drllm-qwen-7b-focalloss-50ep-16gradacc-1e3-pixart-8meanwindow / checkpoint-2000 /model.safetensors.index.json
| { | |
| "metadata": { | |
| "total_parameters": 7628475988, | |
| "total_size": 15256951976 | |
| }, | |
| "weight_map": { | |
| "lm_head.weight": "model-00004-of-00004.safetensors", | |
| "model.embed_tokens.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", | |
| "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", | |
| "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", | |
| "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", | |
| "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", | |
| "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", | |
| "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", | |
| "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", | |
| "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", | |
| "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", | |
| "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", | |
| "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", | |
| "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", | |
| "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", | |
| "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", | |
| "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", | |
| "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", | |
| "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", | |
| "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", | |
| "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", | |
| "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", | |
| "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", | |
| "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", | |
| "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", | |
| "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", | |
| "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", | |
| "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", | |
| "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", | |
| "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", | |
| "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", | |
| "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", | |
| "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", | |
| "model.norm.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.0.linear1.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.0.linear1.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.0.linear2.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.0.linear2.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.1.linear1.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.1.linear1.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.1.linear2.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.1.linear2.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.10.linear1.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.10.linear1.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.10.linear2.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.10.linear2.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.11.linear1.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.11.linear1.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.11.linear2.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.11.linear2.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.12.linear1.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.12.linear1.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.12.linear2.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.12.linear2.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.13.linear1.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.13.linear1.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.13.linear2.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.13.linear2.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.14.linear1.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.14.linear1.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.14.linear2.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.14.linear2.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.15.linear1.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.15.linear1.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.15.linear2.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.15.linear2.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.16.linear1.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.16.linear1.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.16.linear2.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.16.linear2.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.17.linear1.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.17.linear1.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.17.linear2.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.17.linear2.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.18.linear1.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.18.linear1.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.18.linear2.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.18.linear2.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.19.linear1.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.19.linear1.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.19.linear2.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.19.linear2.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.2.linear1.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.2.linear1.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.2.linear2.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.2.linear2.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.20.linear1.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.20.linear1.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.20.linear2.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.20.linear2.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.21.linear1.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.21.linear1.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.21.linear2.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.21.linear2.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.22.linear1.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.22.linear1.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.22.linear2.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.22.linear2.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.23.linear1.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.23.linear1.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.23.linear2.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.23.linear2.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.24.linear1.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.24.linear1.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.24.linear2.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.24.linear2.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.25.linear1.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.25.linear1.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.25.linear2.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.25.linear2.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.26.linear1.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.26.linear1.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.26.linear2.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.26.linear2.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.27.linear1.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.27.linear1.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.27.linear2.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.27.linear2.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.3.linear1.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.3.linear1.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.3.linear2.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.3.linear2.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.4.linear1.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.4.linear1.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.4.linear2.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.4.linear2.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.5.linear1.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.5.linear1.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.5.linear2.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.5.linear2.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.6.linear1.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.6.linear1.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.6.linear2.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.6.linear2.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.7.linear1.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.7.linear1.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.7.linear2.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.7.linear2.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.8.linear1.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.8.linear1.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.8.linear2.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.8.linear2.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.9.linear1.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.9.linear1.weight": "model-00003-of-00004.safetensors", | |
| "model.routers.9.linear2.bias": "model-00003-of-00004.safetensors", | |
| "model.routers.9.linear2.weight": "model-00003-of-00004.safetensors" | |
| } | |
| } | |