Troys Architecture ~ Tri-MoE : With `BlackSheep` Personality that lacks moral judgement. Use it how you will.

added_tokens.json

@@ -0,0 +1,40 @@
+{
+  "<|/code|>": 32014,
+  "<|/data|>": 32033,
+  "<|/inst|>": 32037,
+  "<|/query|>": 32031,
+  "<|/sys|>": 32035,
+  "<|assistant_mask|>": 32017,
+  "<|assistant|>": 32001,
+  "<|calc|>": 32012,
+  "<|code|>": 32013,
+  "<|continue|>": 32009,
+  "<|data|>": 32032,
+  "<|diff_marker|>": 32025,
+  "<|disc_sep|>": 32029,
+  "<|disc_start|>": 32028,
+  "<|disc_thread|><|query|>": 32030,
+  "<|endoftext|>": 32000,
+  "<|end|>": 32007,
+  "<|fim_middle|>": 32021,
+  "<|fim_prefix|>": 32020,
+  "<|fim_suffix|>": 32022,
+  "<|function_call|>": 32005,
+  "<|function_list|>": 32011,
+  "<|function_output|>": 32003,
+  "<|ghissue|>": 32026,
+  "<|ghreview|>": 32027,
+  "<|inst|>": 32036,
+  "<|ipynb_marker|>": 32024,
+  "<|message|>": 32019,
+  "<|meta_start|>": 32023,
+  "<|raw|>": 32008,
+  "<|resource|>": 32016,
+  "<|start|>": 32018,
+  "<|step|>": 32002,
+  "<|summary|>": 32015,
+  "<|system|>": 32006,
+  "<|sys|>": 32034,
+  "<|tag|>": 32004,
+  "<|user|>": 32010
+}

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": ".\\DigitalSoul",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 16384,
+  "mlp_bias": false,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 3,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 32,
+  "num_local_experts": 3,
+  "output_router_logits": false,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.0",
+  "use_cache": false,
+  "vocab_size": 32064
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "transformers_version": "4.44.0",
+  "use_cache": false
+}

pytorch_model-00001-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b3ae275ef4d4d537b45a85befe31bf5c8b6494fc737f80ddecf99810167e240
+size 4991420771

pytorch_model-00002-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e1bdc6c70d0641c15e90fa3f4d5720b08919b0157c53bc171e0092e71998b45
+size 4995766167

pytorch_model-00003-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:873b91f030c9f21032916e0b13c4e3f2f0f30fd95f133be539440928d8e8fca1
+size 4957997958

pytorch_model-00004-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d18de94173b0c3d6e4ec7ea8cd0ee31c1593c1fecbec8a7a6dd78aeda56870c
+size 4983196624

pytorch_model-00005-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bc252986e7c4d2553834a92d9ac37dfb94f279b0efa82f6c4e61057f30ef1fb
+size 1606383024

pytorch_model.bin.index.json

@@ -0,0 +1,650 @@
+{
+  "metadata": {
+    "total_size": 21534529536
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00005-of-00005.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.10.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.16.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.16.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.16.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.16.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.16.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.16.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.16.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.16.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.16.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.16.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.17.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.17.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.17.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.17.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.17.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.17.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.17.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.17.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.17.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.17.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.18.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.18.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.18.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.18.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.18.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.18.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.18.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.18.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.18.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.18.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.19.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.19.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.19.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.19.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.19.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.19.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.19.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.19.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.19.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.19.block_sparse_moe.gate.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.2.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.20.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.20.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.20.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.20.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.20.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.20.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.20.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.20.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.20.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.20.block_sparse_moe.gate.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.block_sparse_moe.gate.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.block_sparse_moe.gate.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.block_sparse_moe.gate.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.block_sparse_moe.gate.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.25.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.25.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.25.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.25.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.25.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.25.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.25.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.25.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.25.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.25.block_sparse_moe.gate.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.26.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.26.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.26.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.26.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.26.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.26.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.26.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.26.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.26.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.26.block_sparse_moe.gate.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.27.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.27.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.27.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.27.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.27.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.27.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.27.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.27.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.27.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.27.block_sparse_moe.gate.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.28.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.28.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.28.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.28.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.28.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.28.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.28.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.28.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.28.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.28.block_sparse_moe.gate.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.29.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.29.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.29.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.29.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.29.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.29.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.29.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.29.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.29.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.29.block_sparse_moe.gate.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.3.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.30.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.30.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.30.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.30.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.30.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.30.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.30.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.30.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.30.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.30.block_sparse_moe.gate.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.31.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.31.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.31.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.31.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.31.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.31.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.31.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.31.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.31.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.31.block_sparse_moe.gate.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.32.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.32.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.32.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.32.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.32.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.32.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.32.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.32.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.32.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.32.block_sparse_moe.gate.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.32.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.33.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.33.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.33.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.33.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.33.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.33.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.33.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.33.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.33.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.33.block_sparse_moe.gate.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.34.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.34.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.34.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.34.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.34.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.34.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.34.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.34.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.34.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.34.block_sparse_moe.gate.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.35.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.35.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.35.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.35.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.35.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.35.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.35.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.35.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.35.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.35.block_sparse_moe.gate.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.36.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.36.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.36.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.36.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.36.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.36.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.36.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.36.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.36.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.36.block_sparse_moe.gate.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.37.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.37.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.37.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.37.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.37.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.37.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.37.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.37.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.37.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.37.block_sparse_moe.gate.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.38.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.38.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.38.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.38.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.38.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.38.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.38.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.38.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.38.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.38.block_sparse_moe.gate.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.39.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.39.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.39.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.39.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.39.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.39.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.39.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.39.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.39.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.39.block_sparse_moe.gate.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.4.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.7.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.7.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.7.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.7.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.7.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.7.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.7.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.7.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.7.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.7.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.8.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.8.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.8.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.8.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.8.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.8.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.8.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.8.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.8.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.8.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.9.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.norm.weight": "pytorch_model-00005-of-00005.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "additional_special_tokens": [
+    "<|/inst|>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": true,
+    "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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,350 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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": true,
+      "single_word": false,
+      "special": false
+    },
+    "32000": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|step|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|function_output|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<|function_call|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<|raw|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<|continue|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32011": {
+      "content": "<|function_list|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32012": {
+      "content": "<|calc|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32013": {
+      "content": "<|code|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "<|/code|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "<|summary|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32016": {
+      "content": "<|resource|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32017": {
+      "content": "<|assistant_mask|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32018": {
+      "content": "<|start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32019": {
+      "content": "<|message|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32020": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32021": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32022": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32023": {
+      "content": "<|meta_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32024": {
+      "content": "<|ipynb_marker|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32025": {
+      "content": "<|diff_marker|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32026": {
+      "content": "<|ghissue|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32027": {
+      "content": "<|ghreview|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32028": {
+      "content": "<|disc_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32029": {
+      "content": "<|disc_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32030": {
+      "content": "<|disc_thread|><|query|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32031": {
+      "content": "<|/query|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32032": {
+      "content": "<|data|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32033": {
+      "content": "<|/data|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32034": {
+      "content": "<|sys|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32035": {
+      "content": "<|/sys|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32036": {
+      "content": "<|inst|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32037": {
+      "content": "<|/inst|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|/inst|>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{{'<|' + message['role'] + '|>' + '\n' + message['content'] + '<|end|>\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|end|>",
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": "<s>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}