diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..7fb7d5252b1cac0f3f9fda7dd4585dbdf1e9b9ad --- /dev/null +++ b/config.json @@ -0,0 +1,36 @@ +{ + "_name_or_path": "meta-llama/Llama-2-7b-chat-hf", + "adapter_dim": 64, + "architectures": [ + "LlamaForCausalLM" + ], + "auto_map": { + "AutoConfig": "configuration_camelidae.CamelidaeConfig", + "AutoModelForCausalLM": "modeling_camelidae.LlamaForCausalLM" + }, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 11008, + "max_position_embeddings": 4096, + "model_type": "llama", + "moe_dtype": "bfloat16", + "moe_scaling": 0.25, + "num_attention_heads": 32, + "num_clusters": 3, + "num_experts": 8, + "num_hidden_layers": 32, + "num_key_value_heads": 32, + "output_router_logits": false, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "tie_word_embeddings": false, + "topk": 2, + "torch_dtype": "bfloat16", + "transformers_version": "4.34.0.dev0", + "use_cache": true, + "vocab_size": 32000 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..f0e05f0f187266a1a2efc5a860fa46be209cc9af --- /dev/null +++ b/generation_config.json @@ -0,0 +1,10 @@ +{ + "bos_token_id": 1, + "do_sample": true, + "eos_token_id": 2, + "max_length": 4096, + "pad_token_id": 0, + "temperature": 0.6, + "top_p": 0.9, + "transformers_version": "4.34.0.dev0" +} diff --git a/pytorch_model-00001-of-00002.bin b/pytorch_model-00001-of-00002.bin new file mode 100644 index 0000000000000000000000000000000000000000..936f3d23ca387698a3b1e9801546afda09481cf9 --- /dev/null +++ b/pytorch_model-00001-of-00002.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:811235288193e968a1179aa39fc69650d38668512576d3058f2fbd7924e1c30b +size 9949874607 diff --git a/pytorch_model-00002-of-00002.bin b/pytorch_model-00002-of-00002.bin new file mode 100644 index 0000000000000000000000000000000000000000..26ec5649a9dff849af71a067bfab72d05aed9543 --- /dev/null +++ b/pytorch_model-00002-of-00002.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68def78a0d04bef5adcd78e9b80fc18e619c148ae4ae66b075e27783c0f7eea9 +size 4339267066 diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json new file mode 100644 index 0000000000000000000000000000000000000000..ee08330b2a2348715e44709ca57c7e9ecb95932d --- /dev/null +++ b/pytorch_model.bin.index.json @@ -0,0 +1,1930 @@ +{ + "metadata": { + "total_size": 14288429056 + }, + "weight_map": { + "lm_head.weight": "pytorch_model-00002-of-00002.bin", + "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.experts.experts_0_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.experts.experts_0_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.experts.experts_0_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.experts.experts_0_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.experts.experts_0_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.experts.experts_0_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.experts.experts_0_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.experts.experts_0_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.experts.experts_0_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.experts.experts_0_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.experts.experts_0_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.experts.experts_0_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.experts.experts_0_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.experts.experts_0_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.experts.experts_0_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.experts.experts_0_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.experts.experts_1_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.experts.experts_1_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.experts.experts_1_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.experts.experts_1_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.experts.experts_1_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.experts.experts_1_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.experts.experts_1_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.experts.experts_1_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.experts.experts_1_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.experts.experts_1_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.experts.experts_1_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.experts.experts_1_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.experts.experts_1_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.experts.experts_1_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.experts.experts_1_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.experts.experts_1_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.experts.experts_2_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.experts.experts_2_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.experts.experts_2_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.experts.experts_2_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.experts.experts_2_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.experts.experts_2_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.experts.experts_2_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.experts.experts_2_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.experts.experts_2_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.experts.experts_2_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.experts.experts_2_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.experts.experts_2_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.experts.experts_2_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.experts.experts_2_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.experts.experts_2_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.experts.experts_2_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.routers.router_0.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.routers.router_1.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.moe_adapter.routers.router_2.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.experts.experts_0_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.experts.experts_0_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.experts.experts_0_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.experts.experts_0_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.experts.experts_0_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.experts.experts_0_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.experts.experts_0_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.experts.experts_0_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.experts.experts_0_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.experts.experts_0_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.experts.experts_0_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.experts.experts_0_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.experts.experts_0_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.experts.experts_0_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.experts.experts_0_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.experts.experts_0_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.experts.experts_1_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.experts.experts_1_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.experts.experts_1_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.experts.experts_1_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.experts.experts_1_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.experts.experts_1_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.experts.experts_1_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.experts.experts_1_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.experts.experts_1_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.experts.experts_1_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.experts.experts_1_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.experts.experts_1_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.experts.experts_1_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.experts.experts_1_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.experts.experts_1_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.experts.experts_1_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.experts.experts_2_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.experts.experts_2_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.experts.experts_2_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.experts.experts_2_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.experts.experts_2_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.experts.experts_2_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.experts.experts_2_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.experts.experts_2_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.experts.experts_2_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.experts.experts_2_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.experts.experts_2_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.experts.experts_2_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.experts.experts_2_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.experts.experts_2_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.experts.experts_2_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.experts.experts_2_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.routers.router_0.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.routers.router_1.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.moe_adapter.routers.router_2.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.experts.experts_0_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.experts.experts_0_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.experts.experts_0_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.experts.experts_0_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.experts.experts_0_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.experts.experts_0_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.experts.experts_0_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.experts.experts_0_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.experts.experts_0_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.experts.experts_0_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.experts.experts_0_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.experts.experts_0_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.experts.experts_0_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.experts.experts_0_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.experts.experts_0_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.experts.experts_0_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.experts.experts_1_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.experts.experts_1_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.experts.experts_1_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.experts.experts_1_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.experts.experts_1_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.experts.experts_1_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.experts.experts_1_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.experts.experts_1_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.experts.experts_1_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.experts.experts_1_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.experts.experts_1_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.experts.experts_1_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.experts.experts_1_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.experts.experts_1_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.experts.experts_1_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.experts.experts_1_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.experts.experts_2_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.experts.experts_2_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.experts.experts_2_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.experts.experts_2_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.experts.experts_2_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.experts.experts_2_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.experts.experts_2_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.experts.experts_2_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.experts.experts_2_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.experts.experts_2_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.experts.experts_2_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.experts.experts_2_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.experts.experts_2_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.experts.experts_2_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.experts.experts_2_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.experts.experts_2_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.routers.router_0.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.routers.router_1.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.moe_adapter.routers.router_2.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.experts.experts_0_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.experts.experts_0_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.experts.experts_0_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.experts.experts_0_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.experts.experts_0_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.experts.experts_0_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.experts.experts_0_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.experts.experts_0_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.experts.experts_0_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.experts.experts_0_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.experts.experts_0_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.experts.experts_0_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.experts.experts_0_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.experts.experts_0_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.experts.experts_0_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.experts.experts_0_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.experts.experts_1_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.experts.experts_1_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.experts.experts_1_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.experts.experts_1_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.experts.experts_1_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.experts.experts_1_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.experts.experts_1_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.experts.experts_1_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.experts.experts_1_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.experts.experts_1_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.experts.experts_1_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.experts.experts_1_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.experts.experts_1_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.experts.experts_1_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.experts.experts_1_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.experts.experts_1_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.experts.experts_2_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.experts.experts_2_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.experts.experts_2_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.experts.experts_2_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.experts.experts_2_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.experts.experts_2_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.experts.experts_2_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.experts.experts_2_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.experts.experts_2_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.experts.experts_2_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.experts.experts_2_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.experts.experts_2_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.experts.experts_2_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.experts.experts_2_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.experts.experts_2_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.experts.experts_2_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.routers.router_0.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.routers.router_1.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.moe_adapter.routers.router_2.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.experts.experts_0_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.experts.experts_0_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.experts.experts_0_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.experts.experts_0_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.experts.experts_0_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.experts.experts_0_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.experts.experts_0_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.experts.experts_0_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.experts.experts_0_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.experts.experts_0_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.experts.experts_0_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.experts.experts_0_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.experts.experts_0_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.experts.experts_0_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.experts.experts_0_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.experts.experts_0_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.experts.experts_1_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.experts.experts_1_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.experts.experts_1_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.experts.experts_1_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.experts.experts_1_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.experts.experts_1_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.experts.experts_1_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.experts.experts_1_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.experts.experts_1_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.experts.experts_1_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.experts.experts_1_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.experts.experts_1_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.experts.experts_1_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.experts.experts_1_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.experts.experts_1_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.experts.experts_1_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.experts.experts_2_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.experts.experts_2_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.experts.experts_2_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.experts.experts_2_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.experts.experts_2_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.experts.experts_2_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.experts.experts_2_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.experts.experts_2_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.experts.experts_2_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.experts.experts_2_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.experts.experts_2_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.experts.experts_2_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.experts.experts_2_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.experts.experts_2_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.experts.experts_2_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.experts.experts_2_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.routers.router_0.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.routers.router_1.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.moe_adapter.routers.router_2.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.experts.experts_0_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.experts.experts_0_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.experts.experts_0_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.experts.experts_0_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.experts.experts_0_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.experts.experts_0_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.experts.experts_0_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.experts.experts_0_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.experts.experts_0_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.experts.experts_0_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.experts.experts_0_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.experts.experts_0_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.experts.experts_0_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.experts.experts_0_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.experts.experts_0_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.experts.experts_0_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.experts.experts_1_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.experts.experts_1_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.experts.experts_1_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.experts.experts_1_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.experts.experts_1_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.experts.experts_1_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.experts.experts_1_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.experts.experts_1_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.experts.experts_1_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.experts.experts_1_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.experts.experts_1_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.experts.experts_1_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.experts.experts_1_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.experts.experts_1_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.experts.experts_1_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.experts.experts_1_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.experts.experts_2_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.experts.experts_2_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.experts.experts_2_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.experts.experts_2_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.experts.experts_2_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.experts.experts_2_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.experts.experts_2_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.experts.experts_2_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.experts.experts_2_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.experts.experts_2_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.experts.experts_2_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.experts.experts_2_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.experts.experts_2_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.experts.experts_2_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.experts.experts_2_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.experts.experts_2_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.routers.router_0.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.routers.router_1.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.moe_adapter.routers.router_2.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.experts.experts_0_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.experts.experts_0_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.experts.experts_0_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.experts.experts_0_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.experts.experts_0_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.experts.experts_0_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.experts.experts_0_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.experts.experts_0_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.experts.experts_0_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.experts.experts_0_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.experts.experts_0_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.experts.experts_0_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.experts.experts_0_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.experts.experts_0_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.experts.experts_0_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.experts.experts_0_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.experts.experts_1_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.experts.experts_1_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.experts.experts_1_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.experts.experts_1_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.experts.experts_1_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.experts.experts_1_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.experts.experts_1_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.experts.experts_1_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.experts.experts_1_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.experts.experts_1_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.experts.experts_1_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.experts.experts_1_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.experts.experts_1_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.experts.experts_1_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.experts.experts_1_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.experts.experts_1_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.experts.experts_2_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.experts.experts_2_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.experts.experts_2_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.experts.experts_2_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.experts.experts_2_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.experts.experts_2_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.experts.experts_2_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.experts.experts_2_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.experts.experts_2_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.experts.experts_2_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.experts.experts_2_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.experts.experts_2_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.experts.experts_2_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.experts.experts_2_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.experts.experts_2_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.experts.experts_2_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.routers.router_0.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.routers.router_1.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.moe_adapter.routers.router_2.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.experts.experts_0_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.experts.experts_0_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.experts.experts_0_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.experts.experts_0_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.experts.experts_0_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.experts.experts_0_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.experts.experts_0_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.experts.experts_0_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.experts.experts_0_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.experts.experts_0_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.experts.experts_0_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.experts.experts_0_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.experts.experts_0_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.experts.experts_0_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.experts.experts_0_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.experts.experts_0_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.experts.experts_1_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.experts.experts_1_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.experts.experts_1_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.experts.experts_1_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.experts.experts_1_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.experts.experts_1_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.experts.experts_1_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.experts.experts_1_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.experts.experts_1_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.experts.experts_1_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.experts.experts_1_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.experts.experts_1_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.experts.experts_1_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.experts.experts_1_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.experts.experts_1_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.experts.experts_1_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.experts.experts_2_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.experts.experts_2_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.experts.experts_2_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.experts.experts_2_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.experts.experts_2_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.experts.experts_2_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.experts.experts_2_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.experts.experts_2_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.experts.experts_2_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.experts.experts_2_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.experts.experts_2_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.experts.experts_2_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.experts.experts_2_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.experts.experts_2_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.experts.experts_2_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.experts.experts_2_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.routers.router_0.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.routers.router_1.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.moe_adapter.routers.router_2.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.experts.experts_0_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.experts.experts_0_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.experts.experts_0_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.experts.experts_0_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.experts.experts_0_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.experts.experts_0_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.experts.experts_0_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.experts.experts_0_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.experts.experts_0_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.experts.experts_0_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.experts.experts_0_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.experts.experts_0_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.experts.experts_0_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.experts.experts_0_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.experts.experts_0_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.experts.experts_0_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.experts.experts_1_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.experts.experts_1_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.experts.experts_1_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.experts.experts_1_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.experts.experts_1_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.experts.experts_1_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.experts.experts_1_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.experts.experts_1_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.experts.experts_1_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.experts.experts_1_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.experts.experts_1_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.experts.experts_1_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.experts.experts_1_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.experts.experts_1_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.experts.experts_1_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.experts.experts_1_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.experts.experts_2_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.experts.experts_2_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.experts.experts_2_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.experts.experts_2_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.experts.experts_2_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.experts.experts_2_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.experts.experts_2_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.experts.experts_2_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.experts.experts_2_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.experts.experts_2_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.experts.experts_2_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.experts.experts_2_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.experts.experts_2_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.experts.experts_2_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.experts.experts_2_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.experts.experts_2_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.routers.router_0.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.routers.router_1.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.moe_adapter.routers.router_2.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.experts.experts_0_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.experts.experts_0_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.experts.experts_0_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.experts.experts_0_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.experts.experts_0_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.experts.experts_0_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.experts.experts_0_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.experts.experts_0_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.experts.experts_0_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.experts.experts_0_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.experts.experts_0_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.experts.experts_0_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.experts.experts_0_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.experts.experts_0_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.experts.experts_0_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.experts.experts_0_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.experts.experts_1_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.experts.experts_1_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.experts.experts_1_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.experts.experts_1_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.experts.experts_1_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.experts.experts_1_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.experts.experts_1_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.experts.experts_1_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.experts.experts_1_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.experts.experts_1_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.experts.experts_1_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.experts.experts_1_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.experts.experts_1_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.experts.experts_1_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.experts.experts_1_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.experts.experts_1_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.experts.experts_2_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.experts.experts_2_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.experts.experts_2_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.experts.experts_2_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.experts.experts_2_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.experts.experts_2_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.experts.experts_2_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.experts.experts_2_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.experts.experts_2_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.experts.experts_2_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.experts.experts_2_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.experts.experts_2_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.experts.experts_2_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.experts.experts_2_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.experts.experts_2_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.experts.experts_2_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.routers.router_0.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.routers.router_1.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.moe_adapter.routers.router_2.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.experts.experts_0_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.experts.experts_0_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.experts.experts_0_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.experts.experts_0_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.experts.experts_0_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.experts.experts_0_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.experts.experts_0_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.experts.experts_0_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.experts.experts_0_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.experts.experts_0_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.experts.experts_0_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.experts.experts_0_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.experts.experts_0_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.experts.experts_0_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.experts.experts_0_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.experts.experts_0_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.experts.experts_1_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.experts.experts_1_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.experts.experts_1_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.experts.experts_1_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.experts.experts_1_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.experts.experts_1_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.experts.experts_1_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.experts.experts_1_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.experts.experts_1_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.experts.experts_1_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.experts.experts_1_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.experts.experts_1_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.experts.experts_1_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.experts.experts_1_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.experts.experts_1_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.experts.experts_1_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.experts.experts_2_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.experts.experts_2_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.experts.experts_2_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.experts.experts_2_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.experts.experts_2_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.experts.experts_2_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.experts.experts_2_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.experts.experts_2_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.experts.experts_2_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.experts.experts_2_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.experts.experts_2_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.experts.experts_2_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.experts.experts_2_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.experts.experts_2_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.experts.experts_2_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.experts.experts_2_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.routers.router_0.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.routers.router_1.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.moe_adapter.routers.router_2.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.experts.experts_0_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.experts.experts_0_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.experts.experts_0_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.experts.experts_0_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.experts.experts_0_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.experts.experts_0_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.experts.experts_0_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.experts.experts_0_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.experts.experts_0_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.experts.experts_0_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.experts.experts_0_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.experts.experts_0_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.experts.experts_0_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.experts.experts_0_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.experts.experts_0_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.experts.experts_0_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.experts.experts_1_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.experts.experts_1_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.experts.experts_1_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.experts.experts_1_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.experts.experts_1_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.experts.experts_1_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.experts.experts_1_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.experts.experts_1_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.experts.experts_1_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.experts.experts_1_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.experts.experts_1_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.experts.experts_1_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.experts.experts_1_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.experts.experts_1_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.experts.experts_1_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.experts.experts_1_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.experts.experts_2_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.experts.experts_2_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.experts.experts_2_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.experts.experts_2_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.experts.experts_2_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.experts.experts_2_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.experts.experts_2_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.experts.experts_2_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.experts.experts_2_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.experts.experts_2_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.experts.experts_2_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.experts.experts_2_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.experts.experts_2_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.experts.experts_2_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.experts.experts_2_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.experts.experts_2_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.routers.router_0.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.routers.router_1.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.moe_adapter.routers.router_2.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.experts.experts_0_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.experts.experts_0_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.experts.experts_0_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.experts.experts_0_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.experts.experts_0_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.experts.experts_0_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.experts.experts_0_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.experts.experts_0_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.experts.experts_0_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.experts.experts_0_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.experts.experts_0_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.experts.experts_0_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.experts.experts_0_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.experts.experts_0_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.experts.experts_0_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.experts.experts_0_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.experts.experts_1_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.experts.experts_1_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.experts.experts_1_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.experts.experts_1_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.experts.experts_1_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.experts.experts_1_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.experts.experts_1_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.experts.experts_1_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.experts.experts_1_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.experts.experts_1_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.experts.experts_1_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.experts.experts_1_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.experts.experts_1_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.experts.experts_1_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.experts.experts_1_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.experts.experts_1_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.experts.experts_2_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.experts.experts_2_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.experts.experts_2_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.experts.experts_2_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.experts.experts_2_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.experts.experts_2_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.experts.experts_2_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.experts.experts_2_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.experts.experts_2_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.experts.experts_2_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.experts.experts_2_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.experts.experts_2_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.experts.experts_2_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.experts.experts_2_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.experts.experts_2_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.experts.experts_2_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.routers.router_0.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.routers.router_1.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.moe_adapter.routers.router_2.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.experts.experts_0_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.experts.experts_0_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.experts.experts_0_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.experts.experts_0_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.experts.experts_0_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.experts.experts_0_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.experts.experts_0_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.experts.experts_0_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.experts.experts_0_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.experts.experts_0_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.experts.experts_0_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.experts.experts_0_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.experts.experts_0_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.experts.experts_0_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.experts.experts_0_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.experts.experts_0_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.experts.experts_1_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.experts.experts_1_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.experts.experts_1_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.experts.experts_1_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.experts.experts_1_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.experts.experts_1_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.experts.experts_1_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.experts.experts_1_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.experts.experts_1_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.experts.experts_1_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.experts.experts_1_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.experts.experts_1_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.experts.experts_1_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.experts.experts_1_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.experts.experts_1_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.experts.experts_1_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.experts.experts_2_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.experts.experts_2_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.experts.experts_2_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.experts.experts_2_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.experts.experts_2_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.experts.experts_2_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.experts.experts_2_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.experts.experts_2_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.experts.experts_2_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.experts.experts_2_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.experts.experts_2_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.experts.experts_2_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.experts.experts_2_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.experts.experts_2_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.experts.experts_2_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.experts.experts_2_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.routers.router_0.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.routers.router_1.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.moe_adapter.routers.router_2.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.experts.experts_0_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.experts.experts_0_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.experts.experts_0_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.experts.experts_0_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.experts.experts_0_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.experts.experts_0_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.experts.experts_0_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.experts.experts_0_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.experts.experts_0_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.experts.experts_0_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.experts.experts_0_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.experts.experts_0_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.experts.experts_0_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.experts.experts_0_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.experts.experts_0_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.experts.experts_0_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.experts.experts_1_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.experts.experts_1_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.experts.experts_1_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.experts.experts_1_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.experts.experts_1_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.experts.experts_1_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.experts.experts_1_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.experts.experts_1_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.experts.experts_1_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.experts.experts_1_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.experts.experts_1_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.experts.experts_1_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.experts.experts_1_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.experts.experts_1_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.experts.experts_1_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.experts.experts_1_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.experts.experts_2_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.experts.experts_2_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.experts.experts_2_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.experts.experts_2_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.experts.experts_2_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.experts.experts_2_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.experts.experts_2_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.experts.experts_2_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.experts.experts_2_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.experts.experts_2_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.experts.experts_2_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.experts.experts_2_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.experts.experts_2_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.experts.experts_2_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.experts.experts_2_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.experts.experts_2_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.routers.router_0.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.routers.router_1.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.moe_adapter.routers.router_2.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.22.mlp.moe_adapter.experts.experts_0_0.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.moe_adapter.experts.experts_0_0.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.moe_adapter.experts.experts_0_1.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.moe_adapter.experts.experts_0_1.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.moe_adapter.experts.experts_0_2.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.moe_adapter.experts.experts_0_2.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.moe_adapter.experts.experts_0_3.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.moe_adapter.experts.experts_0_3.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.moe_adapter.experts.experts_0_4.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.moe_adapter.experts.experts_0_4.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.moe_adapter.experts.experts_0_5.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.moe_adapter.experts.experts_0_5.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.moe_adapter.experts.experts_0_6.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.moe_adapter.experts.experts_0_6.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.moe_adapter.experts.experts_0_7.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.moe_adapter.experts.experts_0_7.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.moe_adapter.experts.experts_1_0.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.moe_adapter.experts.experts_1_0.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.moe_adapter.experts.experts_1_1.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.moe_adapter.experts.experts_1_1.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.moe_adapter.experts.experts_1_2.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.moe_adapter.experts.experts_1_2.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.moe_adapter.experts.experts_1_3.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.moe_adapter.experts.experts_1_3.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.moe_adapter.experts.experts_1_4.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.moe_adapter.experts.experts_1_4.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.moe_adapter.experts.experts_1_5.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.moe_adapter.experts.experts_1_5.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.moe_adapter.experts.experts_1_6.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.moe_adapter.experts.experts_1_6.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.moe_adapter.experts.experts_1_7.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.moe_adapter.experts.experts_1_7.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.moe_adapter.experts.experts_2_0.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.moe_adapter.experts.experts_2_0.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.moe_adapter.experts.experts_2_1.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.moe_adapter.experts.experts_2_1.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.moe_adapter.experts.experts_2_2.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.moe_adapter.experts.experts_2_2.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.moe_adapter.experts.experts_2_3.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.moe_adapter.experts.experts_2_3.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.moe_adapter.experts.experts_2_4.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.moe_adapter.experts.experts_2_4.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.moe_adapter.experts.experts_2_5.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.moe_adapter.experts.experts_2_5.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.moe_adapter.experts.experts_2_6.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.moe_adapter.experts.experts_2_6.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.moe_adapter.experts.experts_2_7.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.moe_adapter.experts.experts_2_7.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.moe_adapter.routers.router_0.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.moe_adapter.routers.router_1.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.moe_adapter.routers.router_2.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.experts.experts_0_0.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.experts.experts_0_0.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.experts.experts_0_1.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.experts.experts_0_1.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.experts.experts_0_2.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.experts.experts_0_2.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.experts.experts_0_3.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.experts.experts_0_3.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.experts.experts_0_4.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.experts.experts_0_4.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.experts.experts_0_5.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.experts.experts_0_5.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.experts.experts_0_6.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.experts.experts_0_6.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.experts.experts_0_7.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.experts.experts_0_7.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.experts.experts_1_0.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.experts.experts_1_0.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.experts.experts_1_1.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.experts.experts_1_1.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.experts.experts_1_2.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.experts.experts_1_2.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.experts.experts_1_3.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.experts.experts_1_3.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.experts.experts_1_4.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.experts.experts_1_4.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.experts.experts_1_5.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.experts.experts_1_5.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.experts.experts_1_6.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.experts.experts_1_6.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.experts.experts_1_7.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.experts.experts_1_7.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.experts.experts_2_0.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.experts.experts_2_0.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.experts.experts_2_1.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.experts.experts_2_1.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.experts.experts_2_2.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.experts.experts_2_2.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.experts.experts_2_3.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.experts.experts_2_3.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.experts.experts_2_4.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.experts.experts_2_4.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.experts.experts_2_5.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.experts.experts_2_5.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.experts.experts_2_6.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.experts.experts_2_6.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.experts.experts_2_7.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.experts.experts_2_7.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.routers.router_0.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.routers.router_1.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.moe_adapter.routers.router_2.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.experts.experts_0_0.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.experts.experts_0_0.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.experts.experts_0_1.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.experts.experts_0_1.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.experts.experts_0_2.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.experts.experts_0_2.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.experts.experts_0_3.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.experts.experts_0_3.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.experts.experts_0_4.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.experts.experts_0_4.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.experts.experts_0_5.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.experts.experts_0_5.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.experts.experts_0_6.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.experts.experts_0_6.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.experts.experts_0_7.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.experts.experts_0_7.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.experts.experts_1_0.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.experts.experts_1_0.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.experts.experts_1_1.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.experts.experts_1_1.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.experts.experts_1_2.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.experts.experts_1_2.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.experts.experts_1_3.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.experts.experts_1_3.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.experts.experts_1_4.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.experts.experts_1_4.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.experts.experts_1_5.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.experts.experts_1_5.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.experts.experts_1_6.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.experts.experts_1_6.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.experts.experts_1_7.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.experts.experts_1_7.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.experts.experts_2_0.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.experts.experts_2_0.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.experts.experts_2_1.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.experts.experts_2_1.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.experts.experts_2_2.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.experts.experts_2_2.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.experts.experts_2_3.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.experts.experts_2_3.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.experts.experts_2_4.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.experts.experts_2_4.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.experts.experts_2_5.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.experts.experts_2_5.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.experts.experts_2_6.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.experts.experts_2_6.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.experts.experts_2_7.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.experts.experts_2_7.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.routers.router_0.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.routers.router_1.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.moe_adapter.routers.router_2.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.experts.experts_0_0.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.experts.experts_0_0.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.experts.experts_0_1.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.experts.experts_0_1.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.experts.experts_0_2.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.experts.experts_0_2.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.experts.experts_0_3.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.experts.experts_0_3.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.experts.experts_0_4.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.experts.experts_0_4.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.experts.experts_0_5.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.experts.experts_0_5.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.experts.experts_0_6.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.experts.experts_0_6.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.experts.experts_0_7.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.experts.experts_0_7.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.experts.experts_1_0.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.experts.experts_1_0.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.experts.experts_1_1.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.experts.experts_1_1.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.experts.experts_1_2.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.experts.experts_1_2.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.experts.experts_1_3.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.experts.experts_1_3.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.experts.experts_1_4.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.experts.experts_1_4.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.experts.experts_1_5.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.experts.experts_1_5.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.experts.experts_1_6.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.experts.experts_1_6.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.experts.experts_1_7.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.experts.experts_1_7.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.experts.experts_2_0.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.experts.experts_2_0.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.experts.experts_2_1.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.experts.experts_2_1.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.experts.experts_2_2.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.experts.experts_2_2.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.experts.experts_2_3.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.experts.experts_2_3.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.experts.experts_2_4.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.experts.experts_2_4.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.experts.experts_2_5.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.experts.experts_2_5.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.experts.experts_2_6.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.experts.experts_2_6.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.experts.experts_2_7.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.experts.experts_2_7.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.routers.router_0.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.routers.router_1.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.moe_adapter.routers.router_2.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.experts.experts_0_0.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.experts.experts_0_0.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.experts.experts_0_1.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.experts.experts_0_1.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.experts.experts_0_2.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.experts.experts_0_2.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.experts.experts_0_3.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.experts.experts_0_3.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.experts.experts_0_4.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.experts.experts_0_4.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.experts.experts_0_5.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.experts.experts_0_5.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.experts.experts_0_6.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.experts.experts_0_6.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.experts.experts_0_7.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.experts.experts_0_7.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.experts.experts_1_0.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.experts.experts_1_0.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.experts.experts_1_1.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.experts.experts_1_1.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.experts.experts_1_2.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.experts.experts_1_2.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.experts.experts_1_3.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.experts.experts_1_3.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.experts.experts_1_4.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.experts.experts_1_4.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.experts.experts_1_5.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.experts.experts_1_5.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.experts.experts_1_6.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.experts.experts_1_6.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.experts.experts_1_7.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.experts.experts_1_7.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.experts.experts_2_0.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.experts.experts_2_0.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.experts.experts_2_1.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.experts.experts_2_1.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.experts.experts_2_2.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.experts.experts_2_2.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.experts.experts_2_3.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.experts.experts_2_3.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.experts.experts_2_4.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.experts.experts_2_4.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.experts.experts_2_5.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.experts.experts_2_5.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.experts.experts_2_6.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.experts.experts_2_6.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.experts.experts_2_7.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.experts.experts_2_7.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.routers.router_0.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.routers.router_1.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.moe_adapter.routers.router_2.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.experts.experts_0_0.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.experts.experts_0_0.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.experts.experts_0_1.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.experts.experts_0_1.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.experts.experts_0_2.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.experts.experts_0_2.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.experts.experts_0_3.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.experts.experts_0_3.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.experts.experts_0_4.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.experts.experts_0_4.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.experts.experts_0_5.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.experts.experts_0_5.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.experts.experts_0_6.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.experts.experts_0_6.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.experts.experts_0_7.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.experts.experts_0_7.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.experts.experts_1_0.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.experts.experts_1_0.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.experts.experts_1_1.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.experts.experts_1_1.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.experts.experts_1_2.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.experts.experts_1_2.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.experts.experts_1_3.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.experts.experts_1_3.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.experts.experts_1_4.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.experts.experts_1_4.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.experts.experts_1_5.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.experts.experts_1_5.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.experts.experts_1_6.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.experts.experts_1_6.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.experts.experts_1_7.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.experts.experts_1_7.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.experts.experts_2_0.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.experts.experts_2_0.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.experts.experts_2_1.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.experts.experts_2_1.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.experts.experts_2_2.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.experts.experts_2_2.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.experts.experts_2_3.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.experts.experts_2_3.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.experts.experts_2_4.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.experts.experts_2_4.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.experts.experts_2_5.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.experts.experts_2_5.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.experts.experts_2_6.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.experts.experts_2_6.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.experts.experts_2_7.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.experts.experts_2_7.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.routers.router_0.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.routers.router_1.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.moe_adapter.routers.router_2.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.experts.experts_0_0.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.experts.experts_0_0.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.experts.experts_0_1.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.experts.experts_0_1.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.experts.experts_0_2.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.experts.experts_0_2.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.experts.experts_0_3.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.experts.experts_0_3.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.experts.experts_0_4.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.experts.experts_0_4.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.experts.experts_0_5.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.experts.experts_0_5.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.experts.experts_0_6.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.experts.experts_0_6.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.experts.experts_0_7.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.experts.experts_0_7.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.experts.experts_1_0.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.experts.experts_1_0.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.experts.experts_1_1.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.experts.experts_1_1.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.experts.experts_1_2.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.experts.experts_1_2.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.experts.experts_1_3.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.experts.experts_1_3.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.experts.experts_1_4.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.experts.experts_1_4.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.experts.experts_1_5.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.experts.experts_1_5.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.experts.experts_1_6.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.experts.experts_1_6.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.experts.experts_1_7.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.experts.experts_1_7.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.experts.experts_2_0.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.experts.experts_2_0.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.experts.experts_2_1.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.experts.experts_2_1.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.experts.experts_2_2.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.experts.experts_2_2.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.experts.experts_2_3.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.experts.experts_2_3.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.experts.experts_2_4.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.experts.experts_2_4.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.experts.experts_2_5.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.experts.experts_2_5.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.experts.experts_2_6.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.experts.experts_2_6.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.experts.experts_2_7.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.experts.experts_2_7.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.routers.router_0.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.routers.router_1.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.moe_adapter.routers.router_2.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.experts.experts_0_0.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.experts.experts_0_0.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.experts.experts_0_1.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.experts.experts_0_1.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.experts.experts_0_2.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.experts.experts_0_2.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.experts.experts_0_3.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.experts.experts_0_3.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.experts.experts_0_4.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.experts.experts_0_4.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.experts.experts_0_5.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.experts.experts_0_5.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.experts.experts_0_6.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.experts.experts_0_6.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.experts.experts_0_7.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.experts.experts_0_7.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.experts.experts_1_0.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.experts.experts_1_0.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.experts.experts_1_1.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.experts.experts_1_1.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.experts.experts_1_2.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.experts.experts_1_2.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.experts.experts_1_3.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.experts.experts_1_3.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.experts.experts_1_4.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.experts.experts_1_4.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.experts.experts_1_5.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.experts.experts_1_5.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.experts.experts_1_6.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.experts.experts_1_6.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.experts.experts_1_7.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.experts.experts_1_7.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.experts.experts_2_0.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.experts.experts_2_0.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.experts.experts_2_1.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.experts.experts_2_1.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.experts.experts_2_2.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.experts.experts_2_2.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.experts.experts_2_3.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.experts.experts_2_3.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.experts.experts_2_4.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.experts.experts_2_4.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.experts.experts_2_5.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.experts.experts_2_5.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.experts.experts_2_6.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.experts.experts_2_6.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.experts.experts_2_7.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.experts.experts_2_7.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.routers.router_0.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.routers.router_1.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.moe_adapter.routers.router_2.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.experts.experts_0_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.experts.experts_0_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.experts.experts_0_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.experts.experts_0_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.experts.experts_0_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.experts.experts_0_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.experts.experts_0_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.experts.experts_0_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.experts.experts_0_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.experts.experts_0_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.experts.experts_0_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.experts.experts_0_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.experts.experts_0_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.experts.experts_0_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.experts.experts_0_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.experts.experts_0_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.experts.experts_1_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.experts.experts_1_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.experts.experts_1_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.experts.experts_1_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.experts.experts_1_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.experts.experts_1_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.experts.experts_1_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.experts.experts_1_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.experts.experts_1_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.experts.experts_1_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.experts.experts_1_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.experts.experts_1_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.experts.experts_1_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.experts.experts_1_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.experts.experts_1_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.experts.experts_1_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.experts.experts_2_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.experts.experts_2_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.experts.experts_2_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.experts.experts_2_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.experts.experts_2_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.experts.experts_2_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.experts.experts_2_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.experts.experts_2_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.experts.experts_2_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.experts.experts_2_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.experts.experts_2_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.experts.experts_2_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.experts.experts_2_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.experts.experts_2_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.experts.experts_2_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.experts.experts_2_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.routers.router_0.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.routers.router_1.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.moe_adapter.routers.router_2.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.experts.experts_0_0.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.experts.experts_0_0.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.experts.experts_0_1.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.experts.experts_0_1.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.experts.experts_0_2.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.experts.experts_0_2.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.experts.experts_0_3.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.experts.experts_0_3.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.experts.experts_0_4.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.experts.experts_0_4.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.experts.experts_0_5.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.experts.experts_0_5.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.experts.experts_0_6.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.experts.experts_0_6.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.experts.experts_0_7.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.experts.experts_0_7.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.experts.experts_1_0.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.experts.experts_1_0.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.experts.experts_1_1.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.experts.experts_1_1.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.experts.experts_1_2.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.experts.experts_1_2.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.experts.experts_1_3.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.experts.experts_1_3.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.experts.experts_1_4.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.experts.experts_1_4.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.experts.experts_1_5.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.experts.experts_1_5.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.experts.experts_1_6.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.experts.experts_1_6.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.experts.experts_1_7.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.experts.experts_1_7.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.experts.experts_2_0.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.experts.experts_2_0.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.experts.experts_2_1.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.experts.experts_2_1.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.experts.experts_2_2.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.experts.experts_2_2.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.experts.experts_2_3.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.experts.experts_2_3.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.experts.experts_2_4.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.experts.experts_2_4.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.experts.experts_2_5.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.experts.experts_2_5.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.experts.experts_2_6.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.experts.experts_2_6.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.experts.experts_2_7.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.experts.experts_2_7.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.routers.router_0.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.routers.router_1.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.moe_adapter.routers.router_2.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.experts.experts_0_0.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.experts.experts_0_0.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.experts.experts_0_1.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.experts.experts_0_1.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.experts.experts_0_2.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.experts.experts_0_2.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.experts.experts_0_3.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.experts.experts_0_3.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.experts.experts_0_4.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.experts.experts_0_4.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.experts.experts_0_5.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.experts.experts_0_5.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.experts.experts_0_6.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.experts.experts_0_6.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.experts.experts_0_7.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.experts.experts_0_7.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.experts.experts_1_0.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.experts.experts_1_0.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.experts.experts_1_1.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.experts.experts_1_1.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.experts.experts_1_2.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.experts.experts_1_2.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.experts.experts_1_3.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.experts.experts_1_3.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.experts.experts_1_4.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.experts.experts_1_4.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.experts.experts_1_5.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.experts.experts_1_5.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.experts.experts_1_6.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.experts.experts_1_6.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.experts.experts_1_7.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.experts.experts_1_7.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.experts.experts_2_0.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.experts.experts_2_0.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.experts.experts_2_1.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.experts.experts_2_1.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.experts.experts_2_2.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.experts.experts_2_2.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.experts.experts_2_3.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.experts.experts_2_3.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.experts.experts_2_4.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.experts.experts_2_4.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.experts.experts_2_5.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.experts.experts_2_5.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.experts.experts_2_6.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.experts.experts_2_6.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.experts.experts_2_7.adapter_down.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.experts.experts_2_7.adapter_up.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.routers.router_0.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.routers.router_1.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.moe_adapter.routers.router_2.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.experts.experts_0_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.experts.experts_0_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.experts.experts_0_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.experts.experts_0_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.experts.experts_0_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.experts.experts_0_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.experts.experts_0_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.experts.experts_0_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.experts.experts_0_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.experts.experts_0_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.experts.experts_0_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.experts.experts_0_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.experts.experts_0_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.experts.experts_0_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.experts.experts_0_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.experts.experts_0_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.experts.experts_1_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.experts.experts_1_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.experts.experts_1_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.experts.experts_1_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.experts.experts_1_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.experts.experts_1_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.experts.experts_1_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.experts.experts_1_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.experts.experts_1_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.experts.experts_1_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.experts.experts_1_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.experts.experts_1_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.experts.experts_1_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.experts.experts_1_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.experts.experts_1_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.experts.experts_1_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.experts.experts_2_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.experts.experts_2_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.experts.experts_2_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.experts.experts_2_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.experts.experts_2_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.experts.experts_2_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.experts.experts_2_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.experts.experts_2_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.experts.experts_2_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.experts.experts_2_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.experts.experts_2_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.experts.experts_2_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.experts.experts_2_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.experts.experts_2_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.experts.experts_2_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.experts.experts_2_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.routers.router_0.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.routers.router_1.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.moe_adapter.routers.router_2.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.experts.experts_0_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.experts.experts_0_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.experts.experts_0_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.experts.experts_0_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.experts.experts_0_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.experts.experts_0_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.experts.experts_0_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.experts.experts_0_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.experts.experts_0_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.experts.experts_0_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.experts.experts_0_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.experts.experts_0_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.experts.experts_0_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.experts.experts_0_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.experts.experts_0_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.experts.experts_0_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.experts.experts_1_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.experts.experts_1_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.experts.experts_1_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.experts.experts_1_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.experts.experts_1_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.experts.experts_1_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.experts.experts_1_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.experts.experts_1_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.experts.experts_1_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.experts.experts_1_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.experts.experts_1_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.experts.experts_1_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.experts.experts_1_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.experts.experts_1_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.experts.experts_1_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.experts.experts_1_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.experts.experts_2_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.experts.experts_2_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.experts.experts_2_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.experts.experts_2_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.experts.experts_2_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.experts.experts_2_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.experts.experts_2_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.experts.experts_2_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.experts.experts_2_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.experts.experts_2_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.experts.experts_2_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.experts.experts_2_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.experts.experts_2_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.experts.experts_2_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.experts.experts_2_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.experts.experts_2_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.routers.router_0.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.routers.router_1.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.moe_adapter.routers.router_2.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.experts.experts_0_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.experts.experts_0_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.experts.experts_0_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.experts.experts_0_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.experts.experts_0_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.experts.experts_0_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.experts.experts_0_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.experts.experts_0_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.experts.experts_0_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.experts.experts_0_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.experts.experts_0_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.experts.experts_0_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.experts.experts_0_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.experts.experts_0_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.experts.experts_0_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.experts.experts_0_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.experts.experts_1_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.experts.experts_1_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.experts.experts_1_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.experts.experts_1_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.experts.experts_1_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.experts.experts_1_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.experts.experts_1_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.experts.experts_1_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.experts.experts_1_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.experts.experts_1_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.experts.experts_1_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.experts.experts_1_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.experts.experts_1_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.experts.experts_1_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.experts.experts_1_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.experts.experts_1_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.experts.experts_2_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.experts.experts_2_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.experts.experts_2_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.experts.experts_2_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.experts.experts_2_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.experts.experts_2_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.experts.experts_2_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.experts.experts_2_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.experts.experts_2_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.experts.experts_2_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.experts.experts_2_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.experts.experts_2_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.experts.experts_2_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.experts.experts_2_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.experts.experts_2_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.experts.experts_2_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.routers.router_0.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.routers.router_1.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.moe_adapter.routers.router_2.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.experts.experts_0_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.experts.experts_0_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.experts.experts_0_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.experts.experts_0_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.experts.experts_0_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.experts.experts_0_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.experts.experts_0_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.experts.experts_0_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.experts.experts_0_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.experts.experts_0_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.experts.experts_0_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.experts.experts_0_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.experts.experts_0_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.experts.experts_0_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.experts.experts_0_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.experts.experts_0_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.experts.experts_1_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.experts.experts_1_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.experts.experts_1_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.experts.experts_1_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.experts.experts_1_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.experts.experts_1_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.experts.experts_1_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.experts.experts_1_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.experts.experts_1_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.experts.experts_1_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.experts.experts_1_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.experts.experts_1_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.experts.experts_1_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.experts.experts_1_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.experts.experts_1_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.experts.experts_1_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.experts.experts_2_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.experts.experts_2_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.experts.experts_2_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.experts.experts_2_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.experts.experts_2_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.experts.experts_2_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.experts.experts_2_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.experts.experts_2_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.experts.experts_2_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.experts.experts_2_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.experts.experts_2_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.experts.experts_2_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.experts.experts_2_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.experts.experts_2_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.experts.experts_2_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.experts.experts_2_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.routers.router_0.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.routers.router_1.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.moe_adapter.routers.router_2.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.experts.experts_0_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.experts.experts_0_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.experts.experts_0_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.experts.experts_0_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.experts.experts_0_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.experts.experts_0_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.experts.experts_0_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.experts.experts_0_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.experts.experts_0_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.experts.experts_0_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.experts.experts_0_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.experts.experts_0_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.experts.experts_0_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.experts.experts_0_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.experts.experts_0_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.experts.experts_0_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.experts.experts_1_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.experts.experts_1_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.experts.experts_1_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.experts.experts_1_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.experts.experts_1_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.experts.experts_1_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.experts.experts_1_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.experts.experts_1_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.experts.experts_1_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.experts.experts_1_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.experts.experts_1_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.experts.experts_1_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.experts.experts_1_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.experts.experts_1_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.experts.experts_1_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.experts.experts_1_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.experts.experts_2_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.experts.experts_2_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.experts.experts_2_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.experts.experts_2_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.experts.experts_2_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.experts.experts_2_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.experts.experts_2_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.experts.experts_2_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.experts.experts_2_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.experts.experts_2_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.experts.experts_2_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.experts.experts_2_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.experts.experts_2_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.experts.experts_2_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.experts.experts_2_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.experts.experts_2_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.routers.router_0.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.routers.router_1.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.moe_adapter.routers.router_2.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.experts.experts_0_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.experts.experts_0_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.experts.experts_0_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.experts.experts_0_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.experts.experts_0_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.experts.experts_0_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.experts.experts_0_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.experts.experts_0_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.experts.experts_0_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.experts.experts_0_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.experts.experts_0_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.experts.experts_0_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.experts.experts_0_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.experts.experts_0_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.experts.experts_0_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.experts.experts_0_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.experts.experts_1_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.experts.experts_1_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.experts.experts_1_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.experts.experts_1_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.experts.experts_1_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.experts.experts_1_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.experts.experts_1_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.experts.experts_1_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.experts.experts_1_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.experts.experts_1_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.experts.experts_1_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.experts.experts_1_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.experts.experts_1_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.experts.experts_1_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.experts.experts_1_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.experts.experts_1_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.experts.experts_2_0.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.experts.experts_2_0.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.experts.experts_2_1.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.experts.experts_2_1.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.experts.experts_2_2.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.experts.experts_2_2.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.experts.experts_2_3.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.experts.experts_2_3.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.experts.experts_2_4.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.experts.experts_2_4.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.experts.experts_2_5.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.experts.experts_2_5.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.experts.experts_2_6.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.experts.experts_2_6.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.experts.experts_2_7.adapter_down.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.experts.experts_2_7.adapter_up.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.routers.router_0.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.routers.router_1.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.moe_adapter.routers.router_2.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin", + "model.norm.weight": "pytorch_model-00002-of-00002.bin" + } +}