| { | |
| "metadata": { | |
| "total_size": 26341023744 | |
| }, | |
| "weight_map": { | |
| "lm_head.weight": "model-00006-of-00006.safetensors", | |
| "model.embed_tokens.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.0.attention.k_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.0.attention.o_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.0.attention.q_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.0.attention.v_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.1.attention.k_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.1.attention.o_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.1.attention.q_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.1.attention.v_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.10.attention.k_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.10.attention.latent_k_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.10.attention.latent_o_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.10.attention.latent_q_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.10.attention.latent_v_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.10.attention.o_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.10.attention.q_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.10.attention.v_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.11.attention.k_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.11.attention.o_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.11.attention.q_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.11.attention.v_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.11.mlp.experts.0.down_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.11.mlp.experts.0.gate_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.11.mlp.experts.0.up_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.11.mlp.experts.1.down_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.11.mlp.experts.1.gate_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.11.mlp.experts.1.up_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.11.mlp.experts.2.down_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.11.mlp.experts.2.gate_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.11.mlp.experts.2.up_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.11.mlp.experts.3.down_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.11.mlp.experts.3.gate_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.11.mlp.experts.3.up_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.11.mlp.experts.4.down_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.11.mlp.experts.4.gate_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.11.mlp.experts.4.up_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.11.mlp.experts.5.down_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.11.mlp.experts.5.gate_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.11.mlp.experts.5.up_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.11.mlp.experts.6.down_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.11.mlp.experts.6.gate_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.11.mlp.experts.6.up_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.11.mlp.experts.7.down_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.11.mlp.experts.7.gate_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.11.mlp.experts.7.up_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.11.mlp.router.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.12.attention.k_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.12.attention.latent_k_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.12.attention.latent_o_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.12.attention.latent_q_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.12.attention.latent_v_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.12.attention.o_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.12.attention.q_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.12.attention.v_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.13.attention.k_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.13.attention.o_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.13.attention.q_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.13.attention.v_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.14.attention.k_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.14.attention.latent_k_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.14.attention.latent_o_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.14.attention.latent_q_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.14.attention.latent_v_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.14.attention.o_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.14.attention.q_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.14.attention.v_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.15.attention.k_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.15.attention.o_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.15.attention.q_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.15.attention.v_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.15.mlp.experts.0.down_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.15.mlp.experts.0.gate_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.15.mlp.experts.0.up_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.15.mlp.experts.1.down_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.15.mlp.experts.1.gate_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.15.mlp.experts.1.up_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.15.mlp.experts.2.down_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.15.mlp.experts.2.gate_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.15.mlp.experts.2.up_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.15.mlp.experts.3.down_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.15.mlp.experts.3.gate_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.15.mlp.experts.3.up_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.15.mlp.experts.4.down_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.15.mlp.experts.4.gate_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.15.mlp.experts.4.up_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.15.mlp.experts.5.down_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.15.mlp.experts.5.gate_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.15.mlp.experts.5.up_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.15.mlp.experts.6.down_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.15.mlp.experts.6.gate_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.15.mlp.experts.6.up_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.15.mlp.experts.7.down_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.15.mlp.experts.7.gate_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.15.mlp.experts.7.up_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.15.mlp.router.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.16.attention.k_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.16.attention.latent_k_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.16.attention.latent_o_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.16.attention.latent_q_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.16.attention.latent_v_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.16.attention.o_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.16.attention.q_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.16.attention.v_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.17.attention.k_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.17.attention.o_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.17.attention.q_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.17.attention.v_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.18.attention.k_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.18.attention.latent_k_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.18.attention.latent_o_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.18.attention.latent_q_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.18.attention.latent_v_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.18.attention.o_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.18.attention.q_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.18.attention.v_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.19.attention.k_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.19.attention.o_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.19.attention.q_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.19.attention.v_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.19.mlp.experts.0.down_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.19.mlp.experts.0.gate_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.19.mlp.experts.0.up_proj.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.19.mlp.experts.1.down_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.19.mlp.experts.1.gate_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.19.mlp.experts.1.up_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.19.mlp.experts.2.down_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.19.mlp.experts.2.gate_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.19.mlp.experts.2.up_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.19.mlp.experts.3.down_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.19.mlp.experts.3.gate_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.19.mlp.experts.3.up_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.19.mlp.experts.4.down_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.19.mlp.experts.4.gate_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.19.mlp.experts.4.up_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.19.mlp.experts.5.down_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.19.mlp.experts.5.gate_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.19.mlp.experts.5.up_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.19.mlp.experts.6.down_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.19.mlp.experts.6.gate_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.19.mlp.experts.6.up_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.19.mlp.experts.7.down_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.19.mlp.experts.7.gate_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.19.mlp.experts.7.up_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.19.mlp.router.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", | |
| "model.layers.2.attention.k_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.2.attention.o_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.2.attention.q_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.2.attention.v_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.20.attention.k_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.20.attention.latent_k_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.20.attention.latent_o_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.20.attention.latent_q_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.20.attention.latent_v_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.20.attention.o_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.20.attention.q_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.20.attention.v_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.21.attention.k_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.21.attention.o_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.21.attention.q_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.21.attention.v_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.22.attention.k_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.22.attention.latent_k_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.22.attention.latent_o_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.22.attention.latent_q_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.22.attention.latent_v_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.22.attention.o_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.22.attention.q_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.22.attention.v_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.23.attention.k_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.23.attention.o_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.23.attention.q_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.23.attention.v_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.23.mlp.experts.0.down_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.23.mlp.experts.0.gate_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.23.mlp.experts.0.up_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.23.mlp.experts.1.down_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.23.mlp.experts.1.gate_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.23.mlp.experts.1.up_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.23.mlp.experts.2.down_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.23.mlp.experts.2.gate_proj.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.23.mlp.experts.2.up_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.23.mlp.experts.3.down_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.23.mlp.experts.3.gate_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.23.mlp.experts.3.up_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.23.mlp.experts.4.down_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.23.mlp.experts.4.gate_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.23.mlp.experts.4.up_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.23.mlp.experts.5.down_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.23.mlp.experts.5.gate_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.23.mlp.experts.5.up_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.23.mlp.experts.6.down_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.23.mlp.experts.6.gate_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.23.mlp.experts.6.up_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.23.mlp.experts.7.down_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.23.mlp.experts.7.gate_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.23.mlp.experts.7.up_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.23.mlp.router.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", | |
| "model.layers.24.attention.k_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.24.attention.latent_k_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.24.attention.latent_o_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.24.attention.latent_q_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.24.attention.latent_v_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.24.attention.o_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.24.attention.q_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.24.attention.v_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.25.attention.k_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.25.attention.o_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.25.attention.q_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.25.attention.v_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.26.attention.k_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.26.attention.o_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.26.attention.q_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.26.attention.v_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.27.attention.k_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.27.attention.o_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.27.attention.q_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.27.attention.v_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.28.attention.k_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.28.attention.o_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.28.attention.q_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.28.attention.v_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.29.attention.k_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.29.attention.o_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.29.attention.q_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.29.attention.v_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.29.input_layernorm.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.29.mlp.down_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.29.mlp.up_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.3.attention.k_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.3.attention.o_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.3.attention.q_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.3.attention.v_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.30.attention.k_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.30.attention.o_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.30.attention.q_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.30.attention.v_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors", | |
| "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.30.mlp.up_proj.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", | |
| "model.layers.31.attention.k_proj.weight": "model-00006-of-00006.safetensors", | |
| "model.layers.31.attention.o_proj.weight": "model-00006-of-00006.safetensors", | |
| "model.layers.31.attention.q_proj.weight": "model-00006-of-00006.safetensors", | |
| "model.layers.31.attention.v_proj.weight": "model-00006-of-00006.safetensors", | |
| "model.layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors", | |
| "model.layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors", | |
| "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", | |
| "model.layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors", | |
| "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", | |
| "model.layers.4.attention.k_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.4.attention.o_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.4.attention.q_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.4.attention.v_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.5.attention.k_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.5.attention.o_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.5.attention.q_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.5.attention.v_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.6.attention.k_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.6.attention.o_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.6.attention.q_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.6.attention.v_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.6.input_layernorm.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.6.mlp.down_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.6.mlp.up_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.7.attention.k_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.7.attention.o_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.7.attention.q_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.7.attention.v_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.7.input_layernorm.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.7.mlp.down_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.7.mlp.up_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.8.attention.k_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.8.attention.latent_k_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.8.attention.latent_o_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.8.attention.latent_q_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.8.attention.latent_v_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.8.attention.o_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.8.attention.q_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.8.attention.v_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.8.input_layernorm.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.8.mlp.up_proj.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", | |
| "model.layers.9.attention.k_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.9.attention.o_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.9.attention.q_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.9.attention.v_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors", | |
| "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", | |
| "model.norm.weight": "model-00006-of-00006.safetensors" | |
| } | |
| } | |