Upload folder using huggingface_hub

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "cloudyu/TomGrc_FusionNet_34Bx2_MoE_v0.1_DPO_f16",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 7168,
+  "initializer_range": 0.02,
+  "intermediate_size": 20480,
+  "max_position_embeddings": 200000,
+  "model_type": "mixtral",
+  "num_attention_heads": 56,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 60,
+  "num_key_value_heads": 8,
+  "num_local_experts": 2,
+  "output_router_logits": false,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 5000000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "vocab_size": 64000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.37.2"
+}

model-00001-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2b74d7daa686e9575668040691c6f605bc989f4c502f5bb20b5e085334f5191
+size 4910599440

model-00002-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb6f31b846b829f648785c6cb711e31affd82abc812a7992f2ca2e8a2e257830
+size 4815208440

model-00003-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1fb3b744ab1ed3d27985b32631c833e1856dca387ab87240e5f30e457494c1b
+size 4873899568

model-00004-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:448e237ca37056591b373d58cddae492262174222fa97bb3115612abcfd9762e
+size 4815237336

model-00005-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc09d9f147c399b898212a701c7c0da3e40bc0e802e678030d40c245952d3e83
+size 4873899584

model-00006-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8536adf55a4d0af3b8e39c96bc5080ba48c3bb2be5f23c6aad49a3a7c1812b6e
+size 4815237368

model-00007-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fda0363038b40f1afa71597253db7fd1fd26066eec64f0bf1303b35bc4d56e0c
+size 4873899592

model-00008-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dfbc1a2aa433fe69e16dce1a17fd1dc129545d2398d4340763149c020f379ae
+size 4991369240

model-00009-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:019e0c1bc5b716bafafc9e749da26ca4126522789d0aa8379a4b4aff69240d13
+size 4991369136

model-00010-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae37e0822ae5199965ca0c756258ec476dd7a81a1d7fc409c2c9678689ddf3fd
+size 4991369240

model-00011-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31f18f697cb8fd11ffb66aa24a08befb9c5b42ca939f13885d30871b9e721a89
+size 4991369136

model-00012-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b921e7effe064a2a91cf54596e026e48b31db4380182eb35ca2f1b684708a44
+size 4991369240

model-00013-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e577a06bbe12675855c19f4da1055ef9a79e9571fdc393a84a4750c7fad5bfe
+size 4991369136

model-00014-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fd05a998564606f908796b3344d3990f031417d65c44123e53c999f1ad93934
+size 4991369240

model-00015-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11510a2b438d4c8a04fbd410447e0fa49de5db138769065dca912554ad236162
+size 4991369136

model-00016-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5009f124f5afd564a4aa0823bab94b51f249fe7d18668bf97dbd1cacd7cf9685
+size 4991369240

model-00017-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:559541af160685aa3257eb43917335ca01bb797f6da21813cceef6b9bea55e6f
+size 4991369136

model-00018-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76c0702c4f109c8bdac31b4617047c392b0b882f857204b83f870fde55fdce68
+size 4991369240

model-00019-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c7dc30a4a2754bfce5c868ececefedaf0dd83c3fe1695073dba12773ecff8b5
+size 4991369136

model-00020-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:483f581bd4e7c25228aa128454901dd64e806ea6ef9176ce46b40651911a1d5c
+size 4991369240

model-00021-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78d61f9af8a76e7af72d878b8924e22c117ef0f67ffa1a5b1be397470a6a31e1
+size 4991369136

model-00022-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aab7703b823367400a706ebfd0628aea1482fd66c55dbccb9dbd3a275c3ed35f
+size 4991369240

model-00023-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d778fac465ba3e566b8d7a781d11c531c88266ade2ca5dc52c91805ea22a941
+size 4991369136

model-00024-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:279de9fa2d01997946effdd2c7453a4edfb87fe197f3203ee1dab5ed05fe4f8a
+size 4991369240

model-00025-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79f9c01c05968b13512d4b762be42c8d78b1355e45084ad8bbd17ffd8cd54d96
+size 2796625472

model.safetensors.index.json

@@ -0,0 +1,790 @@
+{
+  "metadata": {
+    "total_size": 121627785216
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00025-of-00025.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00025.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00025.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00025.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00025.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00025.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00025.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00025.safetensors",
+    "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00025.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00025.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00025.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00025.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00025.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00025.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00025.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00025.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00025.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00025.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00025.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00025.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00025.safetensors",
+    "model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00025.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00025.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00025.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00025.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00025.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00025.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00025.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00025.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00025.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00025.safetensors",
+    "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00025.safetensors",
+    "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00025.safetensors",
+    "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00025.safetensors",
+    "model.layers.10.block_sparse_moe.gate.weight": "model-00005-of-00025.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00005-of-00025.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00025.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00025.safetensors",
+    "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00025.safetensors",
+    "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00025.safetensors",
+    "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00025.safetensors",
+    "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00025.safetensors",
+    "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00025.safetensors",
+    "model.layers.11.block_sparse_moe.gate.weight": "model-00005-of-00025.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00006-of-00025.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00025.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00025.safetensors",
+    "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00025.safetensors",
+    "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00025.safetensors",
+    "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00025.safetensors",
+    "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00025.safetensors",
+    "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00025.safetensors",
+    "model.layers.12.block_sparse_moe.gate.weight": "model-00006-of-00025.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00006-of-00025.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00006-of-00025.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00025.safetensors",
+    "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00025.safetensors",
+    "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00025.safetensors",
+    "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00025.safetensors",
+    "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00025.safetensors",
+    "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00025.safetensors",
+    "model.layers.13.block_sparse_moe.gate.weight": "model-00006-of-00025.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00006-of-00025.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00025.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00025.safetensors",
+    "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00025.safetensors",
+    "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00025.safetensors",
+    "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00025.safetensors",
+    "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00025.safetensors",
+    "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00025.safetensors",
+    "model.layers.14.block_sparse_moe.gate.weight": "model-00006-of-00025.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00007-of-00025.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00025.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00025.safetensors",
+    "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00025.safetensors",
+    "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00025.safetensors",
+    "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00025.safetensors",
+    "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00025.safetensors",
+    "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00025.safetensors",
+    "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00025.safetensors",
+    "model.layers.15.block_sparse_moe.gate.weight": "model-00007-of-00025.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00007-of-00025.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00025.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00025.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00025.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00025.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00025.safetensors",
+    "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00025.safetensors",
+    "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00025.safetensors",
+    "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00025.safetensors",
+    "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00025.safetensors",
+    "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00025.safetensors",
+    "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00025.safetensors",
+    "model.layers.16.block_sparse_moe.gate.weight": "model-00007-of-00025.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00008-of-00025.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00025.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00025.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00007-of-00025.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00025.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00025.safetensors",
+    "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00025.safetensors",
+    "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00025.safetensors",
+    "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00025.safetensors",
+    "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00025.safetensors",
+    "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00025.safetensors",
+    "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00025.safetensors",
+    "model.layers.17.block_sparse_moe.gate.weight": "model-00008-of-00025.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00008-of-00025.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00025.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00025.safetensors",
+    "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00025.safetensors",
+    "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00025.safetensors",
+    "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00025.safetensors",
+    "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00025.safetensors",
+    "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00025.safetensors",
+    "model.layers.18.block_sparse_moe.gate.weight": "model-00008-of-00025.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00008-of-00025.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00008-of-00025.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00025.safetensors",
+    "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00025.safetensors",
+    "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00025.safetensors",
+    "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00025.safetensors",
+    "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00025.safetensors",
+    "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00025.safetensors",
+    "model.layers.19.block_sparse_moe.gate.weight": "model-00009-of-00025.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00009-of-00025.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00009-of-00025.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00025.safetensors",
+    "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00025.safetensors",
+    "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00025.safetensors",
+    "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00025.safetensors",
+    "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00025.safetensors",
+    "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00025.safetensors",
+    "model.layers.2.block_sparse_moe.gate.weight": "model-00002-of-00025.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00025.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00025.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00025.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00025.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00025.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00025.safetensors",
+    "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00025.safetensors",
+    "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00025.safetensors",
+    "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00025.safetensors",
+    "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00025.safetensors",
+    "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00025.safetensors",
+    "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00025.safetensors",
+    "model.layers.20.block_sparse_moe.gate.weight": "model-00009-of-00025.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00009-of-00025.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00009-of-00025.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00025.safetensors",
+    "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00025.safetensors",
+    "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00025.safetensors",
+    "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00025.safetensors",
+    "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00025.safetensors",
+    "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00025.safetensors",
+    "model.layers.21.block_sparse_moe.gate.weight": "model-00009-of-00025.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00010-of-00025.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00010-of-00025.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00025.safetensors",
+    "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00025.safetensors",
+    "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00025.safetensors",
+    "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00025.safetensors",
+    "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00025.safetensors",
+    "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00025.safetensors",
+    "model.layers.22.block_sparse_moe.gate.weight": "model-00010-of-00025.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00010-of-00025.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00010-of-00025.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00025.safetensors",
+    "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00025.safetensors",
+    "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00025.safetensors",
+    "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00025.safetensors",
+    "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00025.safetensors",
+    "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00025.safetensors",
+    "model.layers.23.block_sparse_moe.gate.weight": "model-00010-of-00025.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00010-of-00025.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00010-of-00025.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00025.safetensors",
+    "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00025.safetensors",
+    "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00025.safetensors",
+    "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00025.safetensors",
+    "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00025.safetensors",
+    "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00025.safetensors",
+    "model.layers.24.block_sparse_moe.gate.weight": "model-00011-of-00025.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00011-of-00025.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00011-of-00025.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00025.safetensors",
+    "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00025.safetensors",
+    "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00025.safetensors",
+    "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00025.safetensors",
+    "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00025.safetensors",
+    "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00025.safetensors",
+    "model.layers.25.block_sparse_moe.gate.weight": "model-00011-of-00025.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00011-of-00025.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00011-of-00025.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00025.safetensors",
+    "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00025.safetensors",
+    "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00025.safetensors",
+    "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00025.safetensors",
+    "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00025.safetensors",
+    "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00025.safetensors",
+    "model.layers.26.block_sparse_moe.gate.weight": "model-00011-of-00025.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00012-of-00025.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00012-of-00025.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00025.safetensors",
+    "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00025.safetensors",
+    "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00025.safetensors",
+    "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00025.safetensors",
+    "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00025.safetensors",
+    "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00025.safetensors",
+    "model.layers.27.block_sparse_moe.gate.weight": "model-00012-of-00025.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00012-of-00025.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00012-of-00025.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00025.safetensors",
+    "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00025.safetensors",
+    "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00025.safetensors",
+    "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00025.safetensors",
+    "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00025.safetensors",
+    "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00025.safetensors",
+    "model.layers.28.block_sparse_moe.gate.weight": "model-00012-of-00025.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00012-of-00025.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00012-of-00025.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00025.safetensors",
+    "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00025.safetensors",
+    "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00025.safetensors",
+    "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00025.safetensors",
+    "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00025.safetensors",
+    "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00025.safetensors",
+    "model.layers.29.block_sparse_moe.gate.weight": "model-00013-of-00025.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00013-of-00025.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00013-of-00025.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00025.safetensors",
+    "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00025.safetensors",
+    "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00025.safetensors",
+    "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00025.safetensors",
+    "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00025.safetensors",
+    "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00025.safetensors",
+    "model.layers.3.block_sparse_moe.gate.weight": "model-00002-of-00025.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00025.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00025.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00025.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00025.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00025.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00025.safetensors",
+    "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00025.safetensors",
+    "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00025.safetensors",
+    "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00025.safetensors",
+    "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00025.safetensors",
+    "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00025.safetensors",
+    "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00025.safetensors",
+    "model.layers.30.block_sparse_moe.gate.weight": "model-00013-of-00025.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00013-of-00025.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00013-of-00025.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00025.safetensors",
+    "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00025.safetensors",
+    "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00025.safetensors",
+    "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00025.safetensors",
+    "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00025.safetensors",
+    "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00025.safetensors",
+    "model.layers.31.block_sparse_moe.gate.weight": "model-00013-of-00025.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00014-of-00025.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00014-of-00025.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00025.safetensors",
+    "model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00025.safetensors",
+    "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00025.safetensors",
+    "model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00025.safetensors",
+    "model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00025.safetensors",
+    "model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00025.safetensors",
+    "model.layers.32.block_sparse_moe.gate.weight": "model-00014-of-00025.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00014-of-00025.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00014-of-00025.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00025.safetensors",
+    "model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00025.safetensors",
+    "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00025.safetensors",
+    "model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00025.safetensors",
+    "model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00025.safetensors",
+    "model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00025.safetensors",
+    "model.layers.33.block_sparse_moe.gate.weight": "model-00014-of-00025.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00014-of-00025.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00014-of-00025.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00025.safetensors",
+    "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00025.safetensors",
+    "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00025.safetensors",
+    "model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00025.safetensors",
+    "model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00025.safetensors",
+    "model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00025.safetensors",
+    "model.layers.34.block_sparse_moe.gate.weight": "model-00015-of-00025.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00015-of-00025.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00015-of-00025.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00025.safetensors",
+    "model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00025.safetensors",
+    "model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00025.safetensors",
+    "model.layers.35.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00025.safetensors",
+    "model.layers.35.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00025.safetensors",
+    "model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00025.safetensors",
+    "model.layers.35.block_sparse_moe.gate.weight": "model-00015-of-00025.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00015-of-00025.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00015-of-00025.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00025.safetensors",
+    "model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00025.safetensors",
+    "model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00025.safetensors",
+    "model.layers.36.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00025.safetensors",
+    "model.layers.36.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00025.safetensors",
+    "model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00025.safetensors",
+    "model.layers.36.block_sparse_moe.gate.weight": "model-00015-of-00025.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00016-of-00025.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00016-of-00025.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00025.safetensors",
+    "model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00025.safetensors",
+    "model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00025.safetensors",
+    "model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00025.safetensors",
+    "model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00025.safetensors",
+    "model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00025.safetensors",
+    "model.layers.37.block_sparse_moe.gate.weight": "model-00016-of-00025.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00016-of-00025.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00016-of-00025.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00025.safetensors",
+    "model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00025.safetensors",
+    "model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00025.safetensors",
+    "model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00025.safetensors",
+    "model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00025.safetensors",
+    "model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00025.safetensors",
+    "model.layers.38.block_sparse_moe.gate.weight": "model-00016-of-00025.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00016-of-00025.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00016-of-00025.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00025.safetensors",
+    "model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00025.safetensors",
+    "model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00025.safetensors",
+    "model.layers.39.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00025.safetensors",
+    "model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00025.safetensors",
+    "model.layers.39.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00025.safetensors",
+    "model.layers.39.block_sparse_moe.gate.weight": "model-00017-of-00025.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00017-of-00025.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00017-of-00025.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00025.safetensors",
+    "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00025.safetensors",
+    "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00025.safetensors",
+    "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00025.safetensors",
+    "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00025.safetensors",
+    "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00025.safetensors",
+    "model.layers.4.block_sparse_moe.gate.weight": "model-00002-of-00025.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00003-of-00025.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00025.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00025.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00025.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00025.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00025.safetensors",
+    "model.layers.40.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00025.safetensors",
+    "model.layers.40.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00025.safetensors",
+    "model.layers.40.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00025.safetensors",
+    "model.layers.40.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00025.safetensors",
+    "model.layers.40.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00025.safetensors",
+    "model.layers.40.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00025.safetensors",
+    "model.layers.40.block_sparse_moe.gate.weight": "model-00017-of-00025.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00017-of-00025.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00017-of-00025.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.41.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00025.safetensors",
+    "model.layers.41.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00025.safetensors",
+    "model.layers.41.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00025.safetensors",
+    "model.layers.41.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00025.safetensors",
+    "model.layers.41.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00025.safetensors",
+    "model.layers.41.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00025.safetensors",
+    "model.layers.41.block_sparse_moe.gate.weight": "model-00017-of-00025.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00018-of-00025.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00018-of-00025.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.42.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00025.safetensors",
+    "model.layers.42.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00025.safetensors",
+    "model.layers.42.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00025.safetensors",
+    "model.layers.42.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00025.safetensors",
+    "model.layers.42.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00025.safetensors",
+    "model.layers.42.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00025.safetensors",
+    "model.layers.42.block_sparse_moe.gate.weight": "model-00018-of-00025.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00018-of-00025.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00018-of-00025.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.43.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00025.safetensors",
+    "model.layers.43.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00025.safetensors",
+    "model.layers.43.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00025.safetensors",
+    "model.layers.43.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00025.safetensors",
+    "model.layers.43.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00025.safetensors",
+    "model.layers.43.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00025.safetensors",
+    "model.layers.43.block_sparse_moe.gate.weight": "model-00018-of-00025.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00018-of-00025.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00018-of-00025.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.44.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00025.safetensors",
+    "model.layers.44.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00025.safetensors",
+    "model.layers.44.block_sparse_moe.experts.0.w3.weight": "model-00019-of-00025.safetensors",
+    "model.layers.44.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00025.safetensors",
+    "model.layers.44.block_sparse_moe.experts.1.w2.weight": "model-00019-of-00025.safetensors",
+    "model.layers.44.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00025.safetensors",
+    "model.layers.44.block_sparse_moe.gate.weight": "model-00019-of-00025.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00019-of-00025.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00019-of-00025.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.45.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00025.safetensors",
+    "model.layers.45.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00025.safetensors",
+    "model.layers.45.block_sparse_moe.experts.0.w3.weight": "model-00019-of-00025.safetensors",
+    "model.layers.45.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00025.safetensors",
+    "model.layers.45.block_sparse_moe.experts.1.w2.weight": "model-00019-of-00025.safetensors",
+    "model.layers.45.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00025.safetensors",
+    "model.layers.45.block_sparse_moe.gate.weight": "model-00019-of-00025.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00019-of-00025.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00019-of-00025.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.46.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00025.safetensors",
+    "model.layers.46.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00025.safetensors",
+    "model.layers.46.block_sparse_moe.experts.0.w3.weight": "model-00019-of-00025.safetensors",
+    "model.layers.46.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00025.safetensors",
+    "model.layers.46.block_sparse_moe.experts.1.w2.weight": "model-00020-of-00025.safetensors",
+    "model.layers.46.block_sparse_moe.experts.1.w3.weight": "model-00020-of-00025.safetensors",
+    "model.layers.46.block_sparse_moe.gate.weight": "model-00019-of-00025.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00020-of-00025.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00020-of-00025.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.47.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00025.safetensors",
+    "model.layers.47.block_sparse_moe.experts.0.w2.weight": "model-00020-of-00025.safetensors",
+    "model.layers.47.block_sparse_moe.experts.0.w3.weight": "model-00020-of-00025.safetensors",
+    "model.layers.47.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00025.safetensors",
+    "model.layers.47.block_sparse_moe.experts.1.w2.weight": "model-00020-of-00025.safetensors",
+    "model.layers.47.block_sparse_moe.experts.1.w3.weight": "model-00020-of-00025.safetensors",
+    "model.layers.47.block_sparse_moe.gate.weight": "model-00020-of-00025.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00020-of-00025.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00020-of-00025.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.48.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00025.safetensors",
+    "model.layers.48.block_sparse_moe.experts.0.w2.weight": "model-00020-of-00025.safetensors",
+    "model.layers.48.block_sparse_moe.experts.0.w3.weight": "model-00020-of-00025.safetensors",
+    "model.layers.48.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00025.safetensors",
+    "model.layers.48.block_sparse_moe.experts.1.w2.weight": "model-00020-of-00025.safetensors",
+    "model.layers.48.block_sparse_moe.experts.1.w3.weight": "model-00020-of-00025.safetensors",
+    "model.layers.48.block_sparse_moe.gate.weight": "model-00020-of-00025.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00020-of-00025.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00020-of-00025.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.49.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00025.safetensors",
+    "model.layers.49.block_sparse_moe.experts.0.w2.weight": "model-00021-of-00025.safetensors",
+    "model.layers.49.block_sparse_moe.experts.0.w3.weight": "model-00021-of-00025.safetensors",
+    "model.layers.49.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00025.safetensors",
+    "model.layers.49.block_sparse_moe.experts.1.w2.weight": "model-00021-of-00025.safetensors",
+    "model.layers.49.block_sparse_moe.experts.1.w3.weight": "model-00021-of-00025.safetensors",
+    "model.layers.49.block_sparse_moe.gate.weight": "model-00021-of-00025.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00021-of-00025.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00021-of-00025.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00025.safetensors",
+    "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00025.safetensors",
+    "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00025.safetensors",
+    "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00025.safetensors",
+    "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00025.safetensors",
+    "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00025.safetensors",
+    "model.layers.5.block_sparse_moe.gate.weight": "model-00003-of-00025.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00003-of-00025.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00025.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.50.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00025.safetensors",
+    "model.layers.50.block_sparse_moe.experts.0.w2.weight": "model-00021-of-00025.safetensors",
+    "model.layers.50.block_sparse_moe.experts.0.w3.weight": "model-00021-of-00025.safetensors",
+    "model.layers.50.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00025.safetensors",
+    "model.layers.50.block_sparse_moe.experts.1.w2.weight": "model-00021-of-00025.safetensors",
+    "model.layers.50.block_sparse_moe.experts.1.w3.weight": "model-00021-of-00025.safetensors",
+    "model.layers.50.block_sparse_moe.gate.weight": "model-00021-of-00025.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00021-of-00025.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00021-of-00025.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.51.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00025.safetensors",
+    "model.layers.51.block_sparse_moe.experts.0.w2.weight": "model-00021-of-00025.safetensors",
+    "model.layers.51.block_sparse_moe.experts.0.w3.weight": "model-00021-of-00025.safetensors",
+    "model.layers.51.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00025.safetensors",
+    "model.layers.51.block_sparse_moe.experts.1.w2.weight": "model-00022-of-00025.safetensors",
+    "model.layers.51.block_sparse_moe.experts.1.w3.weight": "model-00022-of-00025.safetensors",
+    "model.layers.51.block_sparse_moe.gate.weight": "model-00021-of-00025.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00022-of-00025.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00022-of-00025.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.52.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00025.safetensors",
+    "model.layers.52.block_sparse_moe.experts.0.w2.weight": "model-00022-of-00025.safetensors",
+    "model.layers.52.block_sparse_moe.experts.0.w3.weight": "model-00022-of-00025.safetensors",
+    "model.layers.52.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00025.safetensors",
+    "model.layers.52.block_sparse_moe.experts.1.w2.weight": "model-00022-of-00025.safetensors",
+    "model.layers.52.block_sparse_moe.experts.1.w3.weight": "model-00022-of-00025.safetensors",
+    "model.layers.52.block_sparse_moe.gate.weight": "model-00022-of-00025.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00022-of-00025.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00022-of-00025.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.53.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00025.safetensors",
+    "model.layers.53.block_sparse_moe.experts.0.w2.weight": "model-00022-of-00025.safetensors",
+    "model.layers.53.block_sparse_moe.experts.0.w3.weight": "model-00022-of-00025.safetensors",
+    "model.layers.53.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00025.safetensors",
+    "model.layers.53.block_sparse_moe.experts.1.w2.weight": "model-00022-of-00025.safetensors",
+    "model.layers.53.block_sparse_moe.experts.1.w3.weight": "model-00022-of-00025.safetensors",
+    "model.layers.53.block_sparse_moe.gate.weight": "model-00022-of-00025.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00022-of-00025.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00022-of-00025.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.54.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00025.safetensors",
+    "model.layers.54.block_sparse_moe.experts.0.w2.weight": "model-00023-of-00025.safetensors",
+    "model.layers.54.block_sparse_moe.experts.0.w3.weight": "model-00023-of-00025.safetensors",
+    "model.layers.54.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00025.safetensors",
+    "model.layers.54.block_sparse_moe.experts.1.w2.weight": "model-00023-of-00025.safetensors",
+    "model.layers.54.block_sparse_moe.experts.1.w3.weight": "model-00023-of-00025.safetensors",
+    "model.layers.54.block_sparse_moe.gate.weight": "model-00023-of-00025.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00023-of-00025.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00023-of-00025.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.55.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00025.safetensors",
+    "model.layers.55.block_sparse_moe.experts.0.w2.weight": "model-00023-of-00025.safetensors",
+    "model.layers.55.block_sparse_moe.experts.0.w3.weight": "model-00023-of-00025.safetensors",
+    "model.layers.55.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00025.safetensors",
+    "model.layers.55.block_sparse_moe.experts.1.w2.weight": "model-00023-of-00025.safetensors",
+    "model.layers.55.block_sparse_moe.experts.1.w3.weight": "model-00023-of-00025.safetensors",
+    "model.layers.55.block_sparse_moe.gate.weight": "model-00023-of-00025.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00023-of-00025.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00023-of-00025.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.56.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00025.safetensors",
+    "model.layers.56.block_sparse_moe.experts.0.w2.weight": "model-00023-of-00025.safetensors",
+    "model.layers.56.block_sparse_moe.experts.0.w3.weight": "model-00023-of-00025.safetensors",
+    "model.layers.56.block_sparse_moe.experts.1.w1.weight": "model-00024-of-00025.safetensors",
+    "model.layers.56.block_sparse_moe.experts.1.w2.weight": "model-00024-of-00025.safetensors",
+    "model.layers.56.block_sparse_moe.experts.1.w3.weight": "model-00024-of-00025.safetensors",
+    "model.layers.56.block_sparse_moe.gate.weight": "model-00023-of-00025.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00024-of-00025.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00024-of-00025.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.57.block_sparse_moe.experts.0.w1.weight": "model-00024-of-00025.safetensors",
+    "model.layers.57.block_sparse_moe.experts.0.w2.weight": "model-00024-of-00025.safetensors",
+    "model.layers.57.block_sparse_moe.experts.0.w3.weight": "model-00024-of-00025.safetensors",
+    "model.layers.57.block_sparse_moe.experts.1.w1.weight": "model-00024-of-00025.safetensors",
+    "model.layers.57.block_sparse_moe.experts.1.w2.weight": "model-00024-of-00025.safetensors",
+    "model.layers.57.block_sparse_moe.experts.1.w3.weight": "model-00024-of-00025.safetensors",
+    "model.layers.57.block_sparse_moe.gate.weight": "model-00024-of-00025.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00024-of-00025.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00024-of-00025.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.58.block_sparse_moe.experts.0.w1.weight": "model-00024-of-00025.safetensors",
+    "model.layers.58.block_sparse_moe.experts.0.w2.weight": "model-00024-of-00025.safetensors",
+    "model.layers.58.block_sparse_moe.experts.0.w3.weight": "model-00024-of-00025.safetensors",
+    "model.layers.58.block_sparse_moe.experts.1.w1.weight": "model-00024-of-00025.safetensors",
+    "model.layers.58.block_sparse_moe.experts.1.w2.weight": "model-00024-of-00025.safetensors",
+    "model.layers.58.block_sparse_moe.experts.1.w3.weight": "model-00024-of-00025.safetensors",
+    "model.layers.58.block_sparse_moe.gate.weight": "model-00024-of-00025.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00024-of-00025.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00024-of-00025.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.59.block_sparse_moe.experts.0.w1.weight": "model-00025-of-00025.safetensors",
+    "model.layers.59.block_sparse_moe.experts.0.w2.weight": "model-00025-of-00025.safetensors",
+    "model.layers.59.block_sparse_moe.experts.0.w3.weight": "model-00025-of-00025.safetensors",
+    "model.layers.59.block_sparse_moe.experts.1.w1.weight": "model-00025-of-00025.safetensors",
+    "model.layers.59.block_sparse_moe.experts.1.w2.weight": "model-00025-of-00025.safetensors",
+    "model.layers.59.block_sparse_moe.experts.1.w3.weight": "model-00025-of-00025.safetensors",
+    "model.layers.59.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00025-of-00025.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00025-of-00025.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00025-of-00025.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00025-of-00025.safetensors",
+    "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00025.safetensors",
+    "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00025.safetensors",
+    "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00025.safetensors",
+    "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00025.safetensors",
+    "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00025.safetensors",
+    "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00025.safetensors",
+    "model.layers.6.block_sparse_moe.gate.weight": "model-00003-of-00025.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00004-of-00025.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00025.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00025.safetensors",
+    "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00025.safetensors",
+    "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00025.safetensors",
+    "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00025.safetensors",
+    "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00025.safetensors",
+    "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00025.safetensors",
+    "model.layers.7.block_sparse_moe.gate.weight": "model-00004-of-00025.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00004-of-00025.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00025.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00025.safetensors",
+    "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00025.safetensors",
+    "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00025.safetensors",
+    "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00025.safetensors",
+    "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00025.safetensors",
+    "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00025.safetensors",
+    "model.layers.8.block_sparse_moe.gate.weight": "model-00004-of-00025.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00004-of-00025.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00025.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00025.safetensors",
+    "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00025.safetensors",
+    "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00025.safetensors",
+    "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00025.safetensors",
+    "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00025.safetensors",
+    "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00025.safetensors",
+    "model.layers.9.block_sparse_moe.gate.weight": "model-00004-of-00025.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00005-of-00025.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00025.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00025.safetensors",
+    "model.norm.weight": "model-00025-of-00025.safetensors"
+  }
+}

special_tokens_map.json

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

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
+size 1033105

tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{%- for idx in range(0, messages|length) -%}\n{%- if messages[idx]['role'] == 'user' -%}\n{%- if idx > 1 -%}\n{{- bos_token + '[INST] ' + messages[idx]['content'] + ' [/INST]' -}}\n{%- else -%}\n{{- messages[idx]['content'] + ' [/INST]' -}}\n{%- endif -%}\n{% elif messages[idx]['role'] == 'system' %}\n{{- '[INST] <<SYS>>\\n' + messages[idx]['content'] + '\\n<</SYS>>\\n\\n' -}}\n{%- elif messages[idx]['role'] == 'assistant' -%}\n{{- ' '  + messages[idx]['content'] + ' ' + eos_token -}}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "max_length": null,
+  "model_max_length": 1024,
+  "pad_to_multiple_of": null,
+  "pad_token": "<s>",
+  "pad_token_type_id": 0,
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "stride": 0,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}