| { |
| "metadata": { |
| "total_parameters": 196956130368, |
| "total_size": 393912284928 |
| }, |
| "weight_map": { |
| "lm_head.weight": "model-00001-of-00008.safetensors", |
| "model.embed_tokens.weight": "model-00001-of-00008.safetensors", |
| "model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors", |
| "model.layers.0.mlp.down_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.0.mlp.up_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", |
| "model.layers.0.self_attn.g_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00008.safetensors", |
| "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00008.safetensors", |
| "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors", |
| "model.layers.1.mlp.down_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.1.mlp.up_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", |
| "model.layers.1.self_attn.g_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00008.safetensors", |
| "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00008.safetensors", |
| "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.10.input_layernorm.weight": "model-00002-of-00008.safetensors", |
| "model.layers.10.moe.down_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.10.moe.gate.weight": "model-00002-of-00008.safetensors", |
| "model.layers.10.moe.gate_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.10.moe.router_bias": "model-00002-of-00008.safetensors", |
| "model.layers.10.moe.up_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", |
| "model.layers.10.self_attn.g_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00008.safetensors", |
| "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00008.safetensors", |
| "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.10.share_expert.down_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.10.share_expert.gate_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.10.share_expert.up_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.11.input_layernorm.weight": "model-00002-of-00008.safetensors", |
| "model.layers.11.moe.down_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.11.moe.gate.weight": "model-00002-of-00008.safetensors", |
| "model.layers.11.moe.gate_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.11.moe.router_bias": "model-00002-of-00008.safetensors", |
| "model.layers.11.moe.up_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", |
| "model.layers.11.self_attn.g_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00008.safetensors", |
| "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00008.safetensors", |
| "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.11.share_expert.down_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.11.share_expert.gate_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.11.share_expert.up_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.12.input_layernorm.weight": "model-00002-of-00008.safetensors", |
| "model.layers.12.moe.down_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.12.moe.gate.weight": "model-00002-of-00008.safetensors", |
| "model.layers.12.moe.gate_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.12.moe.router_bias": "model-00002-of-00008.safetensors", |
| "model.layers.12.moe.up_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", |
| "model.layers.12.self_attn.g_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00008.safetensors", |
| "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00008.safetensors", |
| "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.12.share_expert.down_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.12.share_expert.gate_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.12.share_expert.up_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.13.input_layernorm.weight": "model-00002-of-00008.safetensors", |
| "model.layers.13.moe.down_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.13.moe.gate.weight": "model-00002-of-00008.safetensors", |
| "model.layers.13.moe.gate_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.13.moe.router_bias": "model-00003-of-00008.safetensors", |
| "model.layers.13.moe.up_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", |
| "model.layers.13.self_attn.g_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.13.self_attn.k_norm.weight": "model-00003-of-00008.safetensors", |
| "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.13.self_attn.q_norm.weight": "model-00003-of-00008.safetensors", |
| "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.13.share_expert.down_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.13.share_expert.gate_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.13.share_expert.up_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.14.input_layernorm.weight": "model-00003-of-00008.safetensors", |
| "model.layers.14.moe.down_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.14.moe.gate.weight": "model-00003-of-00008.safetensors", |
| "model.layers.14.moe.gate_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.14.moe.router_bias": "model-00003-of-00008.safetensors", |
| "model.layers.14.moe.up_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", |
| "model.layers.14.self_attn.g_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.14.self_attn.k_norm.weight": "model-00003-of-00008.safetensors", |
| "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.14.self_attn.q_norm.weight": "model-00003-of-00008.safetensors", |
| "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.14.share_expert.down_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.14.share_expert.gate_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.14.share_expert.up_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.15.input_layernorm.weight": "model-00003-of-00008.safetensors", |
| "model.layers.15.moe.down_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.15.moe.gate.weight": "model-00003-of-00008.safetensors", |
| "model.layers.15.moe.gate_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.15.moe.router_bias": "model-00003-of-00008.safetensors", |
| "model.layers.15.moe.up_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", |
| "model.layers.15.self_attn.g_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.15.self_attn.k_norm.weight": "model-00003-of-00008.safetensors", |
| "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.15.self_attn.q_norm.weight": "model-00003-of-00008.safetensors", |
| "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.15.share_expert.down_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.15.share_expert.gate_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.15.share_expert.up_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.16.input_layernorm.weight": "model-00003-of-00008.safetensors", |
| "model.layers.16.moe.down_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.16.moe.gate.weight": "model-00003-of-00008.safetensors", |
| "model.layers.16.moe.gate_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.16.moe.router_bias": "model-00003-of-00008.safetensors", |
| "model.layers.16.moe.up_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", |
| "model.layers.16.self_attn.g_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.16.self_attn.k_norm.weight": "model-00003-of-00008.safetensors", |
| "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.16.self_attn.q_norm.weight": "model-00003-of-00008.safetensors", |
| "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.16.share_expert.down_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.16.share_expert.gate_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.16.share_expert.up_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.17.input_layernorm.weight": "model-00003-of-00008.safetensors", |
| "model.layers.17.moe.down_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.17.moe.gate.weight": "model-00003-of-00008.safetensors", |
| "model.layers.17.moe.gate_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.17.moe.router_bias": "model-00003-of-00008.safetensors", |
| "model.layers.17.moe.up_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", |
| "model.layers.17.self_attn.g_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.17.self_attn.k_norm.weight": "model-00003-of-00008.safetensors", |
| "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.17.self_attn.q_norm.weight": "model-00003-of-00008.safetensors", |
| "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.17.share_expert.down_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.17.share_expert.gate_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.17.share_expert.up_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.18.input_layernorm.weight": "model-00003-of-00008.safetensors", |
| "model.layers.18.moe.down_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.18.moe.gate.weight": "model-00003-of-00008.safetensors", |
| "model.layers.18.moe.gate_proj.weight": "model-00003-of-00008.safetensors", |
| "model.layers.18.moe.router_bias": "model-00003-of-00008.safetensors", |
| "model.layers.18.moe.up_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", |
| "model.layers.18.self_attn.g_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.18.self_attn.k_norm.weight": "model-00004-of-00008.safetensors", |
| "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.18.self_attn.q_norm.weight": "model-00004-of-00008.safetensors", |
| "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.18.share_expert.down_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.18.share_expert.gate_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.18.share_expert.up_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.19.input_layernorm.weight": "model-00004-of-00008.safetensors", |
| "model.layers.19.moe.down_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.19.moe.gate.weight": "model-00004-of-00008.safetensors", |
| "model.layers.19.moe.gate_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.19.moe.router_bias": "model-00004-of-00008.safetensors", |
| "model.layers.19.moe.up_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", |
| "model.layers.19.self_attn.g_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.19.self_attn.k_norm.weight": "model-00004-of-00008.safetensors", |
| "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.19.self_attn.q_norm.weight": "model-00004-of-00008.safetensors", |
| "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.19.share_expert.down_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.19.share_expert.gate_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.19.share_expert.up_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.2.input_layernorm.weight": "model-00001-of-00008.safetensors", |
| "model.layers.2.mlp.down_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.2.mlp.up_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", |
| "model.layers.2.self_attn.g_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00008.safetensors", |
| "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00008.safetensors", |
| "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.20.input_layernorm.weight": "model-00004-of-00008.safetensors", |
| "model.layers.20.moe.down_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.20.moe.gate.weight": "model-00004-of-00008.safetensors", |
| "model.layers.20.moe.gate_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.20.moe.router_bias": "model-00004-of-00008.safetensors", |
| "model.layers.20.moe.up_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", |
| "model.layers.20.self_attn.g_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.20.self_attn.k_norm.weight": "model-00004-of-00008.safetensors", |
| "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.20.self_attn.q_norm.weight": "model-00004-of-00008.safetensors", |
| "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.20.share_expert.down_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.20.share_expert.gate_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.20.share_expert.up_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.21.input_layernorm.weight": "model-00004-of-00008.safetensors", |
| "model.layers.21.moe.down_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.21.moe.gate.weight": "model-00004-of-00008.safetensors", |
| "model.layers.21.moe.gate_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.21.moe.router_bias": "model-00004-of-00008.safetensors", |
| "model.layers.21.moe.up_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", |
| "model.layers.21.self_attn.g_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.21.self_attn.k_norm.weight": "model-00004-of-00008.safetensors", |
| "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.21.self_attn.q_norm.weight": "model-00004-of-00008.safetensors", |
| "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.21.share_expert.down_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.21.share_expert.gate_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.21.share_expert.up_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.22.input_layernorm.weight": "model-00004-of-00008.safetensors", |
| "model.layers.22.moe.down_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.22.moe.gate.weight": "model-00004-of-00008.safetensors", |
| "model.layers.22.moe.gate_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.22.moe.router_bias": "model-00004-of-00008.safetensors", |
| "model.layers.22.moe.up_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", |
| "model.layers.22.self_attn.g_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.22.self_attn.k_norm.weight": "model-00004-of-00008.safetensors", |
| "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.22.self_attn.q_norm.weight": "model-00004-of-00008.safetensors", |
| "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.22.share_expert.down_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.22.share_expert.gate_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.22.share_expert.up_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.23.input_layernorm.weight": "model-00004-of-00008.safetensors", |
| "model.layers.23.moe.down_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.23.moe.gate.weight": "model-00004-of-00008.safetensors", |
| "model.layers.23.moe.gate_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.23.moe.router_bias": "model-00004-of-00008.safetensors", |
| "model.layers.23.moe.up_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", |
| "model.layers.23.self_attn.g_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.23.self_attn.k_norm.weight": "model-00004-of-00008.safetensors", |
| "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.23.self_attn.q_norm.weight": "model-00004-of-00008.safetensors", |
| "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.23.share_expert.down_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.23.share_expert.gate_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.23.share_expert.up_proj.weight": "model-00004-of-00008.safetensors", |
| "model.layers.24.input_layernorm.weight": "model-00004-of-00008.safetensors", |
| "model.layers.24.moe.down_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.24.moe.gate.weight": "model-00005-of-00008.safetensors", |
| "model.layers.24.moe.gate_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.24.moe.router_bias": "model-00005-of-00008.safetensors", |
| "model.layers.24.moe.up_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", |
| "model.layers.24.self_attn.g_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.24.self_attn.k_norm.weight": "model-00005-of-00008.safetensors", |
| "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.24.self_attn.q_norm.weight": "model-00005-of-00008.safetensors", |
| "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.24.share_expert.down_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.24.share_expert.gate_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.24.share_expert.up_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.25.input_layernorm.weight": "model-00005-of-00008.safetensors", |
| "model.layers.25.moe.down_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.25.moe.gate.weight": "model-00005-of-00008.safetensors", |
| "model.layers.25.moe.gate_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.25.moe.router_bias": "model-00005-of-00008.safetensors", |
| "model.layers.25.moe.up_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", |
| "model.layers.25.self_attn.g_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.25.self_attn.k_norm.weight": "model-00005-of-00008.safetensors", |
| "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.25.self_attn.q_norm.weight": "model-00005-of-00008.safetensors", |
| "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.25.share_expert.down_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.25.share_expert.gate_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.25.share_expert.up_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.26.input_layernorm.weight": "model-00005-of-00008.safetensors", |
| "model.layers.26.moe.down_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.26.moe.gate.weight": "model-00005-of-00008.safetensors", |
| "model.layers.26.moe.gate_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.26.moe.router_bias": "model-00005-of-00008.safetensors", |
| "model.layers.26.moe.up_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", |
| "model.layers.26.self_attn.g_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.26.self_attn.k_norm.weight": "model-00005-of-00008.safetensors", |
| "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.26.self_attn.q_norm.weight": "model-00005-of-00008.safetensors", |
| "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.26.share_expert.down_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.26.share_expert.gate_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.26.share_expert.up_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.27.input_layernorm.weight": "model-00005-of-00008.safetensors", |
| "model.layers.27.moe.down_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.27.moe.gate.weight": "model-00005-of-00008.safetensors", |
| "model.layers.27.moe.gate_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.27.moe.router_bias": "model-00005-of-00008.safetensors", |
| "model.layers.27.moe.up_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", |
| "model.layers.27.self_attn.g_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.27.self_attn.k_norm.weight": "model-00005-of-00008.safetensors", |
| "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.27.self_attn.q_norm.weight": "model-00005-of-00008.safetensors", |
| "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.27.share_expert.down_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.27.share_expert.gate_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.27.share_expert.up_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.28.input_layernorm.weight": "model-00005-of-00008.safetensors", |
| "model.layers.28.moe.down_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.28.moe.gate.weight": "model-00005-of-00008.safetensors", |
| "model.layers.28.moe.gate_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.28.moe.router_bias": "model-00005-of-00008.safetensors", |
| "model.layers.28.moe.up_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", |
| "model.layers.28.self_attn.g_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.28.self_attn.k_norm.weight": "model-00005-of-00008.safetensors", |
| "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.28.self_attn.q_norm.weight": "model-00005-of-00008.safetensors", |
| "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.28.share_expert.down_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.28.share_expert.gate_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.28.share_expert.up_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.29.input_layernorm.weight": "model-00005-of-00008.safetensors", |
| "model.layers.29.moe.down_proj.weight": "model-00005-of-00008.safetensors", |
| "model.layers.29.moe.gate.weight": "model-00005-of-00008.safetensors", |
| "model.layers.29.moe.gate_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.29.moe.router_bias": "model-00006-of-00008.safetensors", |
| "model.layers.29.moe.up_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", |
| "model.layers.29.self_attn.g_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.29.self_attn.k_norm.weight": "model-00006-of-00008.safetensors", |
| "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.29.self_attn.q_norm.weight": "model-00006-of-00008.safetensors", |
| "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.29.share_expert.down_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.29.share_expert.gate_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.29.share_expert.up_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.3.input_layernorm.weight": "model-00001-of-00008.safetensors", |
| "model.layers.3.moe.down_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.3.moe.gate.weight": "model-00001-of-00008.safetensors", |
| "model.layers.3.moe.gate_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.3.moe.router_bias": "model-00001-of-00008.safetensors", |
| "model.layers.3.moe.up_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", |
| "model.layers.3.self_attn.g_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00008.safetensors", |
| "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00008.safetensors", |
| "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.3.share_expert.down_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.3.share_expert.gate_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.3.share_expert.up_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.30.input_layernorm.weight": "model-00006-of-00008.safetensors", |
| "model.layers.30.moe.down_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.30.moe.gate.weight": "model-00006-of-00008.safetensors", |
| "model.layers.30.moe.gate_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.30.moe.router_bias": "model-00006-of-00008.safetensors", |
| "model.layers.30.moe.up_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", |
| "model.layers.30.self_attn.g_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.30.self_attn.k_norm.weight": "model-00006-of-00008.safetensors", |
| "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.30.self_attn.q_norm.weight": "model-00006-of-00008.safetensors", |
| "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.30.share_expert.down_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.30.share_expert.gate_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.30.share_expert.up_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.31.input_layernorm.weight": "model-00006-of-00008.safetensors", |
| "model.layers.31.moe.down_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.31.moe.gate.weight": "model-00006-of-00008.safetensors", |
| "model.layers.31.moe.gate_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.31.moe.router_bias": "model-00006-of-00008.safetensors", |
| "model.layers.31.moe.up_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", |
| "model.layers.31.self_attn.g_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.31.self_attn.k_norm.weight": "model-00006-of-00008.safetensors", |
| "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.31.self_attn.q_norm.weight": "model-00006-of-00008.safetensors", |
| "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.31.share_expert.down_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.31.share_expert.gate_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.31.share_expert.up_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.32.input_layernorm.weight": "model-00006-of-00008.safetensors", |
| "model.layers.32.moe.down_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.32.moe.gate.weight": "model-00006-of-00008.safetensors", |
| "model.layers.32.moe.gate_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.32.moe.router_bias": "model-00006-of-00008.safetensors", |
| "model.layers.32.moe.up_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.32.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", |
| "model.layers.32.self_attn.g_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.32.self_attn.k_norm.weight": "model-00006-of-00008.safetensors", |
| "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.32.self_attn.q_norm.weight": "model-00006-of-00008.safetensors", |
| "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.32.share_expert.down_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.32.share_expert.gate_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.32.share_expert.up_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.33.input_layernorm.weight": "model-00006-of-00008.safetensors", |
| "model.layers.33.moe.down_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.33.moe.gate.weight": "model-00006-of-00008.safetensors", |
| "model.layers.33.moe.gate_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.33.moe.router_bias": "model-00006-of-00008.safetensors", |
| "model.layers.33.moe.up_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.33.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", |
| "model.layers.33.self_attn.g_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.33.self_attn.k_norm.weight": "model-00006-of-00008.safetensors", |
| "model.layers.33.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.33.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.33.self_attn.q_norm.weight": "model-00006-of-00008.safetensors", |
| "model.layers.33.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.33.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.33.share_expert.down_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.33.share_expert.gate_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.33.share_expert.up_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.34.input_layernorm.weight": "model-00006-of-00008.safetensors", |
| "model.layers.34.moe.down_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.34.moe.gate.weight": "model-00006-of-00008.safetensors", |
| "model.layers.34.moe.gate_proj.weight": "model-00006-of-00008.safetensors", |
| "model.layers.34.moe.router_bias": "model-00006-of-00008.safetensors", |
| "model.layers.34.moe.up_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", |
| "model.layers.34.self_attn.g_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.34.self_attn.k_norm.weight": "model-00007-of-00008.safetensors", |
| "model.layers.34.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.34.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.34.self_attn.q_norm.weight": "model-00007-of-00008.safetensors", |
| "model.layers.34.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.34.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.34.share_expert.down_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.34.share_expert.gate_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.34.share_expert.up_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.35.input_layernorm.weight": "model-00007-of-00008.safetensors", |
| "model.layers.35.moe.down_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.35.moe.gate.weight": "model-00007-of-00008.safetensors", |
| "model.layers.35.moe.gate_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.35.moe.router_bias": "model-00007-of-00008.safetensors", |
| "model.layers.35.moe.up_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.35.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", |
| "model.layers.35.self_attn.g_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.35.self_attn.k_norm.weight": "model-00007-of-00008.safetensors", |
| "model.layers.35.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.35.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.35.self_attn.q_norm.weight": "model-00007-of-00008.safetensors", |
| "model.layers.35.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.35.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.35.share_expert.down_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.35.share_expert.gate_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.35.share_expert.up_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.36.input_layernorm.weight": "model-00007-of-00008.safetensors", |
| "model.layers.36.moe.down_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.36.moe.gate.weight": "model-00007-of-00008.safetensors", |
| "model.layers.36.moe.gate_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.36.moe.router_bias": "model-00007-of-00008.safetensors", |
| "model.layers.36.moe.up_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.36.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", |
| "model.layers.36.self_attn.g_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.36.self_attn.k_norm.weight": "model-00007-of-00008.safetensors", |
| "model.layers.36.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.36.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.36.self_attn.q_norm.weight": "model-00007-of-00008.safetensors", |
| "model.layers.36.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.36.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.36.share_expert.down_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.36.share_expert.gate_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.36.share_expert.up_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.37.input_layernorm.weight": "model-00007-of-00008.safetensors", |
| "model.layers.37.moe.down_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.37.moe.gate.weight": "model-00007-of-00008.safetensors", |
| "model.layers.37.moe.gate_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.37.moe.router_bias": "model-00007-of-00008.safetensors", |
| "model.layers.37.moe.up_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.37.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", |
| "model.layers.37.self_attn.g_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.37.self_attn.k_norm.weight": "model-00007-of-00008.safetensors", |
| "model.layers.37.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.37.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.37.self_attn.q_norm.weight": "model-00007-of-00008.safetensors", |
| "model.layers.37.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.37.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.37.share_expert.down_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.37.share_expert.gate_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.37.share_expert.up_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.38.input_layernorm.weight": "model-00007-of-00008.safetensors", |
| "model.layers.38.moe.down_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.38.moe.gate.weight": "model-00007-of-00008.safetensors", |
| "model.layers.38.moe.gate_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.38.moe.router_bias": "model-00007-of-00008.safetensors", |
| "model.layers.38.moe.up_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.38.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", |
| "model.layers.38.self_attn.g_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.38.self_attn.k_norm.weight": "model-00007-of-00008.safetensors", |
| "model.layers.38.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.38.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.38.self_attn.q_norm.weight": "model-00007-of-00008.safetensors", |
| "model.layers.38.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.38.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.38.share_expert.down_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.38.share_expert.gate_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.38.share_expert.up_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.39.input_layernorm.weight": "model-00007-of-00008.safetensors", |
| "model.layers.39.moe.down_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.39.moe.gate.weight": "model-00007-of-00008.safetensors", |
| "model.layers.39.moe.gate_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.39.moe.router_bias": "model-00007-of-00008.safetensors", |
| "model.layers.39.moe.up_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.39.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", |
| "model.layers.39.self_attn.g_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.39.self_attn.k_norm.weight": "model-00007-of-00008.safetensors", |
| "model.layers.39.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.39.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.39.self_attn.q_norm.weight": "model-00007-of-00008.safetensors", |
| "model.layers.39.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.39.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.39.share_expert.down_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.39.share_expert.gate_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.39.share_expert.up_proj.weight": "model-00007-of-00008.safetensors", |
| "model.layers.4.input_layernorm.weight": "model-00001-of-00008.safetensors", |
| "model.layers.4.moe.down_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.4.moe.gate.weight": "model-00001-of-00008.safetensors", |
| "model.layers.4.moe.gate_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.4.moe.router_bias": "model-00001-of-00008.safetensors", |
| "model.layers.4.moe.up_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", |
| "model.layers.4.self_attn.g_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00008.safetensors", |
| "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00008.safetensors", |
| "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.4.share_expert.down_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.4.share_expert.gate_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.4.share_expert.up_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.40.input_layernorm.weight": "model-00007-of-00008.safetensors", |
| "model.layers.40.moe.down_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.40.moe.gate.weight": "model-00008-of-00008.safetensors", |
| "model.layers.40.moe.gate_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.40.moe.router_bias": "model-00008-of-00008.safetensors", |
| "model.layers.40.moe.up_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.40.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", |
| "model.layers.40.self_attn.g_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.40.self_attn.k_norm.weight": "model-00008-of-00008.safetensors", |
| "model.layers.40.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.40.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.40.self_attn.q_norm.weight": "model-00008-of-00008.safetensors", |
| "model.layers.40.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.40.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.40.share_expert.down_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.40.share_expert.gate_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.40.share_expert.up_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.41.input_layernorm.weight": "model-00008-of-00008.safetensors", |
| "model.layers.41.moe.down_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.41.moe.gate.weight": "model-00008-of-00008.safetensors", |
| "model.layers.41.moe.gate_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.41.moe.router_bias": "model-00008-of-00008.safetensors", |
| "model.layers.41.moe.up_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.41.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", |
| "model.layers.41.self_attn.g_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.41.self_attn.k_norm.weight": "model-00008-of-00008.safetensors", |
| "model.layers.41.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.41.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.41.self_attn.q_norm.weight": "model-00008-of-00008.safetensors", |
| "model.layers.41.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.41.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.41.share_expert.down_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.41.share_expert.gate_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.41.share_expert.up_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.42.input_layernorm.weight": "model-00008-of-00008.safetensors", |
| "model.layers.42.moe.down_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.42.moe.gate.weight": "model-00008-of-00008.safetensors", |
| "model.layers.42.moe.gate_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.42.moe.router_bias": "model-00008-of-00008.safetensors", |
| "model.layers.42.moe.up_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.42.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", |
| "model.layers.42.self_attn.g_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.42.self_attn.k_norm.weight": "model-00008-of-00008.safetensors", |
| "model.layers.42.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.42.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.42.self_attn.q_norm.weight": "model-00008-of-00008.safetensors", |
| "model.layers.42.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.42.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.42.share_expert.down_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.42.share_expert.gate_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.42.share_expert.up_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.43.input_layernorm.weight": "model-00008-of-00008.safetensors", |
| "model.layers.43.moe.down_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.43.moe.gate.weight": "model-00008-of-00008.safetensors", |
| "model.layers.43.moe.gate_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.43.moe.router_bias": "model-00008-of-00008.safetensors", |
| "model.layers.43.moe.up_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.43.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", |
| "model.layers.43.self_attn.g_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.43.self_attn.k_norm.weight": "model-00008-of-00008.safetensors", |
| "model.layers.43.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.43.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.43.self_attn.q_norm.weight": "model-00008-of-00008.safetensors", |
| "model.layers.43.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.43.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.43.share_expert.down_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.43.share_expert.gate_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.43.share_expert.up_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.44.input_layernorm.weight": "model-00008-of-00008.safetensors", |
| "model.layers.44.moe.down_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.44.moe.gate.weight": "model-00008-of-00008.safetensors", |
| "model.layers.44.moe.gate_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.44.moe.router_bias": "model-00008-of-00008.safetensors", |
| "model.layers.44.moe.up_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.44.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", |
| "model.layers.44.self_attn.g_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.44.self_attn.k_norm.weight": "model-00008-of-00008.safetensors", |
| "model.layers.44.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.44.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.44.self_attn.q_norm.weight": "model-00008-of-00008.safetensors", |
| "model.layers.44.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.44.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.44.share_expert.down_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.44.share_expert.gate_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.44.share_expert.up_proj.weight": "model-00008-of-00008.safetensors", |
| "model.layers.5.input_layernorm.weight": "model-00001-of-00008.safetensors", |
| "model.layers.5.moe.down_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.5.moe.gate.weight": "model-00001-of-00008.safetensors", |
| "model.layers.5.moe.gate_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.5.moe.router_bias": "model-00001-of-00008.safetensors", |
| "model.layers.5.moe.up_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", |
| "model.layers.5.self_attn.g_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00008.safetensors", |
| "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00008.safetensors", |
| "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.5.share_expert.down_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.5.share_expert.gate_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.5.share_expert.up_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.6.input_layernorm.weight": "model-00001-of-00008.safetensors", |
| "model.layers.6.moe.down_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.6.moe.gate.weight": "model-00001-of-00008.safetensors", |
| "model.layers.6.moe.gate_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.6.moe.router_bias": "model-00001-of-00008.safetensors", |
| "model.layers.6.moe.up_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", |
| "model.layers.6.self_attn.g_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00008.safetensors", |
| "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00008.safetensors", |
| "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.6.share_expert.down_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.6.share_expert.gate_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.6.share_expert.up_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.7.input_layernorm.weight": "model-00001-of-00008.safetensors", |
| "model.layers.7.moe.down_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.7.moe.gate.weight": "model-00001-of-00008.safetensors", |
| "model.layers.7.moe.gate_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.7.moe.router_bias": "model-00001-of-00008.safetensors", |
| "model.layers.7.moe.up_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", |
| "model.layers.7.self_attn.g_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00008.safetensors", |
| "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00008.safetensors", |
| "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", |
| "model.layers.7.share_expert.down_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.7.share_expert.gate_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.7.share_expert.up_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.8.input_layernorm.weight": "model-00002-of-00008.safetensors", |
| "model.layers.8.moe.down_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.8.moe.gate.weight": "model-00002-of-00008.safetensors", |
| "model.layers.8.moe.gate_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.8.moe.router_bias": "model-00002-of-00008.safetensors", |
| "model.layers.8.moe.up_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", |
| "model.layers.8.self_attn.g_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.8.self_attn.k_norm.weight": "model-00002-of-00008.safetensors", |
| "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.8.self_attn.q_norm.weight": "model-00002-of-00008.safetensors", |
| "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.8.share_expert.down_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.8.share_expert.gate_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.8.share_expert.up_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.9.input_layernorm.weight": "model-00002-of-00008.safetensors", |
| "model.layers.9.moe.down_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.9.moe.gate.weight": "model-00002-of-00008.safetensors", |
| "model.layers.9.moe.gate_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.9.moe.router_bias": "model-00002-of-00008.safetensors", |
| "model.layers.9.moe.up_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", |
| "model.layers.9.self_attn.g_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.9.self_attn.k_norm.weight": "model-00002-of-00008.safetensors", |
| "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.9.self_attn.q_norm.weight": "model-00002-of-00008.safetensors", |
| "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.9.share_expert.down_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.9.share_expert.gate_proj.weight": "model-00002-of-00008.safetensors", |
| "model.layers.9.share_expert.up_proj.weight": "model-00002-of-00008.safetensors", |
| "model.norm.weight": "model-00008-of-00008.safetensors" |
| } |
| } |
|
|
