| { | |
| "metadata": { | |
| "total_size": 50157558016 | |
| }, | |
| "weight_map": { | |
| "embed_tokens.weight": "model-00001-of-00011.safetensors", | |
| "gated_cross_attn_layers.0.alpha_cross_attn": "model-00006-of-00011.safetensors", | |
| "gated_cross_attn_layers.0.alpha_dense": "model-00006-of-00011.safetensors", | |
| "gated_cross_attn_layers.0.cross_attn.k_proj.weight": "model-00006-of-00011.safetensors", | |
| "gated_cross_attn_layers.0.cross_attn.o_proj.weight": "model-00006-of-00011.safetensors", | |
| "gated_cross_attn_layers.0.cross_attn.q_proj.weight": "model-00006-of-00011.safetensors", | |
| "gated_cross_attn_layers.0.cross_attn.v_proj.weight": "model-00006-of-00011.safetensors", | |
| "gated_cross_attn_layers.0.input_layernorm.weight": "model-00006-of-00011.safetensors", | |
| "gated_cross_attn_layers.0.mlp.down_proj.weight": "model-00006-of-00011.safetensors", | |
| "gated_cross_attn_layers.0.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", | |
| "gated_cross_attn_layers.0.mlp.up_proj.weight": "model-00006-of-00011.safetensors", | |
| "gated_cross_attn_layers.0.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", | |
| "gated_cross_attn_layers.1.alpha_cross_attn": "model-00006-of-00011.safetensors", | |
| "gated_cross_attn_layers.1.alpha_dense": "model-00006-of-00011.safetensors", | |
| "gated_cross_attn_layers.1.cross_attn.k_proj.weight": "model-00006-of-00011.safetensors", | |
| "gated_cross_attn_layers.1.cross_attn.o_proj.weight": "model-00006-of-00011.safetensors", | |
| "gated_cross_attn_layers.1.cross_attn.q_proj.weight": "model-00006-of-00011.safetensors", | |
| "gated_cross_attn_layers.1.cross_attn.v_proj.weight": "model-00006-of-00011.safetensors", | |
| "gated_cross_attn_layers.1.input_layernorm.weight": "model-00006-of-00011.safetensors", | |
| "gated_cross_attn_layers.1.mlp.down_proj.weight": "model-00006-of-00011.safetensors", | |
| "gated_cross_attn_layers.1.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", | |
| "gated_cross_attn_layers.1.mlp.up_proj.weight": "model-00006-of-00011.safetensors", | |
| "gated_cross_attn_layers.1.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", | |
| "gated_cross_attn_layers.10.alpha_cross_attn": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.10.alpha_dense": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.10.cross_attn.k_proj.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.10.cross_attn.o_proj.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.10.cross_attn.q_proj.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.10.cross_attn.v_proj.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.10.input_layernorm.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.10.mlp.down_proj.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.10.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.10.mlp.up_proj.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.10.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.11.alpha_cross_attn": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.11.alpha_dense": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.11.cross_attn.k_proj.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.11.cross_attn.o_proj.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.11.cross_attn.q_proj.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.11.cross_attn.v_proj.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.11.input_layernorm.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.11.mlp.down_proj.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.11.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.11.mlp.up_proj.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.11.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.12.alpha_cross_attn": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.12.alpha_dense": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.12.cross_attn.k_proj.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.12.cross_attn.o_proj.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.12.cross_attn.q_proj.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.12.cross_attn.v_proj.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.12.input_layernorm.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.12.mlp.down_proj.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.12.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.12.mlp.up_proj.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.12.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.13.alpha_cross_attn": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.13.alpha_dense": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.13.cross_attn.k_proj.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.13.cross_attn.o_proj.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.13.cross_attn.q_proj.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.13.cross_attn.v_proj.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.13.input_layernorm.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.13.mlp.down_proj.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.13.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.13.mlp.up_proj.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.13.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.14.alpha_cross_attn": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.14.alpha_dense": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.14.cross_attn.k_proj.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.14.cross_attn.o_proj.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.14.cross_attn.q_proj.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.14.cross_attn.v_proj.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.14.input_layernorm.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.14.mlp.down_proj.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.14.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.14.mlp.up_proj.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.14.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.15.alpha_cross_attn": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.15.alpha_dense": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.15.cross_attn.k_proj.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.15.cross_attn.o_proj.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.15.cross_attn.q_proj.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.15.cross_attn.v_proj.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.15.input_layernorm.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.15.mlp.down_proj.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.15.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.15.mlp.up_proj.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.15.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.16.alpha_cross_attn": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.16.alpha_dense": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.16.cross_attn.k_proj.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.16.cross_attn.o_proj.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.16.cross_attn.q_proj.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.16.cross_attn.v_proj.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.16.input_layernorm.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.16.mlp.down_proj.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.16.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.16.mlp.up_proj.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.16.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.17.alpha_cross_attn": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.17.alpha_dense": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.17.cross_attn.k_proj.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.17.cross_attn.o_proj.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.17.cross_attn.q_proj.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.17.cross_attn.v_proj.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.17.input_layernorm.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.17.mlp.down_proj.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.17.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.17.mlp.up_proj.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.17.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.18.alpha_cross_attn": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.18.alpha_dense": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.18.cross_attn.k_proj.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.18.cross_attn.o_proj.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.18.cross_attn.q_proj.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.18.cross_attn.v_proj.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.18.input_layernorm.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.18.mlp.down_proj.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.18.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.18.mlp.up_proj.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.18.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.19.alpha_cross_attn": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.19.alpha_dense": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.19.cross_attn.k_proj.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.19.cross_attn.o_proj.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.19.cross_attn.q_proj.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.19.cross_attn.v_proj.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.19.input_layernorm.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.19.mlp.down_proj.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.19.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.19.mlp.up_proj.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.19.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.2.alpha_cross_attn": "model-00006-of-00011.safetensors", | |
| "gated_cross_attn_layers.2.alpha_dense": "model-00006-of-00011.safetensors", | |
| "gated_cross_attn_layers.2.cross_attn.k_proj.weight": "model-00006-of-00011.safetensors", | |
| "gated_cross_attn_layers.2.cross_attn.o_proj.weight": "model-00006-of-00011.safetensors", | |
| "gated_cross_attn_layers.2.cross_attn.q_proj.weight": "model-00006-of-00011.safetensors", | |
| "gated_cross_attn_layers.2.cross_attn.v_proj.weight": "model-00006-of-00011.safetensors", | |
| "gated_cross_attn_layers.2.input_layernorm.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.2.mlp.down_proj.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.2.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.2.mlp.up_proj.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.2.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.20.alpha_cross_attn": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.20.alpha_dense": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.20.cross_attn.k_proj.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.20.cross_attn.o_proj.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.20.cross_attn.q_proj.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.20.cross_attn.v_proj.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.20.input_layernorm.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.20.mlp.down_proj.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.20.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.20.mlp.up_proj.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.20.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.21.alpha_cross_attn": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.21.alpha_dense": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.21.cross_attn.k_proj.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.21.cross_attn.o_proj.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.21.cross_attn.q_proj.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.21.cross_attn.v_proj.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.21.input_layernorm.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.21.mlp.down_proj.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.21.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.21.mlp.up_proj.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.21.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.22.alpha_cross_attn": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.22.alpha_dense": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.22.cross_attn.k_proj.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.22.cross_attn.o_proj.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.22.cross_attn.q_proj.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.22.cross_attn.v_proj.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.22.input_layernorm.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.22.mlp.down_proj.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.22.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.22.mlp.up_proj.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.22.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.23.alpha_cross_attn": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.23.alpha_dense": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.23.cross_attn.k_proj.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.23.cross_attn.o_proj.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.23.cross_attn.q_proj.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.23.cross_attn.v_proj.weight": "model-00009-of-00011.safetensors", | |
| "gated_cross_attn_layers.23.input_layernorm.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.23.mlp.down_proj.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.23.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.23.mlp.up_proj.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.23.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.24.alpha_cross_attn": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.24.alpha_dense": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.24.cross_attn.k_proj.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.24.cross_attn.o_proj.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.24.cross_attn.q_proj.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.24.cross_attn.v_proj.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.24.input_layernorm.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.24.mlp.down_proj.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.24.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.24.mlp.up_proj.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.24.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.25.alpha_cross_attn": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.25.alpha_dense": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.25.cross_attn.k_proj.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.25.cross_attn.o_proj.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.25.cross_attn.q_proj.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.25.cross_attn.v_proj.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.25.input_layernorm.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.25.mlp.down_proj.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.25.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.25.mlp.up_proj.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.25.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.26.alpha_cross_attn": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.26.alpha_dense": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.26.cross_attn.k_proj.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.26.cross_attn.o_proj.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.26.cross_attn.q_proj.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.26.cross_attn.v_proj.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.26.input_layernorm.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.26.mlp.down_proj.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.26.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.26.mlp.up_proj.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.26.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.27.alpha_cross_attn": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.27.alpha_dense": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.27.cross_attn.k_proj.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.27.cross_attn.o_proj.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.27.cross_attn.q_proj.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.27.cross_attn.v_proj.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.27.input_layernorm.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.27.mlp.down_proj.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.27.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.27.mlp.up_proj.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.27.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.28.alpha_cross_attn": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.28.alpha_dense": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.28.cross_attn.k_proj.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.28.cross_attn.o_proj.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.28.cross_attn.q_proj.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.28.cross_attn.v_proj.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.28.input_layernorm.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.28.mlp.down_proj.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.28.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.28.mlp.up_proj.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.28.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.29.alpha_cross_attn": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.29.alpha_dense": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.29.cross_attn.k_proj.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.29.cross_attn.o_proj.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.29.cross_attn.q_proj.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.29.cross_attn.v_proj.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.29.input_layernorm.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.29.mlp.down_proj.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.29.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.29.mlp.up_proj.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.29.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.3.alpha_cross_attn": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.3.alpha_dense": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.3.cross_attn.k_proj.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.3.cross_attn.o_proj.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.3.cross_attn.q_proj.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.3.cross_attn.v_proj.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.3.input_layernorm.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.3.mlp.down_proj.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.3.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.3.mlp.up_proj.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.3.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.30.alpha_cross_attn": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.30.alpha_dense": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.30.cross_attn.k_proj.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.30.cross_attn.o_proj.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.30.cross_attn.q_proj.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.30.cross_attn.v_proj.weight": "model-00010-of-00011.safetensors", | |
| "gated_cross_attn_layers.30.input_layernorm.weight": "model-00011-of-00011.safetensors", | |
| "gated_cross_attn_layers.30.mlp.down_proj.weight": "model-00011-of-00011.safetensors", | |
| "gated_cross_attn_layers.30.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", | |
| "gated_cross_attn_layers.30.mlp.up_proj.weight": "model-00011-of-00011.safetensors", | |
| "gated_cross_attn_layers.30.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", | |
| "gated_cross_attn_layers.31.alpha_cross_attn": "model-00011-of-00011.safetensors", | |
| "gated_cross_attn_layers.31.alpha_dense": "model-00011-of-00011.safetensors", | |
| "gated_cross_attn_layers.31.cross_attn.k_proj.weight": "model-00011-of-00011.safetensors", | |
| "gated_cross_attn_layers.31.cross_attn.o_proj.weight": "model-00011-of-00011.safetensors", | |
| "gated_cross_attn_layers.31.cross_attn.q_proj.weight": "model-00011-of-00011.safetensors", | |
| "gated_cross_attn_layers.31.cross_attn.v_proj.weight": "model-00011-of-00011.safetensors", | |
| "gated_cross_attn_layers.31.input_layernorm.weight": "model-00011-of-00011.safetensors", | |
| "gated_cross_attn_layers.31.mlp.down_proj.weight": "model-00011-of-00011.safetensors", | |
| "gated_cross_attn_layers.31.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", | |
| "gated_cross_attn_layers.31.mlp.up_proj.weight": "model-00011-of-00011.safetensors", | |
| "gated_cross_attn_layers.31.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", | |
| "gated_cross_attn_layers.4.alpha_cross_attn": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.4.alpha_dense": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.4.cross_attn.k_proj.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.4.cross_attn.o_proj.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.4.cross_attn.q_proj.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.4.cross_attn.v_proj.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.4.input_layernorm.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.4.mlp.down_proj.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.4.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.4.mlp.up_proj.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.4.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.5.alpha_cross_attn": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.5.alpha_dense": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.5.cross_attn.k_proj.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.5.cross_attn.o_proj.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.5.cross_attn.q_proj.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.5.cross_attn.v_proj.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.5.input_layernorm.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.5.mlp.down_proj.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.5.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.5.mlp.up_proj.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.5.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.6.alpha_cross_attn": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.6.alpha_dense": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.6.cross_attn.k_proj.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.6.cross_attn.o_proj.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.6.cross_attn.q_proj.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.6.cross_attn.v_proj.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.6.input_layernorm.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.6.mlp.down_proj.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.6.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.6.mlp.up_proj.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.6.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.7.alpha_cross_attn": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.7.alpha_dense": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.7.cross_attn.k_proj.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.7.cross_attn.o_proj.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.7.cross_attn.q_proj.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.7.cross_attn.v_proj.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.7.input_layernorm.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.7.mlp.down_proj.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.7.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.7.mlp.up_proj.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.7.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.8.alpha_cross_attn": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.8.alpha_dense": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.8.cross_attn.k_proj.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.8.cross_attn.o_proj.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.8.cross_attn.q_proj.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.8.cross_attn.v_proj.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.8.input_layernorm.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.8.mlp.down_proj.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.8.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.8.mlp.up_proj.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.8.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.9.alpha_cross_attn": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.9.alpha_dense": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.9.cross_attn.k_proj.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.9.cross_attn.o_proj.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.9.cross_attn.q_proj.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.9.cross_attn.v_proj.weight": "model-00007-of-00011.safetensors", | |
| "gated_cross_attn_layers.9.input_layernorm.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.9.mlp.down_proj.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.9.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.9.mlp.up_proj.weight": "model-00008-of-00011.safetensors", | |
| "gated_cross_attn_layers.9.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", | |
| "layers.0.input_layernorm.weight": "model-00001-of-00011.safetensors", | |
| "layers.0.mlp.down_proj.weight": "model-00001-of-00011.safetensors", | |
| "layers.0.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", | |
| "layers.0.mlp.up_proj.weight": "model-00001-of-00011.safetensors", | |
| "layers.0.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", | |
| "layers.0.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", | |
| "layers.0.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", | |
| "layers.0.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", | |
| "layers.0.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", | |
| "layers.1.input_layernorm.weight": "model-00001-of-00011.safetensors", | |
| "layers.1.mlp.down_proj.weight": "model-00001-of-00011.safetensors", | |
| "layers.1.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", | |
| "layers.1.mlp.up_proj.weight": "model-00001-of-00011.safetensors", | |
| "layers.1.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", | |
| "layers.1.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", | |
| "layers.1.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", | |
| "layers.1.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", | |
| "layers.1.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", | |
| "layers.10.input_layernorm.weight": "model-00003-of-00011.safetensors", | |
| "layers.10.mlp.down_proj.weight": "model-00003-of-00011.safetensors", | |
| "layers.10.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", | |
| "layers.10.mlp.up_proj.weight": "model-00003-of-00011.safetensors", | |
| "layers.10.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", | |
| "layers.10.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", | |
| "layers.10.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", | |
| "layers.10.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", | |
| "layers.10.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", | |
| "layers.11.input_layernorm.weight": "model-00003-of-00011.safetensors", | |
| "layers.11.mlp.down_proj.weight": "model-00003-of-00011.safetensors", | |
| "layers.11.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", | |
| "layers.11.mlp.up_proj.weight": "model-00003-of-00011.safetensors", | |
| "layers.11.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", | |
| "layers.11.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", | |
| "layers.11.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", | |
| "layers.11.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", | |
| "layers.11.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", | |
| "layers.12.input_layernorm.weight": "model-00003-of-00011.safetensors", | |
| "layers.12.mlp.down_proj.weight": "model-00003-of-00011.safetensors", | |
| "layers.12.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", | |
| "layers.12.mlp.up_proj.weight": "model-00003-of-00011.safetensors", | |
| "layers.12.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", | |
| "layers.12.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", | |
| "layers.12.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", | |
| "layers.12.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", | |
| "layers.12.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", | |
| "layers.13.input_layernorm.weight": "model-00003-of-00011.safetensors", | |
| "layers.13.mlp.down_proj.weight": "model-00003-of-00011.safetensors", | |
| "layers.13.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", | |
| "layers.13.mlp.up_proj.weight": "model-00003-of-00011.safetensors", | |
| "layers.13.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", | |
| "layers.13.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", | |
| "layers.13.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", | |
| "layers.13.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", | |
| "layers.13.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", | |
| "layers.14.input_layernorm.weight": "model-00003-of-00011.safetensors", | |
| "layers.14.mlp.down_proj.weight": "model-00003-of-00011.safetensors", | |
| "layers.14.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", | |
| "layers.14.mlp.up_proj.weight": "model-00003-of-00011.safetensors", | |
| "layers.14.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", | |
| "layers.14.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", | |
| "layers.14.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", | |
| "layers.14.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", | |
| "layers.14.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", | |
| "layers.15.input_layernorm.weight": "model-00004-of-00011.safetensors", | |
| "layers.15.mlp.down_proj.weight": "model-00003-of-00011.safetensors", | |
| "layers.15.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", | |
| "layers.15.mlp.up_proj.weight": "model-00004-of-00011.safetensors", | |
| "layers.15.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", | |
| "layers.15.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", | |
| "layers.15.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", | |
| "layers.15.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", | |
| "layers.15.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", | |
| "layers.16.input_layernorm.weight": "model-00004-of-00011.safetensors", | |
| "layers.16.mlp.down_proj.weight": "model-00004-of-00011.safetensors", | |
| "layers.16.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", | |
| "layers.16.mlp.up_proj.weight": "model-00004-of-00011.safetensors", | |
| "layers.16.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", | |
| "layers.16.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", | |
| "layers.16.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", | |
| "layers.16.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", | |
| "layers.16.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", | |
| "layers.17.input_layernorm.weight": "model-00004-of-00011.safetensors", | |
| "layers.17.mlp.down_proj.weight": "model-00004-of-00011.safetensors", | |
| "layers.17.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", | |
| "layers.17.mlp.up_proj.weight": "model-00004-of-00011.safetensors", | |
| "layers.17.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", | |
| "layers.17.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", | |
| "layers.17.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", | |
| "layers.17.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", | |
| "layers.17.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", | |
| "layers.18.input_layernorm.weight": "model-00004-of-00011.safetensors", | |
| "layers.18.mlp.down_proj.weight": "model-00004-of-00011.safetensors", | |
| "layers.18.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", | |
| "layers.18.mlp.up_proj.weight": "model-00004-of-00011.safetensors", | |
| "layers.18.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", | |
| "layers.18.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", | |
| "layers.18.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", | |
| "layers.18.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", | |
| "layers.18.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", | |
| "layers.19.input_layernorm.weight": "model-00004-of-00011.safetensors", | |
| "layers.19.mlp.down_proj.weight": "model-00004-of-00011.safetensors", | |
| "layers.19.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", | |
| "layers.19.mlp.up_proj.weight": "model-00004-of-00011.safetensors", | |
| "layers.19.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", | |
| "layers.19.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", | |
| "layers.19.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", | |
| "layers.19.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", | |
| "layers.19.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", | |
| "layers.2.input_layernorm.weight": "model-00001-of-00011.safetensors", | |
| "layers.2.mlp.down_proj.weight": "model-00001-of-00011.safetensors", | |
| "layers.2.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", | |
| "layers.2.mlp.up_proj.weight": "model-00001-of-00011.safetensors", | |
| "layers.2.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", | |
| "layers.2.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", | |
| "layers.2.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", | |
| "layers.2.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", | |
| "layers.2.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", | |
| "layers.20.input_layernorm.weight": "model-00004-of-00011.safetensors", | |
| "layers.20.mlp.down_proj.weight": "model-00004-of-00011.safetensors", | |
| "layers.20.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", | |
| "layers.20.mlp.up_proj.weight": "model-00004-of-00011.safetensors", | |
| "layers.20.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", | |
| "layers.20.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", | |
| "layers.20.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", | |
| "layers.20.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", | |
| "layers.20.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", | |
| "layers.21.input_layernorm.weight": "model-00005-of-00011.safetensors", | |
| "layers.21.mlp.down_proj.weight": "model-00004-of-00011.safetensors", | |
| "layers.21.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", | |
| "layers.21.mlp.up_proj.weight": "model-00005-of-00011.safetensors", | |
| "layers.21.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", | |
| "layers.21.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", | |
| "layers.21.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", | |
| "layers.21.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", | |
| "layers.21.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", | |
| "layers.22.input_layernorm.weight": "model-00005-of-00011.safetensors", | |
| "layers.22.mlp.down_proj.weight": "model-00005-of-00011.safetensors", | |
| "layers.22.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", | |
| "layers.22.mlp.up_proj.weight": "model-00005-of-00011.safetensors", | |
| "layers.22.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", | |
| "layers.22.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", | |
| "layers.22.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", | |
| "layers.22.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", | |
| "layers.22.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", | |
| "layers.23.input_layernorm.weight": "model-00005-of-00011.safetensors", | |
| "layers.23.mlp.down_proj.weight": "model-00005-of-00011.safetensors", | |
| "layers.23.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", | |
| "layers.23.mlp.up_proj.weight": "model-00005-of-00011.safetensors", | |
| "layers.23.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", | |
| "layers.23.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", | |
| "layers.23.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", | |
| "layers.23.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", | |
| "layers.23.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", | |
| "layers.24.input_layernorm.weight": "model-00005-of-00011.safetensors", | |
| "layers.24.mlp.down_proj.weight": "model-00005-of-00011.safetensors", | |
| "layers.24.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", | |
| "layers.24.mlp.up_proj.weight": "model-00005-of-00011.safetensors", | |
| "layers.24.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", | |
| "layers.24.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", | |
| "layers.24.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", | |
| "layers.24.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", | |
| "layers.24.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", | |
| "layers.25.input_layernorm.weight": "model-00005-of-00011.safetensors", | |
| "layers.25.mlp.down_proj.weight": "model-00005-of-00011.safetensors", | |
| "layers.25.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", | |
| "layers.25.mlp.up_proj.weight": "model-00005-of-00011.safetensors", | |
| "layers.25.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", | |
| "layers.25.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", | |
| "layers.25.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", | |
| "layers.25.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", | |
| "layers.25.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", | |
| "layers.26.input_layernorm.weight": "model-00005-of-00011.safetensors", | |
| "layers.26.mlp.down_proj.weight": "model-00005-of-00011.safetensors", | |
| "layers.26.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", | |
| "layers.26.mlp.up_proj.weight": "model-00005-of-00011.safetensors", | |
| "layers.26.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", | |
| "layers.26.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", | |
| "layers.26.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", | |
| "layers.26.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", | |
| "layers.26.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", | |
| "layers.27.input_layernorm.weight": "model-00006-of-00011.safetensors", | |
| "layers.27.mlp.down_proj.weight": "model-00005-of-00011.safetensors", | |
| "layers.27.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", | |
| "layers.27.mlp.up_proj.weight": "model-00006-of-00011.safetensors", | |
| "layers.27.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", | |
| "layers.27.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", | |
| "layers.27.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", | |
| "layers.27.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", | |
| "layers.27.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", | |
| "layers.28.input_layernorm.weight": "model-00006-of-00011.safetensors", | |
| "layers.28.mlp.down_proj.weight": "model-00006-of-00011.safetensors", | |
| "layers.28.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", | |
| "layers.28.mlp.up_proj.weight": "model-00006-of-00011.safetensors", | |
| "layers.28.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", | |
| "layers.28.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", | |
| "layers.28.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", | |
| "layers.28.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", | |
| "layers.28.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", | |
| "layers.29.input_layernorm.weight": "model-00006-of-00011.safetensors", | |
| "layers.29.mlp.down_proj.weight": "model-00006-of-00011.safetensors", | |
| "layers.29.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", | |
| "layers.29.mlp.up_proj.weight": "model-00006-of-00011.safetensors", | |
| "layers.29.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", | |
| "layers.29.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", | |
| "layers.29.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", | |
| "layers.29.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", | |
| "layers.29.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", | |
| "layers.3.input_layernorm.weight": "model-00002-of-00011.safetensors", | |
| "layers.3.mlp.down_proj.weight": "model-00001-of-00011.safetensors", | |
| "layers.3.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", | |
| "layers.3.mlp.up_proj.weight": "model-00002-of-00011.safetensors", | |
| "layers.3.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", | |
| "layers.3.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", | |
| "layers.3.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", | |
| "layers.3.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", | |
| "layers.3.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", | |
| "layers.30.input_layernorm.weight": "model-00006-of-00011.safetensors", | |
| "layers.30.mlp.down_proj.weight": "model-00006-of-00011.safetensors", | |
| "layers.30.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", | |
| "layers.30.mlp.up_proj.weight": "model-00006-of-00011.safetensors", | |
| "layers.30.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", | |
| "layers.30.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", | |
| "layers.30.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", | |
| "layers.30.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", | |
| "layers.30.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", | |
| "layers.31.input_layernorm.weight": "model-00006-of-00011.safetensors", | |
| "layers.31.mlp.down_proj.weight": "model-00006-of-00011.safetensors", | |
| "layers.31.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", | |
| "layers.31.mlp.up_proj.weight": "model-00006-of-00011.safetensors", | |
| "layers.31.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", | |
| "layers.31.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", | |
| "layers.31.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", | |
| "layers.31.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", | |
| "layers.31.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", | |
| "layers.4.input_layernorm.weight": "model-00002-of-00011.safetensors", | |
| "layers.4.mlp.down_proj.weight": "model-00002-of-00011.safetensors", | |
| "layers.4.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", | |
| "layers.4.mlp.up_proj.weight": "model-00002-of-00011.safetensors", | |
| "layers.4.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", | |
| "layers.4.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", | |
| "layers.4.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", | |
| "layers.4.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", | |
| "layers.4.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", | |
| "layers.5.input_layernorm.weight": "model-00002-of-00011.safetensors", | |
| "layers.5.mlp.down_proj.weight": "model-00002-of-00011.safetensors", | |
| "layers.5.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", | |
| "layers.5.mlp.up_proj.weight": "model-00002-of-00011.safetensors", | |
| "layers.5.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", | |
| "layers.5.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", | |
| "layers.5.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", | |
| "layers.5.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", | |
| "layers.5.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", | |
| "layers.6.input_layernorm.weight": "model-00002-of-00011.safetensors", | |
| "layers.6.mlp.down_proj.weight": "model-00002-of-00011.safetensors", | |
| "layers.6.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", | |
| "layers.6.mlp.up_proj.weight": "model-00002-of-00011.safetensors", | |
| "layers.6.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", | |
| "layers.6.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", | |
| "layers.6.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", | |
| "layers.6.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", | |
| "layers.6.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", | |
| "layers.7.input_layernorm.weight": "model-00002-of-00011.safetensors", | |
| "layers.7.mlp.down_proj.weight": "model-00002-of-00011.safetensors", | |
| "layers.7.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", | |
| "layers.7.mlp.up_proj.weight": "model-00002-of-00011.safetensors", | |
| "layers.7.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", | |
| "layers.7.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", | |
| "layers.7.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", | |
| "layers.7.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", | |
| "layers.7.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", | |
| "layers.8.input_layernorm.weight": "model-00002-of-00011.safetensors", | |
| "layers.8.mlp.down_proj.weight": "model-00002-of-00011.safetensors", | |
| "layers.8.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", | |
| "layers.8.mlp.up_proj.weight": "model-00002-of-00011.safetensors", | |
| "layers.8.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", | |
| "layers.8.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", | |
| "layers.8.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", | |
| "layers.8.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", | |
| "layers.8.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", | |
| "layers.9.input_layernorm.weight": "model-00003-of-00011.safetensors", | |
| "layers.9.mlp.down_proj.weight": "model-00002-of-00011.safetensors", | |
| "layers.9.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", | |
| "layers.9.mlp.up_proj.weight": "model-00003-of-00011.safetensors", | |
| "layers.9.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", | |
| "layers.9.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", | |
| "layers.9.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", | |
| "layers.9.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", | |
| "layers.9.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", | |
| "norm.weight": "model-00011-of-00011.safetensors", | |
| "vision_model.embeddings.class_embedding": "model-00001-of-00011.safetensors", | |
| "vision_model.embeddings.patch_embedding.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.embeddings.position_embedding.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.27.layer_norm1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.27.layer_norm1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.27.layer_norm2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.27.layer_norm2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.27.mlp.fc1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.27.mlp.fc1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.27.mlp.fc2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.27.mlp.fc2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.27.self_attn.k_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.27.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.27.self_attn.out_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.27.self_attn.out_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.27.self_attn.q_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.27.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.27.self_attn.v_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.27.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.28.layer_norm1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.28.layer_norm1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.28.layer_norm2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.28.layer_norm2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.28.mlp.fc1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.28.mlp.fc1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.28.mlp.fc2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.28.mlp.fc2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.28.self_attn.k_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.28.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.28.self_attn.out_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.28.self_attn.out_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.28.self_attn.q_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.28.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.28.self_attn.v_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.28.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.29.layer_norm1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.29.layer_norm1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.29.layer_norm2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.29.layer_norm2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.29.mlp.fc1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.29.mlp.fc1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.29.mlp.fc2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.29.mlp.fc2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.29.self_attn.k_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.29.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.29.self_attn.out_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.29.self_attn.out_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.29.self_attn.q_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.29.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.29.self_attn.v_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.29.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.30.layer_norm1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.30.layer_norm1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.30.layer_norm2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.30.layer_norm2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.30.mlp.fc1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.30.mlp.fc1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.30.mlp.fc2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.30.mlp.fc2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.30.self_attn.k_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.30.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.30.self_attn.out_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.30.self_attn.out_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.30.self_attn.q_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.30.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.30.self_attn.v_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.30.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.31.layer_norm1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.31.layer_norm1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.31.layer_norm2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.31.layer_norm2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.31.mlp.fc1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.31.mlp.fc1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.31.mlp.fc2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.31.mlp.fc2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.31.self_attn.k_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.31.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.31.self_attn.out_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.31.self_attn.out_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.31.self_attn.q_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.31.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.31.self_attn.v_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.31.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.post_layernorm.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.post_layernorm.weight": "model-00001-of-00011.safetensors", | |
| "vision_model.pre_layrnorm.bias": "model-00001-of-00011.safetensors", | |
| "vision_model.pre_layrnorm.weight": "model-00001-of-00011.safetensors" | |
| } | |
| } | |