Upload MixtralForCausalLM

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "moe_out",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "num_local_experts": 2,
+  "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,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.37.0.dev0"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57becce5941a368dcc12ed4158b88aa8177a791a811b934a3751a013351ba6d0
+size 4998028744

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:462083cbfbbe739ac4af5bea044c438c256841eb430354e33171d7e98771a348
+size 2447625168

model.safetensors.index.json

@@ -0,0 +1,296 @@
+{
+  "metadata": {
+    "total_size": 7445618688
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}