.weight": "pytorch_model-00003-of-00024.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00004-of-00024.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00003-of-00024.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00003-of-00024.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00003-of-00024.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00004-of-00024.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00003-of-00024.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00003-of-00024.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00003-of-00024.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00003-of-00024.bin",
+    "model.layers.4.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00004-of-00024.bin",
+    "model.layers.4.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00004-of-00024.bin",
+    "model.layers.4.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00004-of-00024.bin",
+    "model.layers.4.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00004-of-00024.bin",
+    "model.layers.4.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00004-of-00024.bin",
+    "model.layers.4.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00004-of-00024.bin",
+    "model.layers.4.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00004-of-00024.bin",
+    "model.layers.4.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00005-of-00024.bin",
+    "model.layers.4.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00005-of-00024.bin",
+    "model.layers.4.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00005-of-00024.bin",
+    "model.layers.4.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00005-of-00024.bin",
+    "model.layers.4.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00005-of-00024.bin",
+    "model.layers.4.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00005-of-00024.bin",
+    "model.layers.4.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00005-of-00024.bin",
+    "model.layers.4.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00005-of-00024.bin",
+    "model.layers.4.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00005-of-00024.bin",
+    "model.layers.4.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00005-of-00024.bin",
+    "model.layers.4.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00005-of-00024.bin",
+    "model.layers.4.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00005-of-00024.bin",
+    "model.layers.4.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00005-of-00024.bin",
+    "model.layers.4.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00005-of-00024.bin",
+    "model.layers.4.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00005-of-00024.bin",
+    "model.layers.4.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00005-of-00024.bin",
+    "model.layers.4.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00005-of-00024.bin",
+    "model.layers.4.block_sparse_moe.gate.weight": "pytorch_model-00004-of-00024.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00005-of-00024.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00004-of-00024.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00004-of-00024.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00004-of-00024.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00005-of-00024.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00004-of-00024.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00004-of-00024.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00004-of-00024.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00004-of-00024.bin",
+    "model.layers.5.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00005-of-00024.bin",
+    "model.layers.5.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00005-of-00024.bin",
+    "model.layers.5.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00005-of-00024.bin",
+    "model.layers.5.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00005-of-00024.bin",
+    "model.layers.5.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00005-of-00024.bin",
+    "model.layers.5.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00005-of-00024.bin",
+    "model.layers.5.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00005-of-00024.bin",
+    "model.layers.5.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00005-of-00024.bin",
+    "model.layers.5.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00005-of-00024.bin",
+    "model.layers.5.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00005-of-00024.bin",
+    "model.layers.5.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00005-of-00024.bin",
+    "model.layers.5.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00005-of-00024.bin",
+    "model.layers.5.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00006-of-00024.bin",
+    "model.layers.5.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00006-of-00024.bin",
+    "model.layers.5.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00006-of-00024.bin",
+    "model.layers.5.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00006-of-00024.bin",
+    "model.layers.5.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00006-of-00024.bin",
+    "model.layers.5.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00006-of-00024.bin",
+    "model.layers.5.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00006-of-00024.bin",
+    "model.layers.5.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00006-of-00024.bin",
+    "model.layers.5.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00006-of-00024.bin",
+    "model.layers.5.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00006-of-00024.bin",
+    "model.layers.5.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00006-of-00024.bin",
+    "model.layers.5.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00006-of-00024.bin",
+    "model.layers.5.block_sparse_moe.gate.weight": "pytorch_model-00005-of-00024.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00006-of-00024.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00005-of-00024.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00005-of-00024.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00005-of-00024.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00006-of-00024.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00005-of-00024.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00005-of-00024.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00005-of-00024.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00005-of-00024.bin",
+    "model.layers.6.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00006-of-00024.bin",
+    "model.layers.6.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00006-of-00024.bin",
+    "model.layers.6.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00006-of-00024.bin",
+    "model.layers.6.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00006-of-00024.bin",
+    "model.layers.6.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00006-of-00024.bin",
+    "model.layers.6.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00006-of-00024.bin",
+    "model.layers.6.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00006-of-00024.bin",
+    "model.layers.6.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00006-of-00024.bin",
+    "model.layers.6.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00006-of-00024.bin",
+    "model.layers.6.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00006-of-00024.bin",
+    "model.layers.6.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00006-of-00024.bin",
+    "model.layers.6.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00006-of-00024.bin",
+    "model.layers.6.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00006-of-00024.bin",
+    "model.layers.6.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00006-of-00024.bin",
+    "model.layers.6.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00006-of-00024.bin",
+    "model.layers.6.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00006-of-00024.bin",
+    "model.layers.6.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00006-of-00024.bin",
+    "model.layers.6.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00007-of-00024.bin",
+    "model.layers.6.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00007-of-00024.bin",
+    "model.layers.6.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00007-of-00024.bin",
+    "model.layers.6.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00007-of-00024.bin",
+    "model.layers.6.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00007-of-00024.bin",
+    "model.layers.6.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00007-of-00024.bin",
+    "model.layers.6.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00007-of-00024.bin",
+    "model.layers.6.block_sparse_moe.gate.weight": "pytorch_model-00006-of-00024.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00007-of-00024.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00006-of-00024.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00006-of-00024.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00006-of-00024.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00007-of-00024.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00006-of-00024.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00006-of-00024.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00006-of-00024.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00006-of-00024.bin",
+    "model.layers.7.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00007-of-00024.bin",
+    "model.layers.7.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00007-of-00024.bin",
+    "model.layers.7.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00007-of-00024.bin",
+    "model.layers.7.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00007-of-00024.bin",
+    "model.layers.7.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00007-of-00024.bin",
+    "model.layers.7.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00007-of-00024.bin",
+    "model.layers.7.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00007-of-00024.bin",
+    "model.layers.7.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00007-of-00024.bin",
+    "model.layers.7.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00007-of-00024.bin",
+    "model.layers.7.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00007-of-00024.bin",
+    "model.layers.7.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00007-of-00024.bin",
+    "model.layers.7.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00007-of-00024.bin",
+    "model.layers.7.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00007-of-00024.bin",
+    "model.layers.7.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00007-of-00024.bin",
+    "model.layers.7.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00007-of-00024.bin",
+    "model.layers.7.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00007-of-00024.bin",
+    "model.layers.7.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00007-of-00024.bin",
+    "model.layers.7.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00007-of-00024.bin",
+    "model.layers.7.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00007-of-00024.bin",
+    "model.layers.7.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00007-of-00024.bin",
+    "model.layers.7.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00007-of-00024.bin",
+    "model.layers.7.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00007-of-00024.bin",
+    "model.layers.7.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00008-of-00024.bin",
+    "model.layers.7.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00008-of-00024.bin",
+    "model.layers.7.block_sparse_moe.gate.weight": "pytorch_model-00007-of-00024.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00008-of-00024.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00007-of-00024.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00007-of-00024.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00007-of-00024.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00008-of-00024.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00007-of-00024.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00007-of-00024.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00007-of-00024.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00007-of-00024.bin",
+    "model.layers.8.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00008-of-00024.bin",
+    "model.layers.8.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00008-of-00024.bin",
+    "model.layers.8.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00008-of-00024.bin",
+    "model.layers.8.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00008-of-00024.bin",
+    "model.layers.8.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00008-of-00024.bin",
+    "model.layers.8.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00008-of-00024.bin",
+    "model.layers.8.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00008-of-00024.bin",
+    "model.layers.8.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00008-of-00024.bin",
+    "model.layers.8.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00008-of-00024.bin",
+    "model.layers.8.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00008-of-00024.bin",
+    "model.layers.8.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00008-of-00024.bin",
+    "model.layers.8.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00008-of-00024.bin",
+    "model.layers.8.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00008-of-00024.bin",
+    "model.layers.8.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00008-of-00024.bin",
+    "model.layers.8.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00008-of-00024.bin",
+    "model.layers.8.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00008-of-00024.bin",
+    "model.layers.8.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00008-of-00024.bin",
+    "model.layers.8.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00008-of-00024.bin",
+    "model.layers.8.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00008-of-00024.bin",
+    "model.layers.8.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00008-of-00024.bin",
+    "model.layers.8.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00008-of-00024.bin",
+    "model.layers.8.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00008-of-00024.bin",
+    "model.layers.8.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00008-of-00024.bin",
+    "model.layers.8.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00008-of-00024.bin",
+    "model.layers.8.block_sparse_moe.gate.weight": "pytorch_model-00008-of-00024.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00008-of-00024.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00008-of-00024.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00008-of-00024.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00008-of-00024.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00008-of-00024.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00008-of-00024.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00008-of-00024.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00008-of-00024.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00008-of-00024.bin",
+    "model.layers.9.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00009-of-00024.bin",
+    "model.layers.9.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00009-of-00024.bin",
+    "model.layers.9.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00009-of-00024.bin",
+    "model.layers.9.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00009-of-00024.bin",
+    "model.layers.9.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00009-of-00024.bin",
+    "model.layers.9.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00009-of-00024.bin",
+    "model.layers.9.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00009-of-00024.bin",
+    "model.layers.9.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00009-of-00024.bin",
+    "model.layers.9.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00009-of-00024.bin",
+    "model.layers.9.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00009-of-00024.bin",
+    "model.layers.9.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00009-of-00024.bin",
+    "model.layers.9.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00009-of-00024.bin",
+    "model.layers.9.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00009-of-00024.bin",
+    "model.layers.9.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00009-of-00024.bin",
+    "model.layers.9.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00009-of-00024.bin",
+    "model.layers.9.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00009-of-00024.bin",
+    "model.layers.9.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00009-of-00024.bin",
+    "model.layers.9.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00009-of-00024.bin",
+    "model.layers.9.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00009-of-00024.bin",
+    "model.layers.9.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00009-of-00024.bin",
+    "model.layers.9.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00009-of-00024.bin",
+    "model.layers.9.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00009-of-00024.bin",
+    "model.layers.9.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00009-of-00024.bin",
+    "model.layers.9.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00009-of-00024.bin",
+    "model.layers.9.block_sparse_moe.gate.weight": "pytorch_model-00009-of-00024.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00009-of-00024.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00009-of-00024.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00008-of-00024.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00008-of-00024.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00009-of-00024.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00008-of-00024.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00008-of-00024.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00008-of-00024.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00008-of-00024.bin",
+    "model.norm.weight": "pytorch_model-00024-of-00024.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16c7bb55a4086eff7c63d3a73bb0e92578ba318dee0a8b51f7fe128911268a7d
+size 17477707

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

tokenizer_config.json

@@ -0,0 +1,53 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "max_length": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "<bos>",
+  "pad_token_type_id": 0,
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}