Upload folder using huggingface_hub

config.json

@@ -0,0 +1,54 @@
+{
+  "architectures": [
+    "OpenMoeForCausalLM"
+  ],
+  "attention_bias": false,
+  "auto_map": {
+    "AutoModelForCausalLM": "modeling_openmoe.OpenMoeForCausalLM"
+  },
+  "bos_token_id": 0,
+  "dropout_rate": 0.0,
+  "enable_comm_overlap": false,
+  "enable_hierarchical_alltoall": false,
+  "enable_kernel": false,
+  "enable_load_balance": false,
+  "eos_token_id": 1,
+  "expert_parallel": null,
+  "head_dim": 128,
+  "hidden_act": "swiglu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "label_smoothing": 0.001,
+  "layer_norm_epsilon": 1e-06,
+  "load_balance_beam_width": 8,
+  "load_balance_group_swap_factor": 0.4,
+  "load_balance_tolerance": 0.1,
+  "max_position_embeddings": 2048,
+  "mlp_gated": true,
+  "model_type": "llama",
+  "moe_layer_interval": 6,
+  "num_attention_heads": 24,
+  "num_experts": 32,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 24,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "router_aux_loss_factor": 0.01,
+  "router_capacity_factor_eval": 2.0,
+  "router_capacity_factor_train": 1.25,
+  "router_drop_tks": true,
+  "router_min_capacity": 4,
+  "router_noisy_policy": null,
+  "router_topk": 2,
+  "router_z_loss_factor": 0.0001,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.0",
+  "use_cache": true,
+  "vocab_size": 256384,
+  "z_loss_factor": 0.01
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.34.0"
+}

pytorch_model-00001-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e312714ebda4aa5b166f8cdcd2a62c3d69a48f3fd587401cd537b16b596b622
+size 8341801178

pytorch_model-00002-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6ef51592eeffe3d1da383aa356b704ffb68f2b9db5ee13ce1a22dc06e19b652
+size 6509949054

pytorch_model-00003-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:137e62363e70b6a1f104b0e2859674cd072aecc8cbe462445547b74f1be2c64d
+size 9990902124

pytorch_model-00004-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9aec4b07f272b719c31b3931f67b957a14a3a3b2e642a889d14ca92cbe8b678
+size 9974404632

pytorch_model-00005-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a157b0acab9c2a828b9272ce364d0f40240572a50454d36e3d7d250691df5d54
+size 8086978210

pytorch_model-00006-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e57ff4d935ef63da0299ebf595c04612665cf8a4eafa6e733f30e22f0ffe5ce
+size 4516236491

pytorch_model.bin.index.json

@@ -0,0 +1,246 @@
+{
+  "metadata": {
+    "total_size": 47420186624
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00006-of-00006.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.extra_mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.11.extra_mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.11.extra_mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.mlp.experts.wi_gate": "pytorch_model-00003-of-00006.bin",
+    "model.layers.11.mlp.experts.wi_up": "pytorch_model-00003-of-00006.bin",
+    "model.layers.11.mlp.experts.wo": "pytorch_model-00003-of-00006.bin",
+    "model.layers.11.mlp.gate_weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.pre_extra_mlp_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.17.extra_mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.17.extra_mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.17.extra_mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.17.mlp.experts.wi_gate": "pytorch_model-00004-of-00006.bin",
+    "model.layers.17.mlp.experts.wi_up": "pytorch_model-00004-of-00006.bin",
+    "model.layers.17.mlp.experts.wo": "pytorch_model-00004-of-00006.bin",
+    "model.layers.17.mlp.gate_weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.17.pre_extra_mlp_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.23.extra_mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.23.extra_mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.23.extra_mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.23.mlp.experts.wi_gate": "pytorch_model-00005-of-00006.bin",
+    "model.layers.23.mlp.experts.wi_up": "pytorch_model-00005-of-00006.bin",
+    "model.layers.23.mlp.experts.wo": "pytorch_model-00006-of-00006.bin",
+    "model.layers.23.mlp.gate_weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.23.pre_extra_mlp_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.extra_mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.5.extra_mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.5.extra_mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.mlp.experts.wi_gate": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.mlp.experts.wi_up": "pytorch_model-00002-of-00006.bin",
+    "model.layers.5.mlp.experts.wo": "pytorch_model-00002-of-00006.bin",
+    "model.layers.5.mlp.gate_weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.pre_extra_mlp_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.norm.weight": "pytorch_model-00006-of-00006.bin"
+  }
+}