diff --git "a/pytorch_model.bin.index.json" "b/pytorch_model.bin.index.json" deleted file mode 100644--- "a/pytorch_model.bin.index.json" +++ /dev/null @@ -1,1563 +0,0 @@ -{ - "metadata": { - "total_size": 176901927168 - }, - "weight_map": { - "language_model.lm_head.weight": "pytorch_model-00042-of-00046.bin", - "language_model.model.embed_tokens.weight": "pytorch_model-00001-of-00046.bin", - "language_model.model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00046.bin", - "language_model.model.layers.0.mlp.down_proj.weight": "pytorch_model-00002-of-00046.bin", - "language_model.model.layers.0.mlp.gate_proj.weight": "pytorch_model-00002-of-00046.bin", - "language_model.model.layers.0.mlp.up_proj.weight": "pytorch_model-00002-of-00046.bin", - "language_model.model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00046.bin", - "language_model.model.layers.0.self_attn.k_proj.bias": "pytorch_model-00002-of-00046.bin", - "language_model.model.layers.0.self_attn.k_proj.weight": "pytorch_model-00002-of-00046.bin", - "language_model.model.layers.0.self_attn.o_proj.weight": "pytorch_model-00002-of-00046.bin", - "language_model.model.layers.0.self_attn.q_proj.bias": "pytorch_model-00002-of-00046.bin", - "language_model.model.layers.0.self_attn.q_proj.weight": "pytorch_model-00002-of-00046.bin", - "language_model.model.layers.0.self_attn.v_proj.bias": "pytorch_model-00002-of-00046.bin", - "language_model.model.layers.0.self_attn.v_proj.weight": "pytorch_model-00002-of-00046.bin", - "language_model.model.layers.1.input_layernorm.weight": "pytorch_model-00002-of-00046.bin", - "language_model.model.layers.1.mlp.down_proj.weight": "pytorch_model-00002-of-00046.bin", - "language_model.model.layers.1.mlp.gate_proj.weight": "pytorch_model-00002-of-00046.bin", - "language_model.model.layers.1.mlp.up_proj.weight": "pytorch_model-00002-of-00046.bin", - "language_model.model.layers.1.post_attention_layernorm.weight": "pytorch_model-00002-of-00046.bin", - "language_model.model.layers.1.self_attn.k_proj.bias": "pytorch_model-00002-of-00046.bin", - "language_model.model.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00046.bin", - "language_model.model.layers.1.self_attn.o_proj.weight": "pytorch_model-00002-of-00046.bin", - "language_model.model.layers.1.self_attn.q_proj.bias": "pytorch_model-00002-of-00046.bin", - "language_model.model.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00046.bin", - "language_model.model.layers.1.self_attn.v_proj.bias": "pytorch_model-00002-of-00046.bin", - "language_model.model.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00046.bin", - "language_model.model.layers.10.input_layernorm.weight": "pytorch_model-00006-of-00046.bin", - "language_model.model.layers.10.mlp.down_proj.weight": "pytorch_model-00007-of-00046.bin", - "language_model.model.layers.10.mlp.gate_proj.weight": "pytorch_model-00007-of-00046.bin", - "language_model.model.layers.10.mlp.up_proj.weight": "pytorch_model-00007-of-00046.bin", - "language_model.model.layers.10.post_attention_layernorm.weight": "pytorch_model-00006-of-00046.bin", - "language_model.model.layers.10.self_attn.k_proj.bias": "pytorch_model-00007-of-00046.bin", - "language_model.model.layers.10.self_attn.k_proj.weight": "pytorch_model-00007-of-00046.bin", - "language_model.model.layers.10.self_attn.o_proj.weight": "pytorch_model-00007-of-00046.bin", - "language_model.model.layers.10.self_attn.q_proj.bias": "pytorch_model-00007-of-00046.bin", - "language_model.model.layers.10.self_attn.q_proj.weight": "pytorch_model-00007-of-00046.bin", - "language_model.model.layers.10.self_attn.v_proj.bias": "pytorch_model-00007-of-00046.bin", - "language_model.model.layers.10.self_attn.v_proj.weight": "pytorch_model-00007-of-00046.bin", - "language_model.model.layers.11.input_layernorm.weight": "pytorch_model-00007-of-00046.bin", - "language_model.model.layers.11.mlp.down_proj.weight": "pytorch_model-00007-of-00046.bin", - "language_model.model.layers.11.mlp.gate_proj.weight": "pytorch_model-00007-of-00046.bin", - "language_model.model.layers.11.mlp.up_proj.weight": "pytorch_model-00007-of-00046.bin", - "language_model.model.layers.11.post_attention_layernorm.weight": "pytorch_model-00007-of-00046.bin", - "language_model.model.layers.11.self_attn.k_proj.bias": "pytorch_model-00007-of-00046.bin", - "language_model.model.layers.11.self_attn.k_proj.weight": "pytorch_model-00007-of-00046.bin", - "language_model.model.layers.11.self_attn.o_proj.weight": "pytorch_model-00007-of-00046.bin", - "language_model.model.layers.11.self_attn.q_proj.bias": "pytorch_model-00007-of-00046.bin", - "language_model.model.layers.11.self_attn.q_proj.weight": "pytorch_model-00007-of-00046.bin", - "language_model.model.layers.11.self_attn.v_proj.bias": "pytorch_model-00007-of-00046.bin", - "language_model.model.layers.11.self_attn.v_proj.weight": "pytorch_model-00007-of-00046.bin", - "language_model.model.layers.12.input_layernorm.weight": "pytorch_model-00007-of-00046.bin", - "language_model.model.layers.12.mlp.down_proj.weight": "pytorch_model-00008-of-00046.bin", - "language_model.model.layers.12.mlp.gate_proj.weight": "pytorch_model-00008-of-00046.bin", - "language_model.model.layers.12.mlp.up_proj.weight": "pytorch_model-00008-of-00046.bin", - "language_model.model.layers.12.post_attention_layernorm.weight": "pytorch_model-00007-of-00046.bin", - "language_model.model.layers.12.self_attn.k_proj.bias": "pytorch_model-00008-of-00046.bin", - "language_model.model.layers.12.self_attn.k_proj.weight": "pytorch_model-00008-of-00046.bin", - "language_model.model.layers.12.self_attn.o_proj.weight": "pytorch_model-00008-of-00046.bin", - "language_model.model.layers.12.self_attn.q_proj.bias": "pytorch_model-00008-of-00046.bin", - "language_model.model.layers.12.self_attn.q_proj.weight": "pytorch_model-00008-of-00046.bin", - "language_model.model.layers.12.self_attn.v_proj.bias": "pytorch_model-00008-of-00046.bin", - "language_model.model.layers.12.self_attn.v_proj.weight": "pytorch_model-00008-of-00046.bin", - "language_model.model.layers.13.input_layernorm.weight": "pytorch_model-00008-of-00046.bin", - "language_model.model.layers.13.mlp.down_proj.weight": "pytorch_model-00008-of-00046.bin", - "language_model.model.layers.13.mlp.gate_proj.weight": "pytorch_model-00008-of-00046.bin", - "language_model.model.layers.13.mlp.up_proj.weight": "pytorch_model-00008-of-00046.bin", - "language_model.model.layers.13.post_attention_layernorm.weight": "pytorch_model-00008-of-00046.bin", - "language_model.model.layers.13.self_attn.k_proj.bias": "pytorch_model-00008-of-00046.bin", - "language_model.model.layers.13.self_attn.k_proj.weight": "pytorch_model-00008-of-00046.bin", - "language_model.model.layers.13.self_attn.o_proj.weight": "pytorch_model-00008-of-00046.bin", - "language_model.model.layers.13.self_attn.q_proj.bias": "pytorch_model-00008-of-00046.bin", - "language_model.model.layers.13.self_attn.q_proj.weight": "pytorch_model-00008-of-00046.bin", - "language_model.model.layers.13.self_attn.v_proj.bias": "pytorch_model-00008-of-00046.bin", - "language_model.model.layers.13.self_attn.v_proj.weight": "pytorch_model-00008-of-00046.bin", - "language_model.model.layers.14.input_layernorm.weight": "pytorch_model-00008-of-00046.bin", - "language_model.model.layers.14.mlp.down_proj.weight": "pytorch_model-00009-of-00046.bin", - "language_model.model.layers.14.mlp.gate_proj.weight": "pytorch_model-00009-of-00046.bin", - "language_model.model.layers.14.mlp.up_proj.weight": "pytorch_model-00009-of-00046.bin", - "language_model.model.layers.14.post_attention_layernorm.weight": "pytorch_model-00008-of-00046.bin", - "language_model.model.layers.14.self_attn.k_proj.bias": "pytorch_model-00009-of-00046.bin", - "language_model.model.layers.14.self_attn.k_proj.weight": "pytorch_model-00009-of-00046.bin", - "language_model.model.layers.14.self_attn.o_proj.weight": "pytorch_model-00009-of-00046.bin", - "language_model.model.layers.14.self_attn.q_proj.bias": "pytorch_model-00009-of-00046.bin", - "language_model.model.layers.14.self_attn.q_proj.weight": "pytorch_model-00009-of-00046.bin", - "language_model.model.layers.14.self_attn.v_proj.bias": "pytorch_model-00009-of-00046.bin", - "language_model.model.layers.14.self_attn.v_proj.weight": "pytorch_model-00009-of-00046.bin", - "language_model.model.layers.15.input_layernorm.weight": "pytorch_model-00009-of-00046.bin", - "language_model.model.layers.15.mlp.down_proj.weight": "pytorch_model-00009-of-00046.bin", - "language_model.model.layers.15.mlp.gate_proj.weight": "pytorch_model-00009-of-00046.bin", - "language_model.model.layers.15.mlp.up_proj.weight": "pytorch_model-00009-of-00046.bin", - "language_model.model.layers.15.post_attention_layernorm.weight": "pytorch_model-00009-of-00046.bin", - "language_model.model.layers.15.self_attn.k_proj.bias": "pytorch_model-00009-of-00046.bin", - "language_model.model.layers.15.self_attn.k_proj.weight": "pytorch_model-00009-of-00046.bin", - "language_model.model.layers.15.self_attn.o_proj.weight": "pytorch_model-00009-of-00046.bin", - "language_model.model.layers.15.self_attn.q_proj.bias": "pytorch_model-00009-of-00046.bin", - "language_model.model.layers.15.self_attn.q_proj.weight": "pytorch_model-00009-of-00046.bin", - "language_model.model.layers.15.self_attn.v_proj.bias": "pytorch_model-00009-of-00046.bin", - "language_model.model.layers.15.self_attn.v_proj.weight": "pytorch_model-00009-of-00046.bin", - "language_model.model.layers.16.input_layernorm.weight": "pytorch_model-00009-of-00046.bin", - "language_model.model.layers.16.mlp.down_proj.weight": "pytorch_model-00010-of-00046.bin", - "language_model.model.layers.16.mlp.gate_proj.weight": "pytorch_model-00010-of-00046.bin", - "language_model.model.layers.16.mlp.up_proj.weight": "pytorch_model-00010-of-00046.bin", - "language_model.model.layers.16.post_attention_layernorm.weight": "pytorch_model-00009-of-00046.bin", - "language_model.model.layers.16.self_attn.k_proj.bias": "pytorch_model-00010-of-00046.bin", - "language_model.model.layers.16.self_attn.k_proj.weight": "pytorch_model-00010-of-00046.bin", - "language_model.model.layers.16.self_attn.o_proj.weight": "pytorch_model-00010-of-00046.bin", - "language_model.model.layers.16.self_attn.q_proj.bias": "pytorch_model-00010-of-00046.bin", - "language_model.model.layers.16.self_attn.q_proj.weight": "pytorch_model-00010-of-00046.bin", - "language_model.model.layers.16.self_attn.v_proj.bias": "pytorch_model-00010-of-00046.bin", - "language_model.model.layers.16.self_attn.v_proj.weight": "pytorch_model-00010-of-00046.bin", - "language_model.model.layers.17.input_layernorm.weight": "pytorch_model-00010-of-00046.bin", - "language_model.model.layers.17.mlp.down_proj.weight": "pytorch_model-00010-of-00046.bin", - "language_model.model.layers.17.mlp.gate_proj.weight": "pytorch_model-00010-of-00046.bin", - "language_model.model.layers.17.mlp.up_proj.weight": "pytorch_model-00010-of-00046.bin", - "language_model.model.layers.17.post_attention_layernorm.weight": "pytorch_model-00010-of-00046.bin", - "language_model.model.layers.17.self_attn.k_proj.bias": "pytorch_model-00010-of-00046.bin", - "language_model.model.layers.17.self_attn.k_proj.weight": "pytorch_model-00010-of-00046.bin", - "language_model.model.layers.17.self_attn.o_proj.weight": "pytorch_model-00010-of-00046.bin", - "language_model.model.layers.17.self_attn.q_proj.bias": "pytorch_model-00010-of-00046.bin", - "language_model.model.layers.17.self_attn.q_proj.weight": "pytorch_model-00010-of-00046.bin", - "language_model.model.layers.17.self_attn.v_proj.bias": "pytorch_model-00010-of-00046.bin", - "language_model.model.layers.17.self_attn.v_proj.weight": "pytorch_model-00010-of-00046.bin", - "language_model.model.layers.18.input_layernorm.weight": "pytorch_model-00010-of-00046.bin", - "language_model.model.layers.18.mlp.down_proj.weight": "pytorch_model-00011-of-00046.bin", - "language_model.model.layers.18.mlp.gate_proj.weight": "pytorch_model-00011-of-00046.bin", - "language_model.model.layers.18.mlp.up_proj.weight": "pytorch_model-00011-of-00046.bin", - "language_model.model.layers.18.post_attention_layernorm.weight": "pytorch_model-00010-of-00046.bin", - "language_model.model.layers.18.self_attn.k_proj.bias": "pytorch_model-00011-of-00046.bin", - "language_model.model.layers.18.self_attn.k_proj.weight": "pytorch_model-00011-of-00046.bin", - "language_model.model.layers.18.self_attn.o_proj.weight": "pytorch_model-00011-of-00046.bin", - "language_model.model.layers.18.self_attn.q_proj.bias": "pytorch_model-00011-of-00046.bin", - "language_model.model.layers.18.self_attn.q_proj.weight": "pytorch_model-00011-of-00046.bin", - "language_model.model.layers.18.self_attn.v_proj.bias": "pytorch_model-00011-of-00046.bin", - "language_model.model.layers.18.self_attn.v_proj.weight": "pytorch_model-00011-of-00046.bin", - "language_model.model.layers.19.input_layernorm.weight": "pytorch_model-00011-of-00046.bin", - "language_model.model.layers.19.mlp.down_proj.weight": "pytorch_model-00011-of-00046.bin", - "language_model.model.layers.19.mlp.gate_proj.weight": "pytorch_model-00011-of-00046.bin", - "language_model.model.layers.19.mlp.up_proj.weight": "pytorch_model-00011-of-00046.bin", - "language_model.model.layers.19.post_attention_layernorm.weight": "pytorch_model-00011-of-00046.bin", - "language_model.model.layers.19.self_attn.k_proj.bias": "pytorch_model-00011-of-00046.bin", - "language_model.model.layers.19.self_attn.k_proj.weight": "pytorch_model-00011-of-00046.bin", - "language_model.model.layers.19.self_attn.o_proj.weight": "pytorch_model-00011-of-00046.bin", - "language_model.model.layers.19.self_attn.q_proj.bias": "pytorch_model-00011-of-00046.bin", - "language_model.model.layers.19.self_attn.q_proj.weight": "pytorch_model-00011-of-00046.bin", - "language_model.model.layers.19.self_attn.v_proj.bias": "pytorch_model-00011-of-00046.bin", - "language_model.model.layers.19.self_attn.v_proj.weight": "pytorch_model-00011-of-00046.bin", - "language_model.model.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00046.bin", - "language_model.model.layers.2.mlp.down_proj.weight": "pytorch_model-00003-of-00046.bin", - "language_model.model.layers.2.mlp.gate_proj.weight": "pytorch_model-00003-of-00046.bin", - "language_model.model.layers.2.mlp.up_proj.weight": "pytorch_model-00003-of-00046.bin", - "language_model.model.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00046.bin", - "language_model.model.layers.2.self_attn.k_proj.bias": "pytorch_model-00003-of-00046.bin", - "language_model.model.layers.2.self_attn.k_proj.weight": "pytorch_model-00003-of-00046.bin", - "language_model.model.layers.2.self_attn.o_proj.weight": "pytorch_model-00003-of-00046.bin", - "language_model.model.layers.2.self_attn.q_proj.bias": "pytorch_model-00003-of-00046.bin", - "language_model.model.layers.2.self_attn.q_proj.weight": "pytorch_model-00003-of-00046.bin", - "language_model.model.layers.2.self_attn.v_proj.bias": "pytorch_model-00003-of-00046.bin", - "language_model.model.layers.2.self_attn.v_proj.weight": "pytorch_model-00003-of-00046.bin", - "language_model.model.layers.20.input_layernorm.weight": "pytorch_model-00011-of-00046.bin", - "language_model.model.layers.20.mlp.down_proj.weight": "pytorch_model-00012-of-00046.bin", - "language_model.model.layers.20.mlp.gate_proj.weight": "pytorch_model-00012-of-00046.bin", - "language_model.model.layers.20.mlp.up_proj.weight": "pytorch_model-00012-of-00046.bin", - "language_model.model.layers.20.post_attention_layernorm.weight": "pytorch_model-00011-of-00046.bin", - "language_model.model.layers.20.self_attn.k_proj.bias": "pytorch_model-00012-of-00046.bin", - "language_model.model.layers.20.self_attn.k_proj.weight": "pytorch_model-00012-of-00046.bin", - "language_model.model.layers.20.self_attn.o_proj.weight": "pytorch_model-00012-of-00046.bin", - "language_model.model.layers.20.self_attn.q_proj.bias": "pytorch_model-00012-of-00046.bin", - "language_model.model.layers.20.self_attn.q_proj.weight": "pytorch_model-00012-of-00046.bin", - "language_model.model.layers.20.self_attn.v_proj.bias": "pytorch_model-00012-of-00046.bin", - "language_model.model.layers.20.self_attn.v_proj.weight": "pytorch_model-00012-of-00046.bin", - "language_model.model.layers.21.input_layernorm.weight": "pytorch_model-00012-of-00046.bin", - "language_model.model.layers.21.mlp.down_proj.weight": "pytorch_model-00012-of-00046.bin", - "language_model.model.layers.21.mlp.gate_proj.weight": "pytorch_model-00012-of-00046.bin", - "language_model.model.layers.21.mlp.up_proj.weight": "pytorch_model-00012-of-00046.bin", - "language_model.model.layers.21.post_attention_layernorm.weight": "pytorch_model-00012-of-00046.bin", - "language_model.model.layers.21.self_attn.k_proj.bias": "pytorch_model-00012-of-00046.bin", - "language_model.model.layers.21.self_attn.k_proj.weight": "pytorch_model-00012-of-00046.bin", - "language_model.model.layers.21.self_attn.o_proj.weight": "pytorch_model-00012-of-00046.bin", - "language_model.model.layers.21.self_attn.q_proj.bias": "pytorch_model-00012-of-00046.bin", - "language_model.model.layers.21.self_attn.q_proj.weight": "pytorch_model-00012-of-00046.bin", - "language_model.model.layers.21.self_attn.v_proj.bias": "pytorch_model-00012-of-00046.bin", - "language_model.model.layers.21.self_attn.v_proj.weight": "pytorch_model-00012-of-00046.bin", - "language_model.model.layers.22.input_layernorm.weight": "pytorch_model-00012-of-00046.bin", - "language_model.model.layers.22.mlp.down_proj.weight": "pytorch_model-00013-of-00046.bin", - "language_model.model.layers.22.mlp.gate_proj.weight": "pytorch_model-00013-of-00046.bin", - "language_model.model.layers.22.mlp.up_proj.weight": "pytorch_model-00013-of-00046.bin", - "language_model.model.layers.22.post_attention_layernorm.weight": "pytorch_model-00012-of-00046.bin", - "language_model.model.layers.22.self_attn.k_proj.bias": "pytorch_model-00013-of-00046.bin", - "language_model.model.layers.22.self_attn.k_proj.weight": "pytorch_model-00013-of-00046.bin", - "language_model.model.layers.22.self_attn.o_proj.weight": "pytorch_model-00013-of-00046.bin", - "language_model.model.layers.22.self_attn.q_proj.bias": "pytorch_model-00013-of-00046.bin", - "language_model.model.layers.22.self_attn.q_proj.weight": "pytorch_model-00013-of-00046.bin", - "language_model.model.layers.22.self_attn.v_proj.bias": "pytorch_model-00013-of-00046.bin", - "language_model.model.layers.22.self_attn.v_proj.weight": "pytorch_model-00013-of-00046.bin", - "language_model.model.layers.23.input_layernorm.weight": "pytorch_model-00013-of-00046.bin", - "language_model.model.layers.23.mlp.down_proj.weight": "pytorch_model-00013-of-00046.bin", - "language_model.model.layers.23.mlp.gate_proj.weight": "pytorch_model-00013-of-00046.bin", - "language_model.model.layers.23.mlp.up_proj.weight": "pytorch_model-00013-of-00046.bin", - "language_model.model.layers.23.post_attention_layernorm.weight": "pytorch_model-00013-of-00046.bin", - "language_model.model.layers.23.self_attn.k_proj.bias": "pytorch_model-00013-of-00046.bin", - "language_model.model.layers.23.self_attn.k_proj.weight": "pytorch_model-00013-of-00046.bin", - "language_model.model.layers.23.self_attn.o_proj.weight": "pytorch_model-00013-of-00046.bin", - "language_model.model.layers.23.self_attn.q_proj.bias": "pytorch_model-00013-of-00046.bin", - "language_model.model.layers.23.self_attn.q_proj.weight": "pytorch_model-00013-of-00046.bin", - "language_model.model.layers.23.self_attn.v_proj.bias": "pytorch_model-00013-of-00046.bin", - "language_model.model.layers.23.self_attn.v_proj.weight": "pytorch_model-00013-of-00046.bin", - "language_model.model.layers.24.input_layernorm.weight": "pytorch_model-00013-of-00046.bin", - "language_model.model.layers.24.mlp.down_proj.weight": "pytorch_model-00014-of-00046.bin", - "language_model.model.layers.24.mlp.gate_proj.weight": "pytorch_model-00014-of-00046.bin", - "language_model.model.layers.24.mlp.up_proj.weight": "pytorch_model-00014-of-00046.bin", - "language_model.model.layers.24.post_attention_layernorm.weight": "pytorch_model-00013-of-00046.bin", - "language_model.model.layers.24.self_attn.k_proj.bias": "pytorch_model-00014-of-00046.bin", - "language_model.model.layers.24.self_attn.k_proj.weight": "pytorch_model-00014-of-00046.bin", - "language_model.model.layers.24.self_attn.o_proj.weight": "pytorch_model-00014-of-00046.bin", - "language_model.model.layers.24.self_attn.q_proj.bias": "pytorch_model-00014-of-00046.bin", - "language_model.model.layers.24.self_attn.q_proj.weight": "pytorch_model-00014-of-00046.bin", - "language_model.model.layers.24.self_attn.v_proj.bias": "pytorch_model-00014-of-00046.bin", - "language_model.model.layers.24.self_attn.v_proj.weight": "pytorch_model-00014-of-00046.bin", - "language_model.model.layers.25.input_layernorm.weight": "pytorch_model-00014-of-00046.bin", - "language_model.model.layers.25.mlp.down_proj.weight": "pytorch_model-00014-of-00046.bin", - "language_model.model.layers.25.mlp.gate_proj.weight": "pytorch_model-00014-of-00046.bin", - "language_model.model.layers.25.mlp.up_proj.weight": "pytorch_model-00014-of-00046.bin", - "language_model.model.layers.25.post_attention_layernorm.weight": "pytorch_model-00014-of-00046.bin", - "language_model.model.layers.25.self_attn.k_proj.bias": "pytorch_model-00014-of-00046.bin", - "language_model.model.layers.25.self_attn.k_proj.weight": "pytorch_model-00014-of-00046.bin", - "language_model.model.layers.25.self_attn.o_proj.weight": "pytorch_model-00014-of-00046.bin", - "language_model.model.layers.25.self_attn.q_proj.bias": "pytorch_model-00014-of-00046.bin", - "language_model.model.layers.25.self_attn.q_proj.weight": "pytorch_model-00014-of-00046.bin", - "language_model.model.layers.25.self_attn.v_proj.bias": "pytorch_model-00014-of-00046.bin", - "language_model.model.layers.25.self_attn.v_proj.weight": "pytorch_model-00014-of-00046.bin", - "language_model.model.layers.26.input_layernorm.weight": "pytorch_model-00014-of-00046.bin", - "language_model.model.layers.26.mlp.down_proj.weight": "pytorch_model-00015-of-00046.bin", - "language_model.model.layers.26.mlp.gate_proj.weight": "pytorch_model-00015-of-00046.bin", - "language_model.model.layers.26.mlp.up_proj.weight": "pytorch_model-00015-of-00046.bin", - "language_model.model.layers.26.post_attention_layernorm.weight": "pytorch_model-00014-of-00046.bin", - "language_model.model.layers.26.self_attn.k_proj.bias": "pytorch_model-00015-of-00046.bin", - "language_model.model.layers.26.self_attn.k_proj.weight": "pytorch_model-00015-of-00046.bin", - "language_model.model.layers.26.self_attn.o_proj.weight": "pytorch_model-00015-of-00046.bin", - "language_model.model.layers.26.self_attn.q_proj.bias": "pytorch_model-00015-of-00046.bin", - "language_model.model.layers.26.self_attn.q_proj.weight": "pytorch_model-00015-of-00046.bin", - "language_model.model.layers.26.self_attn.v_proj.bias": "pytorch_model-00015-of-00046.bin", - "language_model.model.layers.26.self_attn.v_proj.weight": "pytorch_model-00015-of-00046.bin", - "language_model.model.layers.27.input_layernorm.weight": "pytorch_model-00015-of-00046.bin", - "language_model.model.layers.27.mlp.down_proj.weight": "pytorch_model-00015-of-00046.bin", - "language_model.model.layers.27.mlp.gate_proj.weight": "pytorch_model-00015-of-00046.bin", - "language_model.model.layers.27.mlp.up_proj.weight": "pytorch_model-00015-of-00046.bin", - "language_model.model.layers.27.post_attention_layernorm.weight": "pytorch_model-00015-of-00046.bin", - "language_model.model.layers.27.self_attn.k_proj.bias": "pytorch_model-00015-of-00046.bin", - "language_model.model.layers.27.self_attn.k_proj.weight": "pytorch_model-00015-of-00046.bin", - "language_model.model.layers.27.self_attn.o_proj.weight": "pytorch_model-00015-of-00046.bin", - "language_model.model.layers.27.self_attn.q_proj.bias": "pytorch_model-00015-of-00046.bin", - "language_model.model.layers.27.self_attn.q_proj.weight": "pytorch_model-00015-of-00046.bin", - "language_model.model.layers.27.self_attn.v_proj.bias": "pytorch_model-00015-of-00046.bin", - "language_model.model.layers.27.self_attn.v_proj.weight": "pytorch_model-00015-of-00046.bin", - "language_model.model.layers.28.input_layernorm.weight": "pytorch_model-00015-of-00046.bin", - "language_model.model.layers.28.mlp.down_proj.weight": "pytorch_model-00016-of-00046.bin", - "language_model.model.layers.28.mlp.gate_proj.weight": "pytorch_model-00016-of-00046.bin", - "language_model.model.layers.28.mlp.up_proj.weight": "pytorch_model-00016-of-00046.bin", - "language_model.model.layers.28.post_attention_layernorm.weight": "pytorch_model-00015-of-00046.bin", - "language_model.model.layers.28.self_attn.k_proj.bias": "pytorch_model-00016-of-00046.bin", - "language_model.model.layers.28.self_attn.k_proj.weight": "pytorch_model-00016-of-00046.bin", - "language_model.model.layers.28.self_attn.o_proj.weight": "pytorch_model-00016-of-00046.bin", - "language_model.model.layers.28.self_attn.q_proj.bias": "pytorch_model-00016-of-00046.bin", - "language_model.model.layers.28.self_attn.q_proj.weight": "pytorch_model-00016-of-00046.bin", - "language_model.model.layers.28.self_attn.v_proj.bias": "pytorch_model-00016-of-00046.bin", - "language_model.model.layers.28.self_attn.v_proj.weight": "pytorch_model-00016-of-00046.bin", - "language_model.model.layers.29.input_layernorm.weight": "pytorch_model-00016-of-00046.bin", - "language_model.model.layers.29.mlp.down_proj.weight": "pytorch_model-00016-of-00046.bin", - "language_model.model.layers.29.mlp.gate_proj.weight": "pytorch_model-00016-of-00046.bin", - "language_model.model.layers.29.mlp.up_proj.weight": "pytorch_model-00016-of-00046.bin", - "language_model.model.layers.29.post_attention_layernorm.weight": "pytorch_model-00016-of-00046.bin", - "language_model.model.layers.29.self_attn.k_proj.bias": "pytorch_model-00016-of-00046.bin", - "language_model.model.layers.29.self_attn.k_proj.weight": "pytorch_model-00016-of-00046.bin", - "language_model.model.layers.29.self_attn.o_proj.weight": "pytorch_model-00016-of-00046.bin", - "language_model.model.layers.29.self_attn.q_proj.bias": "pytorch_model-00016-of-00046.bin", - "language_model.model.layers.29.self_attn.q_proj.weight": "pytorch_model-00016-of-00046.bin", - "language_model.model.layers.29.self_attn.v_proj.bias": "pytorch_model-00016-of-00046.bin", - "language_model.model.layers.29.self_attn.v_proj.weight": "pytorch_model-00016-of-00046.bin", - "language_model.model.layers.3.input_layernorm.weight": "pytorch_model-00003-of-00046.bin", - "language_model.model.layers.3.mlp.down_proj.weight": "pytorch_model-00003-of-00046.bin", - "language_model.model.layers.3.mlp.gate_proj.weight": "pytorch_model-00003-of-00046.bin", - "language_model.model.layers.3.mlp.up_proj.weight": "pytorch_model-00003-of-00046.bin", - "language_model.model.layers.3.post_attention_layernorm.weight": "pytorch_model-00003-of-00046.bin", - "language_model.model.layers.3.self_attn.k_proj.bias": "pytorch_model-00003-of-00046.bin", - "language_model.model.layers.3.self_attn.k_proj.weight": "pytorch_model-00003-of-00046.bin", - "language_model.model.layers.3.self_attn.o_proj.weight": "pytorch_model-00003-of-00046.bin", - "language_model.model.layers.3.self_attn.q_proj.bias": "pytorch_model-00003-of-00046.bin", - "language_model.model.layers.3.self_attn.q_proj.weight": "pytorch_model-00003-of-00046.bin", - "language_model.model.layers.3.self_attn.v_proj.bias": "pytorch_model-00003-of-00046.bin", - "language_model.model.layers.3.self_attn.v_proj.weight": "pytorch_model-00003-of-00046.bin", - "language_model.model.layers.30.input_layernorm.weight": "pytorch_model-00016-of-00046.bin", - "language_model.model.layers.30.mlp.down_proj.weight": "pytorch_model-00017-of-00046.bin", - "language_model.model.layers.30.mlp.gate_proj.weight": "pytorch_model-00017-of-00046.bin", - "language_model.model.layers.30.mlp.up_proj.weight": "pytorch_model-00017-of-00046.bin", - "language_model.model.layers.30.post_attention_layernorm.weight": "pytorch_model-00016-of-00046.bin", - "language_model.model.layers.30.self_attn.k_proj.bias": "pytorch_model-00017-of-00046.bin", - "language_model.model.layers.30.self_attn.k_proj.weight": "pytorch_model-00017-of-00046.bin", - "language_model.model.layers.30.self_attn.o_proj.weight": "pytorch_model-00017-of-00046.bin", - "language_model.model.layers.30.self_attn.q_proj.bias": "pytorch_model-00017-of-00046.bin", - "language_model.model.layers.30.self_attn.q_proj.weight": "pytorch_model-00017-of-00046.bin", - "language_model.model.layers.30.self_attn.v_proj.bias": "pytorch_model-00017-of-00046.bin", - "language_model.model.layers.30.self_attn.v_proj.weight": "pytorch_model-00017-of-00046.bin", - "language_model.model.layers.31.input_layernorm.weight": "pytorch_model-00017-of-00046.bin", - "language_model.model.layers.31.mlp.down_proj.weight": "pytorch_model-00017-of-00046.bin", - "language_model.model.layers.31.mlp.gate_proj.weight": "pytorch_model-00017-of-00046.bin", - "language_model.model.layers.31.mlp.up_proj.weight": "pytorch_model-00017-of-00046.bin", - "language_model.model.layers.31.post_attention_layernorm.weight": "pytorch_model-00017-of-00046.bin", - "language_model.model.layers.31.self_attn.k_proj.bias": "pytorch_model-00017-of-00046.bin", - "language_model.model.layers.31.self_attn.k_proj.weight": "pytorch_model-00017-of-00046.bin", - "language_model.model.layers.31.self_attn.o_proj.weight": "pytorch_model-00017-of-00046.bin", - "language_model.model.layers.31.self_attn.q_proj.bias": "pytorch_model-00017-of-00046.bin", - "language_model.model.layers.31.self_attn.q_proj.weight": "pytorch_model-00017-of-00046.bin", - "language_model.model.layers.31.self_attn.v_proj.bias": "pytorch_model-00017-of-00046.bin", - "language_model.model.layers.31.self_attn.v_proj.weight": "pytorch_model-00017-of-00046.bin", - "language_model.model.layers.32.input_layernorm.weight": "pytorch_model-00017-of-00046.bin", - "language_model.model.layers.32.mlp.down_proj.weight": "pytorch_model-00018-of-00046.bin", - "language_model.model.layers.32.mlp.gate_proj.weight": "pytorch_model-00018-of-00046.bin", - "language_model.model.layers.32.mlp.up_proj.weight": "pytorch_model-00018-of-00046.bin", - "language_model.model.layers.32.post_attention_layernorm.weight": "pytorch_model-00017-of-00046.bin", - "language_model.model.layers.32.self_attn.k_proj.bias": "pytorch_model-00018-of-00046.bin", - "language_model.model.layers.32.self_attn.k_proj.weight": "pytorch_model-00018-of-00046.bin", - "language_model.model.layers.32.self_attn.o_proj.weight": "pytorch_model-00018-of-00046.bin", - "language_model.model.layers.32.self_attn.q_proj.bias": "pytorch_model-00018-of-00046.bin", - "language_model.model.layers.32.self_attn.q_proj.weight": "pytorch_model-00018-of-00046.bin", - "language_model.model.layers.32.self_attn.v_proj.bias": "pytorch_model-00018-of-00046.bin", - "language_model.model.layers.32.self_attn.v_proj.weight": "pytorch_model-00018-of-00046.bin", - "language_model.model.layers.33.input_layernorm.weight": "pytorch_model-00018-of-00046.bin", - "language_model.model.layers.33.mlp.down_proj.weight": "pytorch_model-00018-of-00046.bin", - "language_model.model.layers.33.mlp.gate_proj.weight": "pytorch_model-00018-of-00046.bin", - "language_model.model.layers.33.mlp.up_proj.weight": "pytorch_model-00018-of-00046.bin", - "language_model.model.layers.33.post_attention_layernorm.weight": "pytorch_model-00018-of-00046.bin", - "language_model.model.layers.33.self_attn.k_proj.bias": "pytorch_model-00018-of-00046.bin", - "language_model.model.layers.33.self_attn.k_proj.weight": "pytorch_model-00018-of-00046.bin", - "language_model.model.layers.33.self_attn.o_proj.weight": "pytorch_model-00018-of-00046.bin", - "language_model.model.layers.33.self_attn.q_proj.bias": "pytorch_model-00018-of-00046.bin", - "language_model.model.layers.33.self_attn.q_proj.weight": "pytorch_model-00018-of-00046.bin", - "language_model.model.layers.33.self_attn.v_proj.bias": "pytorch_model-00018-of-00046.bin", - "language_model.model.layers.33.self_attn.v_proj.weight": "pytorch_model-00018-of-00046.bin", - "language_model.model.layers.34.input_layernorm.weight": "pytorch_model-00018-of-00046.bin", - "language_model.model.layers.34.mlp.down_proj.weight": "pytorch_model-00019-of-00046.bin", - "language_model.model.layers.34.mlp.gate_proj.weight": "pytorch_model-00019-of-00046.bin", - "language_model.model.layers.34.mlp.up_proj.weight": "pytorch_model-00019-of-00046.bin", - "language_model.model.layers.34.post_attention_layernorm.weight": "pytorch_model-00018-of-00046.bin", - "language_model.model.layers.34.self_attn.k_proj.bias": "pytorch_model-00019-of-00046.bin", - "language_model.model.layers.34.self_attn.k_proj.weight": "pytorch_model-00019-of-00046.bin", - "language_model.model.layers.34.self_attn.o_proj.weight": "pytorch_model-00019-of-00046.bin", - "language_model.model.layers.34.self_attn.q_proj.bias": "pytorch_model-00019-of-00046.bin", - "language_model.model.layers.34.self_attn.q_proj.weight": "pytorch_model-00019-of-00046.bin", - "language_model.model.layers.34.self_attn.v_proj.bias": "pytorch_model-00019-of-00046.bin", - "language_model.model.layers.34.self_attn.v_proj.weight": "pytorch_model-00019-of-00046.bin", - "language_model.model.layers.35.input_layernorm.weight": "pytorch_model-00019-of-00046.bin", - "language_model.model.layers.35.mlp.down_proj.weight": "pytorch_model-00019-of-00046.bin", - "language_model.model.layers.35.mlp.gate_proj.weight": "pytorch_model-00019-of-00046.bin", - "language_model.model.layers.35.mlp.up_proj.weight": "pytorch_model-00019-of-00046.bin", - "language_model.model.layers.35.post_attention_layernorm.weight": "pytorch_model-00019-of-00046.bin", - "language_model.model.layers.35.self_attn.k_proj.bias": "pytorch_model-00019-of-00046.bin", - "language_model.model.layers.35.self_attn.k_proj.weight": "pytorch_model-00019-of-00046.bin", - "language_model.model.layers.35.self_attn.o_proj.weight": "pytorch_model-00019-of-00046.bin", - "language_model.model.layers.35.self_attn.q_proj.bias": "pytorch_model-00019-of-00046.bin", - "language_model.model.layers.35.self_attn.q_proj.weight": "pytorch_model-00019-of-00046.bin", - "language_model.model.layers.35.self_attn.v_proj.bias": "pytorch_model-00019-of-00046.bin", - "language_model.model.layers.35.self_attn.v_proj.weight": "pytorch_model-00019-of-00046.bin", - "language_model.model.layers.36.input_layernorm.weight": "pytorch_model-00019-of-00046.bin", - "language_model.model.layers.36.mlp.down_proj.weight": "pytorch_model-00020-of-00046.bin", - "language_model.model.layers.36.mlp.gate_proj.weight": "pytorch_model-00020-of-00046.bin", - "language_model.model.layers.36.mlp.up_proj.weight": "pytorch_model-00020-of-00046.bin", - "language_model.model.layers.36.post_attention_layernorm.weight": "pytorch_model-00019-of-00046.bin", - "language_model.model.layers.36.self_attn.k_proj.bias": "pytorch_model-00020-of-00046.bin", - "language_model.model.layers.36.self_attn.k_proj.weight": "pytorch_model-00020-of-00046.bin", - "language_model.model.layers.36.self_attn.o_proj.weight": "pytorch_model-00020-of-00046.bin", - "language_model.model.layers.36.self_attn.q_proj.bias": "pytorch_model-00020-of-00046.bin", - "language_model.model.layers.36.self_attn.q_proj.weight": "pytorch_model-00020-of-00046.bin", - "language_model.model.layers.36.self_attn.v_proj.bias": "pytorch_model-00020-of-00046.bin", - "language_model.model.layers.36.self_attn.v_proj.weight": "pytorch_model-00020-of-00046.bin", - "language_model.model.layers.37.input_layernorm.weight": "pytorch_model-00020-of-00046.bin", - "language_model.model.layers.37.mlp.down_proj.weight": "pytorch_model-00020-of-00046.bin", - "language_model.model.layers.37.mlp.gate_proj.weight": "pytorch_model-00020-of-00046.bin", - "language_model.model.layers.37.mlp.up_proj.weight": "pytorch_model-00020-of-00046.bin", - "language_model.model.layers.37.post_attention_layernorm.weight": "pytorch_model-00020-of-00046.bin", - "language_model.model.layers.37.self_attn.k_proj.bias": "pytorch_model-00020-of-00046.bin", - "language_model.model.layers.37.self_attn.k_proj.weight": "pytorch_model-00020-of-00046.bin", - "language_model.model.layers.37.self_attn.o_proj.weight": "pytorch_model-00020-of-00046.bin", - "language_model.model.layers.37.self_attn.q_proj.bias": "pytorch_model-00020-of-00046.bin", - "language_model.model.layers.37.self_attn.q_proj.weight": "pytorch_model-00020-of-00046.bin", - "language_model.model.layers.37.self_attn.v_proj.bias": "pytorch_model-00020-of-00046.bin", - "language_model.model.layers.37.self_attn.v_proj.weight": "pytorch_model-00020-of-00046.bin", - "language_model.model.layers.38.input_layernorm.weight": "pytorch_model-00020-of-00046.bin", - "language_model.model.layers.38.mlp.down_proj.weight": "pytorch_model-00021-of-00046.bin", - "language_model.model.layers.38.mlp.gate_proj.weight": "pytorch_model-00021-of-00046.bin", - "language_model.model.layers.38.mlp.up_proj.weight": "pytorch_model-00021-of-00046.bin", - "language_model.model.layers.38.post_attention_layernorm.weight": "pytorch_model-00020-of-00046.bin", - "language_model.model.layers.38.self_attn.k_proj.bias": "pytorch_model-00021-of-00046.bin", - "language_model.model.layers.38.self_attn.k_proj.weight": "pytorch_model-00021-of-00046.bin", - "language_model.model.layers.38.self_attn.o_proj.weight": "pytorch_model-00021-of-00046.bin", - "language_model.model.layers.38.self_attn.q_proj.bias": "pytorch_model-00021-of-00046.bin", - "language_model.model.layers.38.self_attn.q_proj.weight": "pytorch_model-00021-of-00046.bin", - "language_model.model.layers.38.self_attn.v_proj.bias": "pytorch_model-00021-of-00046.bin", - "language_model.model.layers.38.self_attn.v_proj.weight": "pytorch_model-00021-of-00046.bin", - "language_model.model.layers.39.input_layernorm.weight": "pytorch_model-00021-of-00046.bin", - "language_model.model.layers.39.mlp.down_proj.weight": "pytorch_model-00021-of-00046.bin", - "language_model.model.layers.39.mlp.gate_proj.weight": "pytorch_model-00021-of-00046.bin", - "language_model.model.layers.39.mlp.up_proj.weight": "pytorch_model-00021-of-00046.bin", - "language_model.model.layers.39.post_attention_layernorm.weight": "pytorch_model-00021-of-00046.bin", - "language_model.model.layers.39.self_attn.k_proj.bias": "pytorch_model-00021-of-00046.bin", - "language_model.model.layers.39.self_attn.k_proj.weight": "pytorch_model-00021-of-00046.bin", - "language_model.model.layers.39.self_attn.o_proj.weight": "pytorch_model-00021-of-00046.bin", - "language_model.model.layers.39.self_attn.q_proj.bias": "pytorch_model-00021-of-00046.bin", - "language_model.model.layers.39.self_attn.q_proj.weight": "pytorch_model-00021-of-00046.bin", - "language_model.model.layers.39.self_attn.v_proj.bias": "pytorch_model-00021-of-00046.bin", - "language_model.model.layers.39.self_attn.v_proj.weight": "pytorch_model-00021-of-00046.bin", - "language_model.model.layers.4.input_layernorm.weight": "pytorch_model-00003-of-00046.bin", - "language_model.model.layers.4.mlp.down_proj.weight": "pytorch_model-00004-of-00046.bin", - "language_model.model.layers.4.mlp.gate_proj.weight": "pytorch_model-00004-of-00046.bin", - "language_model.model.layers.4.mlp.up_proj.weight": "pytorch_model-00004-of-00046.bin", - "language_model.model.layers.4.post_attention_layernorm.weight": "pytorch_model-00003-of-00046.bin", - "language_model.model.layers.4.self_attn.k_proj.bias": "pytorch_model-00004-of-00046.bin", - "language_model.model.layers.4.self_attn.k_proj.weight": "pytorch_model-00004-of-00046.bin", - "language_model.model.layers.4.self_attn.o_proj.weight": "pytorch_model-00004-of-00046.bin", - "language_model.model.layers.4.self_attn.q_proj.bias": "pytorch_model-00004-of-00046.bin", - "language_model.model.layers.4.self_attn.q_proj.weight": "pytorch_model-00004-of-00046.bin", - "language_model.model.layers.4.self_attn.v_proj.bias": "pytorch_model-00004-of-00046.bin", - "language_model.model.layers.4.self_attn.v_proj.weight": "pytorch_model-00004-of-00046.bin", - "language_model.model.layers.40.input_layernorm.weight": "pytorch_model-00021-of-00046.bin", - "language_model.model.layers.40.mlp.down_proj.weight": "pytorch_model-00022-of-00046.bin", - "language_model.model.layers.40.mlp.gate_proj.weight": "pytorch_model-00022-of-00046.bin", - "language_model.model.layers.40.mlp.up_proj.weight": "pytorch_model-00022-of-00046.bin", - "language_model.model.layers.40.post_attention_layernorm.weight": "pytorch_model-00021-of-00046.bin", - "language_model.model.layers.40.self_attn.k_proj.bias": "pytorch_model-00022-of-00046.bin", - "language_model.model.layers.40.self_attn.k_proj.weight": "pytorch_model-00022-of-00046.bin", - "language_model.model.layers.40.self_attn.o_proj.weight": "pytorch_model-00022-of-00046.bin", - "language_model.model.layers.40.self_attn.q_proj.bias": "pytorch_model-00022-of-00046.bin", - "language_model.model.layers.40.self_attn.q_proj.weight": "pytorch_model-00022-of-00046.bin", - "language_model.model.layers.40.self_attn.v_proj.bias": "pytorch_model-00022-of-00046.bin", - "language_model.model.layers.40.self_attn.v_proj.weight": "pytorch_model-00022-of-00046.bin", - "language_model.model.layers.41.input_layernorm.weight": "pytorch_model-00022-of-00046.bin", - "language_model.model.layers.41.mlp.down_proj.weight": "pytorch_model-00022-of-00046.bin", - "language_model.model.layers.41.mlp.gate_proj.weight": "pytorch_model-00022-of-00046.bin", - "language_model.model.layers.41.mlp.up_proj.weight": "pytorch_model-00022-of-00046.bin", - "language_model.model.layers.41.post_attention_layernorm.weight": "pytorch_model-00022-of-00046.bin", - "language_model.model.layers.41.self_attn.k_proj.bias": "pytorch_model-00022-of-00046.bin", - "language_model.model.layers.41.self_attn.k_proj.weight": "pytorch_model-00022-of-00046.bin", - "language_model.model.layers.41.self_attn.o_proj.weight": "pytorch_model-00022-of-00046.bin", - "language_model.model.layers.41.self_attn.q_proj.bias": "pytorch_model-00022-of-00046.bin", - "language_model.model.layers.41.self_attn.q_proj.weight": "pytorch_model-00022-of-00046.bin", - "language_model.model.layers.41.self_attn.v_proj.bias": "pytorch_model-00022-of-00046.bin", - "language_model.model.layers.41.self_attn.v_proj.weight": "pytorch_model-00022-of-00046.bin", - "language_model.model.layers.42.input_layernorm.weight": "pytorch_model-00022-of-00046.bin", - "language_model.model.layers.42.mlp.down_proj.weight": "pytorch_model-00023-of-00046.bin", - "language_model.model.layers.42.mlp.gate_proj.weight": "pytorch_model-00023-of-00046.bin", - "language_model.model.layers.42.mlp.up_proj.weight": "pytorch_model-00023-of-00046.bin", - "language_model.model.layers.42.post_attention_layernorm.weight": "pytorch_model-00022-of-00046.bin", - "language_model.model.layers.42.self_attn.k_proj.bias": "pytorch_model-00023-of-00046.bin", - "language_model.model.layers.42.self_attn.k_proj.weight": "pytorch_model-00023-of-00046.bin", - "language_model.model.layers.42.self_attn.o_proj.weight": "pytorch_model-00023-of-00046.bin", - "language_model.model.layers.42.self_attn.q_proj.bias": "pytorch_model-00023-of-00046.bin", - "language_model.model.layers.42.self_attn.q_proj.weight": "pytorch_model-00023-of-00046.bin", - "language_model.model.layers.42.self_attn.v_proj.bias": "pytorch_model-00023-of-00046.bin", - "language_model.model.layers.42.self_attn.v_proj.weight": "pytorch_model-00023-of-00046.bin", - "language_model.model.layers.43.input_layernorm.weight": "pytorch_model-00023-of-00046.bin", - "language_model.model.layers.43.mlp.down_proj.weight": "pytorch_model-00023-of-00046.bin", - "language_model.model.layers.43.mlp.gate_proj.weight": "pytorch_model-00023-of-00046.bin", - "language_model.model.layers.43.mlp.up_proj.weight": "pytorch_model-00023-of-00046.bin", - "language_model.model.layers.43.post_attention_layernorm.weight": "pytorch_model-00023-of-00046.bin", - "language_model.model.layers.43.self_attn.k_proj.bias": "pytorch_model-00023-of-00046.bin", - "language_model.model.layers.43.self_attn.k_proj.weight": "pytorch_model-00023-of-00046.bin", - "language_model.model.layers.43.self_attn.o_proj.weight": "pytorch_model-00023-of-00046.bin", - "language_model.model.layers.43.self_attn.q_proj.bias": "pytorch_model-00023-of-00046.bin", - "language_model.model.layers.43.self_attn.q_proj.weight": "pytorch_model-00023-of-00046.bin", - "language_model.model.layers.43.self_attn.v_proj.bias": "pytorch_model-00023-of-00046.bin", - "language_model.model.layers.43.self_attn.v_proj.weight": "pytorch_model-00023-of-00046.bin", - "language_model.model.layers.44.input_layernorm.weight": "pytorch_model-00023-of-00046.bin", - "language_model.model.layers.44.mlp.down_proj.weight": "pytorch_model-00024-of-00046.bin", - "language_model.model.layers.44.mlp.gate_proj.weight": "pytorch_model-00024-of-00046.bin", - "language_model.model.layers.44.mlp.up_proj.weight": "pytorch_model-00024-of-00046.bin", - "language_model.model.layers.44.post_attention_layernorm.weight": "pytorch_model-00023-of-00046.bin", - "language_model.model.layers.44.self_attn.k_proj.bias": "pytorch_model-00024-of-00046.bin", - "language_model.model.layers.44.self_attn.k_proj.weight": "pytorch_model-00024-of-00046.bin", - "language_model.model.layers.44.self_attn.o_proj.weight": "pytorch_model-00024-of-00046.bin", - "language_model.model.layers.44.self_attn.q_proj.bias": "pytorch_model-00024-of-00046.bin", - "language_model.model.layers.44.self_attn.q_proj.weight": "pytorch_model-00024-of-00046.bin", - "language_model.model.layers.44.self_attn.v_proj.bias": "pytorch_model-00024-of-00046.bin", - "language_model.model.layers.44.self_attn.v_proj.weight": "pytorch_model-00024-of-00046.bin", - "language_model.model.layers.45.input_layernorm.weight": "pytorch_model-00024-of-00046.bin", - "language_model.model.layers.45.mlp.down_proj.weight": "pytorch_model-00024-of-00046.bin", - "language_model.model.layers.45.mlp.gate_proj.weight": "pytorch_model-00024-of-00046.bin", - "language_model.model.layers.45.mlp.up_proj.weight": "pytorch_model-00024-of-00046.bin", - "language_model.model.layers.45.post_attention_layernorm.weight": "pytorch_model-00024-of-00046.bin", - "language_model.model.layers.45.self_attn.k_proj.bias": "pytorch_model-00024-of-00046.bin", - "language_model.model.layers.45.self_attn.k_proj.weight": "pytorch_model-00024-of-00046.bin", - "language_model.model.layers.45.self_attn.o_proj.weight": "pytorch_model-00024-of-00046.bin", - "language_model.model.layers.45.self_attn.q_proj.bias": "pytorch_model-00024-of-00046.bin", - "language_model.model.layers.45.self_attn.q_proj.weight": "pytorch_model-00024-of-00046.bin", - "language_model.model.layers.45.self_attn.v_proj.bias": "pytorch_model-00024-of-00046.bin", - "language_model.model.layers.45.self_attn.v_proj.weight": "pytorch_model-00024-of-00046.bin", - "language_model.model.layers.46.input_layernorm.weight": "pytorch_model-00024-of-00046.bin", - "language_model.model.layers.46.mlp.down_proj.weight": "pytorch_model-00025-of-00046.bin", - "language_model.model.layers.46.mlp.gate_proj.weight": "pytorch_model-00025-of-00046.bin", - "language_model.model.layers.46.mlp.up_proj.weight": "pytorch_model-00025-of-00046.bin", - "language_model.model.layers.46.post_attention_layernorm.weight": "pytorch_model-00024-of-00046.bin", - "language_model.model.layers.46.self_attn.k_proj.bias": "pytorch_model-00025-of-00046.bin", - "language_model.model.layers.46.self_attn.k_proj.weight": "pytorch_model-00025-of-00046.bin", - "language_model.model.layers.46.self_attn.o_proj.weight": "pytorch_model-00025-of-00046.bin", - "language_model.model.layers.46.self_attn.q_proj.bias": "pytorch_model-00025-of-00046.bin", - "language_model.model.layers.46.self_attn.q_proj.weight": "pytorch_model-00025-of-00046.bin", - "language_model.model.layers.46.self_attn.v_proj.bias": "pytorch_model-00025-of-00046.bin", - "language_model.model.layers.46.self_attn.v_proj.weight": "pytorch_model-00025-of-00046.bin", - "language_model.model.layers.47.input_layernorm.weight": "pytorch_model-00025-of-00046.bin", - "language_model.model.layers.47.mlp.down_proj.weight": "pytorch_model-00025-of-00046.bin", - "language_model.model.layers.47.mlp.gate_proj.weight": "pytorch_model-00025-of-00046.bin", - "language_model.model.layers.47.mlp.up_proj.weight": "pytorch_model-00025-of-00046.bin", - "language_model.model.layers.47.post_attention_layernorm.weight": "pytorch_model-00025-of-00046.bin", - "language_model.model.layers.47.self_attn.k_proj.bias": "pytorch_model-00025-of-00046.bin", - "language_model.model.layers.47.self_attn.k_proj.weight": "pytorch_model-00025-of-00046.bin", - "language_model.model.layers.47.self_attn.o_proj.weight": "pytorch_model-00025-of-00046.bin", - "language_model.model.layers.47.self_attn.q_proj.bias": "pytorch_model-00025-of-00046.bin", - "language_model.model.layers.47.self_attn.q_proj.weight": "pytorch_model-00025-of-00046.bin", - "language_model.model.layers.47.self_attn.v_proj.bias": "pytorch_model-00025-of-00046.bin", - "language_model.model.layers.47.self_attn.v_proj.weight": "pytorch_model-00025-of-00046.bin", - "language_model.model.layers.48.input_layernorm.weight": "pytorch_model-00025-of-00046.bin", - "language_model.model.layers.48.mlp.down_proj.weight": "pytorch_model-00026-of-00046.bin", - "language_model.model.layers.48.mlp.gate_proj.weight": "pytorch_model-00026-of-00046.bin", - "language_model.model.layers.48.mlp.up_proj.weight": "pytorch_model-00026-of-00046.bin", - "language_model.model.layers.48.post_attention_layernorm.weight": "pytorch_model-00025-of-00046.bin", - "language_model.model.layers.48.self_attn.k_proj.bias": "pytorch_model-00026-of-00046.bin", - "language_model.model.layers.48.self_attn.k_proj.weight": "pytorch_model-00026-of-00046.bin", - "language_model.model.layers.48.self_attn.o_proj.weight": "pytorch_model-00026-of-00046.bin", - "language_model.model.layers.48.self_attn.q_proj.bias": "pytorch_model-00026-of-00046.bin", - "language_model.model.layers.48.self_attn.q_proj.weight": "pytorch_model-00026-of-00046.bin", - "language_model.model.layers.48.self_attn.v_proj.bias": "pytorch_model-00026-of-00046.bin", - "language_model.model.layers.48.self_attn.v_proj.weight": "pytorch_model-00026-of-00046.bin", - "language_model.model.layers.49.input_layernorm.weight": "pytorch_model-00026-of-00046.bin", - "language_model.model.layers.49.mlp.down_proj.weight": "pytorch_model-00026-of-00046.bin", - "language_model.model.layers.49.mlp.gate_proj.weight": "pytorch_model-00026-of-00046.bin", - "language_model.model.layers.49.mlp.up_proj.weight": "pytorch_model-00026-of-00046.bin", - "language_model.model.layers.49.post_attention_layernorm.weight": "pytorch_model-00026-of-00046.bin", - "language_model.model.layers.49.self_attn.k_proj.bias": "pytorch_model-00026-of-00046.bin", - "language_model.model.layers.49.self_attn.k_proj.weight": "pytorch_model-00026-of-00046.bin", - "language_model.model.layers.49.self_attn.o_proj.weight": "pytorch_model-00026-of-00046.bin", - "language_model.model.layers.49.self_attn.q_proj.bias": "pytorch_model-00026-of-00046.bin", - "language_model.model.layers.49.self_attn.q_proj.weight": "pytorch_model-00026-of-00046.bin", - "language_model.model.layers.49.self_attn.v_proj.bias": "pytorch_model-00026-of-00046.bin", - "language_model.model.layers.49.self_attn.v_proj.weight": "pytorch_model-00026-of-00046.bin", - "language_model.model.layers.5.input_layernorm.weight": "pytorch_model-00004-of-00046.bin", - "language_model.model.layers.5.mlp.down_proj.weight": "pytorch_model-00004-of-00046.bin", - "language_model.model.layers.5.mlp.gate_proj.weight": "pytorch_model-00004-of-00046.bin", - "language_model.model.layers.5.mlp.up_proj.weight": "pytorch_model-00004-of-00046.bin", - "language_model.model.layers.5.post_attention_layernorm.weight": "pytorch_model-00004-of-00046.bin", - "language_model.model.layers.5.self_attn.k_proj.bias": "pytorch_model-00004-of-00046.bin", - "language_model.model.layers.5.self_attn.k_proj.weight": "pytorch_model-00004-of-00046.bin", - "language_model.model.layers.5.self_attn.o_proj.weight": "pytorch_model-00004-of-00046.bin", - "language_model.model.layers.5.self_attn.q_proj.bias": "pytorch_model-00004-of-00046.bin", - "language_model.model.layers.5.self_attn.q_proj.weight": "pytorch_model-00004-of-00046.bin", - "language_model.model.layers.5.self_attn.v_proj.bias": "pytorch_model-00004-of-00046.bin", - "language_model.model.layers.5.self_attn.v_proj.weight": "pytorch_model-00004-of-00046.bin", - "language_model.model.layers.50.input_layernorm.weight": "pytorch_model-00026-of-00046.bin", - "language_model.model.layers.50.mlp.down_proj.weight": "pytorch_model-00027-of-00046.bin", - "language_model.model.layers.50.mlp.gate_proj.weight": "pytorch_model-00027-of-00046.bin", - "language_model.model.layers.50.mlp.up_proj.weight": "pytorch_model-00027-of-00046.bin", - "language_model.model.layers.50.post_attention_layernorm.weight": "pytorch_model-00026-of-00046.bin", - "language_model.model.layers.50.self_attn.k_proj.bias": "pytorch_model-00027-of-00046.bin", - "language_model.model.layers.50.self_attn.k_proj.weight": "pytorch_model-00027-of-00046.bin", - "language_model.model.layers.50.self_attn.o_proj.weight": "pytorch_model-00027-of-00046.bin", - "language_model.model.layers.50.self_attn.q_proj.bias": "pytorch_model-00027-of-00046.bin", - "language_model.model.layers.50.self_attn.q_proj.weight": "pytorch_model-00027-of-00046.bin", - "language_model.model.layers.50.self_attn.v_proj.bias": "pytorch_model-00027-of-00046.bin", - "language_model.model.layers.50.self_attn.v_proj.weight": "pytorch_model-00027-of-00046.bin", - "language_model.model.layers.51.input_layernorm.weight": "pytorch_model-00027-of-00046.bin", - "language_model.model.layers.51.mlp.down_proj.weight": "pytorch_model-00027-of-00046.bin", - "language_model.model.layers.51.mlp.gate_proj.weight": "pytorch_model-00027-of-00046.bin", - "language_model.model.layers.51.mlp.up_proj.weight": "pytorch_model-00027-of-00046.bin", - "language_model.model.layers.51.post_attention_layernorm.weight": "pytorch_model-00027-of-00046.bin", - "language_model.model.layers.51.self_attn.k_proj.bias": "pytorch_model-00027-of-00046.bin", - "language_model.model.layers.51.self_attn.k_proj.weight": "pytorch_model-00027-of-00046.bin", - "language_model.model.layers.51.self_attn.o_proj.weight": "pytorch_model-00027-of-00046.bin", - "language_model.model.layers.51.self_attn.q_proj.bias": "pytorch_model-00027-of-00046.bin", - "language_model.model.layers.51.self_attn.q_proj.weight": "pytorch_model-00027-of-00046.bin", - "language_model.model.layers.51.self_attn.v_proj.bias": "pytorch_model-00027-of-00046.bin", - "language_model.model.layers.51.self_attn.v_proj.weight": "pytorch_model-00027-of-00046.bin", - "language_model.model.layers.52.input_layernorm.weight": "pytorch_model-00027-of-00046.bin", - "language_model.model.layers.52.mlp.down_proj.weight": "pytorch_model-00028-of-00046.bin", - "language_model.model.layers.52.mlp.gate_proj.weight": "pytorch_model-00028-of-00046.bin", - "language_model.model.layers.52.mlp.up_proj.weight": "pytorch_model-00028-of-00046.bin", - "language_model.model.layers.52.post_attention_layernorm.weight": "pytorch_model-00027-of-00046.bin", - "language_model.model.layers.52.self_attn.k_proj.bias": "pytorch_model-00028-of-00046.bin", - "language_model.model.layers.52.self_attn.k_proj.weight": "pytorch_model-00028-of-00046.bin", - "language_model.model.layers.52.self_attn.o_proj.weight": "pytorch_model-00028-of-00046.bin", - "language_model.model.layers.52.self_attn.q_proj.bias": "pytorch_model-00028-of-00046.bin", - "language_model.model.layers.52.self_attn.q_proj.weight": "pytorch_model-00028-of-00046.bin", - "language_model.model.layers.52.self_attn.v_proj.bias": "pytorch_model-00028-of-00046.bin", - "language_model.model.layers.52.self_attn.v_proj.weight": "pytorch_model-00028-of-00046.bin", - "language_model.model.layers.53.input_layernorm.weight": "pytorch_model-00028-of-00046.bin", - "language_model.model.layers.53.mlp.down_proj.weight": "pytorch_model-00028-of-00046.bin", - "language_model.model.layers.53.mlp.gate_proj.weight": "pytorch_model-00028-of-00046.bin", - "language_model.model.layers.53.mlp.up_proj.weight": "pytorch_model-00028-of-00046.bin", - "language_model.model.layers.53.post_attention_layernorm.weight": "pytorch_model-00028-of-00046.bin", - "language_model.model.layers.53.self_attn.k_proj.bias": "pytorch_model-00028-of-00046.bin", - "language_model.model.layers.53.self_attn.k_proj.weight": "pytorch_model-00028-of-00046.bin", - "language_model.model.layers.53.self_attn.o_proj.weight": "pytorch_model-00028-of-00046.bin", - "language_model.model.layers.53.self_attn.q_proj.bias": "pytorch_model-00028-of-00046.bin", - "language_model.model.layers.53.self_attn.q_proj.weight": "pytorch_model-00028-of-00046.bin", - "language_model.model.layers.53.self_attn.v_proj.bias": "pytorch_model-00028-of-00046.bin", - "language_model.model.layers.53.self_attn.v_proj.weight": "pytorch_model-00028-of-00046.bin", - "language_model.model.layers.54.input_layernorm.weight": "pytorch_model-00028-of-00046.bin", - "language_model.model.layers.54.mlp.down_proj.weight": "pytorch_model-00029-of-00046.bin", - "language_model.model.layers.54.mlp.gate_proj.weight": "pytorch_model-00029-of-00046.bin", - "language_model.model.layers.54.mlp.up_proj.weight": "pytorch_model-00029-of-00046.bin", - "language_model.model.layers.54.post_attention_layernorm.weight": "pytorch_model-00028-of-00046.bin", - "language_model.model.layers.54.self_attn.k_proj.bias": "pytorch_model-00029-of-00046.bin", - "language_model.model.layers.54.self_attn.k_proj.weight": "pytorch_model-00029-of-00046.bin", - "language_model.model.layers.54.self_attn.o_proj.weight": "pytorch_model-00029-of-00046.bin", - "language_model.model.layers.54.self_attn.q_proj.bias": "pytorch_model-00029-of-00046.bin", - "language_model.model.layers.54.self_attn.q_proj.weight": "pytorch_model-00029-of-00046.bin", - "language_model.model.layers.54.self_attn.v_proj.bias": "pytorch_model-00029-of-00046.bin", - "language_model.model.layers.54.self_attn.v_proj.weight": "pytorch_model-00029-of-00046.bin", - "language_model.model.layers.55.input_layernorm.weight": "pytorch_model-00029-of-00046.bin", - "language_model.model.layers.55.mlp.down_proj.weight": "pytorch_model-00029-of-00046.bin", - "language_model.model.layers.55.mlp.gate_proj.weight": "pytorch_model-00029-of-00046.bin", - "language_model.model.layers.55.mlp.up_proj.weight": "pytorch_model-00029-of-00046.bin", - "language_model.model.layers.55.post_attention_layernorm.weight": "pytorch_model-00029-of-00046.bin", - "language_model.model.layers.55.self_attn.k_proj.bias": "pytorch_model-00029-of-00046.bin", - "language_model.model.layers.55.self_attn.k_proj.weight": "pytorch_model-00029-of-00046.bin", - "language_model.model.layers.55.self_attn.o_proj.weight": "pytorch_model-00029-of-00046.bin", - "language_model.model.layers.55.self_attn.q_proj.bias": "pytorch_model-00029-of-00046.bin", - "language_model.model.layers.55.self_attn.q_proj.weight": "pytorch_model-00029-of-00046.bin", - "language_model.model.layers.55.self_attn.v_proj.bias": "pytorch_model-00029-of-00046.bin", - "language_model.model.layers.55.self_attn.v_proj.weight": "pytorch_model-00029-of-00046.bin", - "language_model.model.layers.56.input_layernorm.weight": "pytorch_model-00029-of-00046.bin", - "language_model.model.layers.56.mlp.down_proj.weight": "pytorch_model-00030-of-00046.bin", - "language_model.model.layers.56.mlp.gate_proj.weight": "pytorch_model-00030-of-00046.bin", - "language_model.model.layers.56.mlp.up_proj.weight": "pytorch_model-00030-of-00046.bin", - "language_model.model.layers.56.post_attention_layernorm.weight": "pytorch_model-00029-of-00046.bin", - "language_model.model.layers.56.self_attn.k_proj.bias": "pytorch_model-00030-of-00046.bin", - "language_model.model.layers.56.self_attn.k_proj.weight": "pytorch_model-00030-of-00046.bin", - "language_model.model.layers.56.self_attn.o_proj.weight": "pytorch_model-00030-of-00046.bin", - "language_model.model.layers.56.self_attn.q_proj.bias": "pytorch_model-00030-of-00046.bin", - "language_model.model.layers.56.self_attn.q_proj.weight": "pytorch_model-00030-of-00046.bin", - "language_model.model.layers.56.self_attn.v_proj.bias": "pytorch_model-00030-of-00046.bin", - "language_model.model.layers.56.self_attn.v_proj.weight": "pytorch_model-00030-of-00046.bin", - "language_model.model.layers.57.input_layernorm.weight": "pytorch_model-00030-of-00046.bin", - "language_model.model.layers.57.mlp.down_proj.weight": "pytorch_model-00030-of-00046.bin", - "language_model.model.layers.57.mlp.gate_proj.weight": "pytorch_model-00030-of-00046.bin", - "language_model.model.layers.57.mlp.up_proj.weight": "pytorch_model-00030-of-00046.bin", - "language_model.model.layers.57.post_attention_layernorm.weight": "pytorch_model-00030-of-00046.bin", - "language_model.model.layers.57.self_attn.k_proj.bias": "pytorch_model-00030-of-00046.bin", - "language_model.model.layers.57.self_attn.k_proj.weight": "pytorch_model-00030-of-00046.bin", - "language_model.model.layers.57.self_attn.o_proj.weight": "pytorch_model-00030-of-00046.bin", - "language_model.model.layers.57.self_attn.q_proj.bias": "pytorch_model-00030-of-00046.bin", - "language_model.model.layers.57.self_attn.q_proj.weight": "pytorch_model-00030-of-00046.bin", - "language_model.model.layers.57.self_attn.v_proj.bias": "pytorch_model-00030-of-00046.bin", - "language_model.model.layers.57.self_attn.v_proj.weight": "pytorch_model-00030-of-00046.bin", - "language_model.model.layers.58.input_layernorm.weight": "pytorch_model-00030-of-00046.bin", - "language_model.model.layers.58.mlp.down_proj.weight": "pytorch_model-00031-of-00046.bin", - "language_model.model.layers.58.mlp.gate_proj.weight": "pytorch_model-00031-of-00046.bin", - "language_model.model.layers.58.mlp.up_proj.weight": "pytorch_model-00031-of-00046.bin", - "language_model.model.layers.58.post_attention_layernorm.weight": "pytorch_model-00030-of-00046.bin", - "language_model.model.layers.58.self_attn.k_proj.bias": "pytorch_model-00031-of-00046.bin", - "language_model.model.layers.58.self_attn.k_proj.weight": "pytorch_model-00031-of-00046.bin", - "language_model.model.layers.58.self_attn.o_proj.weight": "pytorch_model-00031-of-00046.bin", - "language_model.model.layers.58.self_attn.q_proj.bias": "pytorch_model-00031-of-00046.bin", - "language_model.model.layers.58.self_attn.q_proj.weight": "pytorch_model-00031-of-00046.bin", - "language_model.model.layers.58.self_attn.v_proj.bias": "pytorch_model-00031-of-00046.bin", - "language_model.model.layers.58.self_attn.v_proj.weight": "pytorch_model-00031-of-00046.bin", - "language_model.model.layers.59.input_layernorm.weight": "pytorch_model-00031-of-00046.bin", - "language_model.model.layers.59.mlp.down_proj.weight": "pytorch_model-00031-of-00046.bin", - "language_model.model.layers.59.mlp.gate_proj.weight": "pytorch_model-00031-of-00046.bin", - "language_model.model.layers.59.mlp.up_proj.weight": "pytorch_model-00031-of-00046.bin", - "language_model.model.layers.59.post_attention_layernorm.weight": "pytorch_model-00031-of-00046.bin", - "language_model.model.layers.59.self_attn.k_proj.bias": "pytorch_model-00031-of-00046.bin", - "language_model.model.layers.59.self_attn.k_proj.weight": "pytorch_model-00031-of-00046.bin", - "language_model.model.layers.59.self_attn.o_proj.weight": "pytorch_model-00031-of-00046.bin", - "language_model.model.layers.59.self_attn.q_proj.bias": "pytorch_model-00031-of-00046.bin", - "language_model.model.layers.59.self_attn.q_proj.weight": "pytorch_model-00031-of-00046.bin", - "language_model.model.layers.59.self_attn.v_proj.bias": "pytorch_model-00031-of-00046.bin", - "language_model.model.layers.59.self_attn.v_proj.weight": "pytorch_model-00031-of-00046.bin", - "language_model.model.layers.6.input_layernorm.weight": "pytorch_model-00004-of-00046.bin", - "language_model.model.layers.6.mlp.down_proj.weight": "pytorch_model-00005-of-00046.bin", - "language_model.model.layers.6.mlp.gate_proj.weight": "pytorch_model-00005-of-00046.bin", - "language_model.model.layers.6.mlp.up_proj.weight": "pytorch_model-00005-of-00046.bin", - "language_model.model.layers.6.post_attention_layernorm.weight": "pytorch_model-00004-of-00046.bin", - "language_model.model.layers.6.self_attn.k_proj.bias": "pytorch_model-00005-of-00046.bin", - "language_model.model.layers.6.self_attn.k_proj.weight": "pytorch_model-00005-of-00046.bin", - "language_model.model.layers.6.self_attn.o_proj.weight": "pytorch_model-00005-of-00046.bin", - "language_model.model.layers.6.self_attn.q_proj.bias": "pytorch_model-00005-of-00046.bin", - "language_model.model.layers.6.self_attn.q_proj.weight": "pytorch_model-00005-of-00046.bin", - "language_model.model.layers.6.self_attn.v_proj.bias": "pytorch_model-00005-of-00046.bin", - "language_model.model.layers.6.self_attn.v_proj.weight": "pytorch_model-00005-of-00046.bin", - "language_model.model.layers.60.input_layernorm.weight": "pytorch_model-00031-of-00046.bin", - "language_model.model.layers.60.mlp.down_proj.weight": "pytorch_model-00032-of-00046.bin", - "language_model.model.layers.60.mlp.gate_proj.weight": "pytorch_model-00032-of-00046.bin", - "language_model.model.layers.60.mlp.up_proj.weight": "pytorch_model-00032-of-00046.bin", - "language_model.model.layers.60.post_attention_layernorm.weight": "pytorch_model-00031-of-00046.bin", - "language_model.model.layers.60.self_attn.k_proj.bias": "pytorch_model-00032-of-00046.bin", - "language_model.model.layers.60.self_attn.k_proj.weight": "pytorch_model-00032-of-00046.bin", - "language_model.model.layers.60.self_attn.o_proj.weight": "pytorch_model-00032-of-00046.bin", - "language_model.model.layers.60.self_attn.q_proj.bias": "pytorch_model-00032-of-00046.bin", - "language_model.model.layers.60.self_attn.q_proj.weight": "pytorch_model-00032-of-00046.bin", - "language_model.model.layers.60.self_attn.v_proj.bias": "pytorch_model-00032-of-00046.bin", - "language_model.model.layers.60.self_attn.v_proj.weight": "pytorch_model-00032-of-00046.bin", - "language_model.model.layers.61.input_layernorm.weight": "pytorch_model-00032-of-00046.bin", - "language_model.model.layers.61.mlp.down_proj.weight": "pytorch_model-00032-of-00046.bin", - "language_model.model.layers.61.mlp.gate_proj.weight": "pytorch_model-00032-of-00046.bin", - "language_model.model.layers.61.mlp.up_proj.weight": "pytorch_model-00032-of-00046.bin", - "language_model.model.layers.61.post_attention_layernorm.weight": "pytorch_model-00032-of-00046.bin", - "language_model.model.layers.61.self_attn.k_proj.bias": "pytorch_model-00032-of-00046.bin", - "language_model.model.layers.61.self_attn.k_proj.weight": "pytorch_model-00032-of-00046.bin", - "language_model.model.layers.61.self_attn.o_proj.weight": "pytorch_model-00032-of-00046.bin", - "language_model.model.layers.61.self_attn.q_proj.bias": "pytorch_model-00032-of-00046.bin", - "language_model.model.layers.61.self_attn.q_proj.weight": "pytorch_model-00032-of-00046.bin", - "language_model.model.layers.61.self_attn.v_proj.bias": "pytorch_model-00032-of-00046.bin", - "language_model.model.layers.61.self_attn.v_proj.weight": "pytorch_model-00032-of-00046.bin", - "language_model.model.layers.62.input_layernorm.weight": "pytorch_model-00032-of-00046.bin", - "language_model.model.layers.62.mlp.down_proj.weight": "pytorch_model-00033-of-00046.bin", - "language_model.model.layers.62.mlp.gate_proj.weight": "pytorch_model-00033-of-00046.bin", - "language_model.model.layers.62.mlp.up_proj.weight": "pytorch_model-00033-of-00046.bin", - "language_model.model.layers.62.post_attention_layernorm.weight": "pytorch_model-00032-of-00046.bin", - "language_model.model.layers.62.self_attn.k_proj.bias": "pytorch_model-00033-of-00046.bin", - "language_model.model.layers.62.self_attn.k_proj.weight": "pytorch_model-00033-of-00046.bin", - "language_model.model.layers.62.self_attn.o_proj.weight": "pytorch_model-00033-of-00046.bin", - "language_model.model.layers.62.self_attn.q_proj.bias": "pytorch_model-00033-of-00046.bin", - "language_model.model.layers.62.self_attn.q_proj.weight": "pytorch_model-00033-of-00046.bin", - "language_model.model.layers.62.self_attn.v_proj.bias": "pytorch_model-00033-of-00046.bin", - "language_model.model.layers.62.self_attn.v_proj.weight": "pytorch_model-00033-of-00046.bin", - "language_model.model.layers.63.input_layernorm.weight": "pytorch_model-00033-of-00046.bin", - "language_model.model.layers.63.mlp.down_proj.weight": "pytorch_model-00033-of-00046.bin", - "language_model.model.layers.63.mlp.gate_proj.weight": "pytorch_model-00033-of-00046.bin", - "language_model.model.layers.63.mlp.up_proj.weight": "pytorch_model-00033-of-00046.bin", - "language_model.model.layers.63.post_attention_layernorm.weight": "pytorch_model-00033-of-00046.bin", - "language_model.model.layers.63.self_attn.k_proj.bias": "pytorch_model-00033-of-00046.bin", - "language_model.model.layers.63.self_attn.k_proj.weight": "pytorch_model-00033-of-00046.bin", - "language_model.model.layers.63.self_attn.o_proj.weight": "pytorch_model-00033-of-00046.bin", - "language_model.model.layers.63.self_attn.q_proj.bias": "pytorch_model-00033-of-00046.bin", - "language_model.model.layers.63.self_attn.q_proj.weight": "pytorch_model-00033-of-00046.bin", - "language_model.model.layers.63.self_attn.v_proj.bias": "pytorch_model-00033-of-00046.bin", - "language_model.model.layers.63.self_attn.v_proj.weight": "pytorch_model-00033-of-00046.bin", - "language_model.model.layers.64.input_layernorm.weight": "pytorch_model-00033-of-00046.bin", - "language_model.model.layers.64.mlp.down_proj.weight": "pytorch_model-00034-of-00046.bin", - "language_model.model.layers.64.mlp.gate_proj.weight": "pytorch_model-00034-of-00046.bin", - "language_model.model.layers.64.mlp.up_proj.weight": "pytorch_model-00034-of-00046.bin", - "language_model.model.layers.64.post_attention_layernorm.weight": "pytorch_model-00033-of-00046.bin", - "language_model.model.layers.64.self_attn.k_proj.bias": "pytorch_model-00034-of-00046.bin", - "language_model.model.layers.64.self_attn.k_proj.weight": "pytorch_model-00034-of-00046.bin", - "language_model.model.layers.64.self_attn.o_proj.weight": "pytorch_model-00034-of-00046.bin", - "language_model.model.layers.64.self_attn.q_proj.bias": "pytorch_model-00034-of-00046.bin", - "language_model.model.layers.64.self_attn.q_proj.weight": "pytorch_model-00034-of-00046.bin", - "language_model.model.layers.64.self_attn.v_proj.bias": "pytorch_model-00034-of-00046.bin", - "language_model.model.layers.64.self_attn.v_proj.weight": "pytorch_model-00034-of-00046.bin", - "language_model.model.layers.65.input_layernorm.weight": "pytorch_model-00034-of-00046.bin", - "language_model.model.layers.65.mlp.down_proj.weight": "pytorch_model-00034-of-00046.bin", - "language_model.model.layers.65.mlp.gate_proj.weight": "pytorch_model-00034-of-00046.bin", - "language_model.model.layers.65.mlp.up_proj.weight": "pytorch_model-00034-of-00046.bin", - "language_model.model.layers.65.post_attention_layernorm.weight": "pytorch_model-00034-of-00046.bin", - "language_model.model.layers.65.self_attn.k_proj.bias": "pytorch_model-00034-of-00046.bin", - "language_model.model.layers.65.self_attn.k_proj.weight": "pytorch_model-00034-of-00046.bin", - "language_model.model.layers.65.self_attn.o_proj.weight": "pytorch_model-00034-of-00046.bin", - "language_model.model.layers.65.self_attn.q_proj.bias": "pytorch_model-00034-of-00046.bin", - "language_model.model.layers.65.self_attn.q_proj.weight": "pytorch_model-00034-of-00046.bin", - "language_model.model.layers.65.self_attn.v_proj.bias": "pytorch_model-00034-of-00046.bin", - "language_model.model.layers.65.self_attn.v_proj.weight": "pytorch_model-00034-of-00046.bin", - "language_model.model.layers.66.input_layernorm.weight": "pytorch_model-00034-of-00046.bin", - "language_model.model.layers.66.mlp.down_proj.weight": "pytorch_model-00035-of-00046.bin", - "language_model.model.layers.66.mlp.gate_proj.weight": "pytorch_model-00035-of-00046.bin", - "language_model.model.layers.66.mlp.up_proj.weight": "pytorch_model-00035-of-00046.bin", - "language_model.model.layers.66.post_attention_layernorm.weight": "pytorch_model-00034-of-00046.bin", - "language_model.model.layers.66.self_attn.k_proj.bias": "pytorch_model-00035-of-00046.bin", - "language_model.model.layers.66.self_attn.k_proj.weight": "pytorch_model-00035-of-00046.bin", - "language_model.model.layers.66.self_attn.o_proj.weight": "pytorch_model-00035-of-00046.bin", - "language_model.model.layers.66.self_attn.q_proj.bias": "pytorch_model-00035-of-00046.bin", - "language_model.model.layers.66.self_attn.q_proj.weight": "pytorch_model-00035-of-00046.bin", - "language_model.model.layers.66.self_attn.v_proj.bias": "pytorch_model-00035-of-00046.bin", - "language_model.model.layers.66.self_attn.v_proj.weight": "pytorch_model-00035-of-00046.bin", - "language_model.model.layers.67.input_layernorm.weight": "pytorch_model-00035-of-00046.bin", - "language_model.model.layers.67.mlp.down_proj.weight": "pytorch_model-00035-of-00046.bin", - "language_model.model.layers.67.mlp.gate_proj.weight": "pytorch_model-00035-of-00046.bin", - "language_model.model.layers.67.mlp.up_proj.weight": "pytorch_model-00035-of-00046.bin", - "language_model.model.layers.67.post_attention_layernorm.weight": "pytorch_model-00035-of-00046.bin", - "language_model.model.layers.67.self_attn.k_proj.bias": "pytorch_model-00035-of-00046.bin", - "language_model.model.layers.67.self_attn.k_proj.weight": "pytorch_model-00035-of-00046.bin", - "language_model.model.layers.67.self_attn.o_proj.weight": "pytorch_model-00035-of-00046.bin", - "language_model.model.layers.67.self_attn.q_proj.bias": "pytorch_model-00035-of-00046.bin", - "language_model.model.layers.67.self_attn.q_proj.weight": "pytorch_model-00035-of-00046.bin", - "language_model.model.layers.67.self_attn.v_proj.bias": "pytorch_model-00035-of-00046.bin", - "language_model.model.layers.67.self_attn.v_proj.weight": "pytorch_model-00035-of-00046.bin", - "language_model.model.layers.68.input_layernorm.weight": "pytorch_model-00035-of-00046.bin", - "language_model.model.layers.68.mlp.down_proj.weight": "pytorch_model-00036-of-00046.bin", - "language_model.model.layers.68.mlp.gate_proj.weight": "pytorch_model-00036-of-00046.bin", - "language_model.model.layers.68.mlp.up_proj.weight": "pytorch_model-00036-of-00046.bin", - "language_model.model.layers.68.post_attention_layernorm.weight": "pytorch_model-00035-of-00046.bin", - "language_model.model.layers.68.self_attn.k_proj.bias": "pytorch_model-00036-of-00046.bin", - "language_model.model.layers.68.self_attn.k_proj.weight": "pytorch_model-00036-of-00046.bin", - "language_model.model.layers.68.self_attn.o_proj.weight": "pytorch_model-00036-of-00046.bin", - "language_model.model.layers.68.self_attn.q_proj.bias": "pytorch_model-00036-of-00046.bin", - "language_model.model.layers.68.self_attn.q_proj.weight": "pytorch_model-00036-of-00046.bin", - "language_model.model.layers.68.self_attn.v_proj.bias": "pytorch_model-00036-of-00046.bin", - "language_model.model.layers.68.self_attn.v_proj.weight": "pytorch_model-00036-of-00046.bin", - "language_model.model.layers.69.input_layernorm.weight": "pytorch_model-00036-of-00046.bin", - "language_model.model.layers.69.mlp.down_proj.weight": "pytorch_model-00036-of-00046.bin", - "language_model.model.layers.69.mlp.gate_proj.weight": "pytorch_model-00036-of-00046.bin", - "language_model.model.layers.69.mlp.up_proj.weight": "pytorch_model-00036-of-00046.bin", - "language_model.model.layers.69.post_attention_layernorm.weight": "pytorch_model-00036-of-00046.bin", - "language_model.model.layers.69.self_attn.k_proj.bias": "pytorch_model-00036-of-00046.bin", - "language_model.model.layers.69.self_attn.k_proj.weight": "pytorch_model-00036-of-00046.bin", - "language_model.model.layers.69.self_attn.o_proj.weight": "pytorch_model-00036-of-00046.bin", - "language_model.model.layers.69.self_attn.q_proj.bias": "pytorch_model-00036-of-00046.bin", - "language_model.model.layers.69.self_attn.q_proj.weight": "pytorch_model-00036-of-00046.bin", - "language_model.model.layers.69.self_attn.v_proj.bias": "pytorch_model-00036-of-00046.bin", - "language_model.model.layers.69.self_attn.v_proj.weight": "pytorch_model-00036-of-00046.bin", - "language_model.model.layers.7.input_layernorm.weight": "pytorch_model-00005-of-00046.bin", - "language_model.model.layers.7.mlp.down_proj.weight": "pytorch_model-00005-of-00046.bin", - "language_model.model.layers.7.mlp.gate_proj.weight": "pytorch_model-00005-of-00046.bin", - "language_model.model.layers.7.mlp.up_proj.weight": "pytorch_model-00005-of-00046.bin", - "language_model.model.layers.7.post_attention_layernorm.weight": "pytorch_model-00005-of-00046.bin", - "language_model.model.layers.7.self_attn.k_proj.bias": "pytorch_model-00005-of-00046.bin", - "language_model.model.layers.7.self_attn.k_proj.weight": "pytorch_model-00005-of-00046.bin", - "language_model.model.layers.7.self_attn.o_proj.weight": "pytorch_model-00005-of-00046.bin", - "language_model.model.layers.7.self_attn.q_proj.bias": "pytorch_model-00005-of-00046.bin", - "language_model.model.layers.7.self_attn.q_proj.weight": "pytorch_model-00005-of-00046.bin", - "language_model.model.layers.7.self_attn.v_proj.bias": "pytorch_model-00005-of-00046.bin", - "language_model.model.layers.7.self_attn.v_proj.weight": "pytorch_model-00005-of-00046.bin", - "language_model.model.layers.70.input_layernorm.weight": "pytorch_model-00036-of-00046.bin", - "language_model.model.layers.70.mlp.down_proj.weight": "pytorch_model-00037-of-00046.bin", - "language_model.model.layers.70.mlp.gate_proj.weight": "pytorch_model-00037-of-00046.bin", - "language_model.model.layers.70.mlp.up_proj.weight": "pytorch_model-00037-of-00046.bin", - "language_model.model.layers.70.post_attention_layernorm.weight": "pytorch_model-00036-of-00046.bin", - "language_model.model.layers.70.self_attn.k_proj.bias": "pytorch_model-00037-of-00046.bin", - "language_model.model.layers.70.self_attn.k_proj.weight": "pytorch_model-00037-of-00046.bin", - "language_model.model.layers.70.self_attn.o_proj.weight": "pytorch_model-00037-of-00046.bin", - "language_model.model.layers.70.self_attn.q_proj.bias": "pytorch_model-00037-of-00046.bin", - "language_model.model.layers.70.self_attn.q_proj.weight": "pytorch_model-00037-of-00046.bin", - "language_model.model.layers.70.self_attn.v_proj.bias": "pytorch_model-00037-of-00046.bin", - "language_model.model.layers.70.self_attn.v_proj.weight": "pytorch_model-00037-of-00046.bin", - "language_model.model.layers.71.input_layernorm.weight": "pytorch_model-00037-of-00046.bin", - "language_model.model.layers.71.mlp.down_proj.weight": "pytorch_model-00037-of-00046.bin", - "language_model.model.layers.71.mlp.gate_proj.weight": "pytorch_model-00037-of-00046.bin", - "language_model.model.layers.71.mlp.up_proj.weight": "pytorch_model-00037-of-00046.bin", - "language_model.model.layers.71.post_attention_layernorm.weight": "pytorch_model-00037-of-00046.bin", - "language_model.model.layers.71.self_attn.k_proj.bias": "pytorch_model-00037-of-00046.bin", - "language_model.model.layers.71.self_attn.k_proj.weight": "pytorch_model-00037-of-00046.bin", - "language_model.model.layers.71.self_attn.o_proj.weight": "pytorch_model-00037-of-00046.bin", - "language_model.model.layers.71.self_attn.q_proj.bias": "pytorch_model-00037-of-00046.bin", - "language_model.model.layers.71.self_attn.q_proj.weight": "pytorch_model-00037-of-00046.bin", - "language_model.model.layers.71.self_attn.v_proj.bias": "pytorch_model-00037-of-00046.bin", - "language_model.model.layers.71.self_attn.v_proj.weight": "pytorch_model-00037-of-00046.bin", - "language_model.model.layers.72.input_layernorm.weight": "pytorch_model-00037-of-00046.bin", - "language_model.model.layers.72.mlp.down_proj.weight": "pytorch_model-00038-of-00046.bin", - "language_model.model.layers.72.mlp.gate_proj.weight": "pytorch_model-00038-of-00046.bin", - "language_model.model.layers.72.mlp.up_proj.weight": "pytorch_model-00038-of-00046.bin", - "language_model.model.layers.72.post_attention_layernorm.weight": "pytorch_model-00037-of-00046.bin", - "language_model.model.layers.72.self_attn.k_proj.bias": "pytorch_model-00038-of-00046.bin", - "language_model.model.layers.72.self_attn.k_proj.weight": "pytorch_model-00038-of-00046.bin", - "language_model.model.layers.72.self_attn.o_proj.weight": "pytorch_model-00038-of-00046.bin", - "language_model.model.layers.72.self_attn.q_proj.bias": "pytorch_model-00038-of-00046.bin", - "language_model.model.layers.72.self_attn.q_proj.weight": "pytorch_model-00038-of-00046.bin", - "language_model.model.layers.72.self_attn.v_proj.bias": "pytorch_model-00038-of-00046.bin", - "language_model.model.layers.72.self_attn.v_proj.weight": "pytorch_model-00038-of-00046.bin", - "language_model.model.layers.73.input_layernorm.weight": "pytorch_model-00038-of-00046.bin", - "language_model.model.layers.73.mlp.down_proj.weight": "pytorch_model-00038-of-00046.bin", - "language_model.model.layers.73.mlp.gate_proj.weight": "pytorch_model-00038-of-00046.bin", - "language_model.model.layers.73.mlp.up_proj.weight": "pytorch_model-00038-of-00046.bin", - "language_model.model.layers.73.post_attention_layernorm.weight": "pytorch_model-00038-of-00046.bin", - "language_model.model.layers.73.self_attn.k_proj.bias": "pytorch_model-00038-of-00046.bin", - "language_model.model.layers.73.self_attn.k_proj.weight": "pytorch_model-00038-of-00046.bin", - "language_model.model.layers.73.self_attn.o_proj.weight": "pytorch_model-00038-of-00046.bin", - "language_model.model.layers.73.self_attn.q_proj.bias": "pytorch_model-00038-of-00046.bin", - "language_model.model.layers.73.self_attn.q_proj.weight": "pytorch_model-00038-of-00046.bin", - "language_model.model.layers.73.self_attn.v_proj.bias": "pytorch_model-00038-of-00046.bin", - "language_model.model.layers.73.self_attn.v_proj.weight": "pytorch_model-00038-of-00046.bin", - "language_model.model.layers.74.input_layernorm.weight": "pytorch_model-00038-of-00046.bin", - "language_model.model.layers.74.mlp.down_proj.weight": "pytorch_model-00039-of-00046.bin", - "language_model.model.layers.74.mlp.gate_proj.weight": "pytorch_model-00039-of-00046.bin", - "language_model.model.layers.74.mlp.up_proj.weight": "pytorch_model-00039-of-00046.bin", - "language_model.model.layers.74.post_attention_layernorm.weight": "pytorch_model-00038-of-00046.bin", - "language_model.model.layers.74.self_attn.k_proj.bias": "pytorch_model-00039-of-00046.bin", - "language_model.model.layers.74.self_attn.k_proj.weight": "pytorch_model-00039-of-00046.bin", - "language_model.model.layers.74.self_attn.o_proj.weight": "pytorch_model-00039-of-00046.bin", - "language_model.model.layers.74.self_attn.q_proj.bias": "pytorch_model-00039-of-00046.bin", - "language_model.model.layers.74.self_attn.q_proj.weight": "pytorch_model-00039-of-00046.bin", - "language_model.model.layers.74.self_attn.v_proj.bias": "pytorch_model-00039-of-00046.bin", - "language_model.model.layers.74.self_attn.v_proj.weight": "pytorch_model-00039-of-00046.bin", - "language_model.model.layers.75.input_layernorm.weight": "pytorch_model-00039-of-00046.bin", - "language_model.model.layers.75.mlp.down_proj.weight": "pytorch_model-00039-of-00046.bin", - "language_model.model.layers.75.mlp.gate_proj.weight": "pytorch_model-00039-of-00046.bin", - "language_model.model.layers.75.mlp.up_proj.weight": "pytorch_model-00039-of-00046.bin", - "language_model.model.layers.75.post_attention_layernorm.weight": "pytorch_model-00039-of-00046.bin", - "language_model.model.layers.75.self_attn.k_proj.bias": "pytorch_model-00039-of-00046.bin", - "language_model.model.layers.75.self_attn.k_proj.weight": "pytorch_model-00039-of-00046.bin", - "language_model.model.layers.75.self_attn.o_proj.weight": "pytorch_model-00039-of-00046.bin", - "language_model.model.layers.75.self_attn.q_proj.bias": "pytorch_model-00039-of-00046.bin", - "language_model.model.layers.75.self_attn.q_proj.weight": "pytorch_model-00039-of-00046.bin", - "language_model.model.layers.75.self_attn.v_proj.bias": "pytorch_model-00039-of-00046.bin", - "language_model.model.layers.75.self_attn.v_proj.weight": "pytorch_model-00039-of-00046.bin", - "language_model.model.layers.76.input_layernorm.weight": "pytorch_model-00039-of-00046.bin", - "language_model.model.layers.76.mlp.down_proj.weight": "pytorch_model-00040-of-00046.bin", - "language_model.model.layers.76.mlp.gate_proj.weight": "pytorch_model-00040-of-00046.bin", - "language_model.model.layers.76.mlp.up_proj.weight": "pytorch_model-00040-of-00046.bin", - "language_model.model.layers.76.post_attention_layernorm.weight": "pytorch_model-00039-of-00046.bin", - "language_model.model.layers.76.self_attn.k_proj.bias": "pytorch_model-00040-of-00046.bin", - "language_model.model.layers.76.self_attn.k_proj.weight": "pytorch_model-00040-of-00046.bin", - "language_model.model.layers.76.self_attn.o_proj.weight": "pytorch_model-00040-of-00046.bin", - "language_model.model.layers.76.self_attn.q_proj.bias": "pytorch_model-00040-of-00046.bin", - "language_model.model.layers.76.self_attn.q_proj.weight": "pytorch_model-00040-of-00046.bin", - "language_model.model.layers.76.self_attn.v_proj.bias": "pytorch_model-00040-of-00046.bin", - "language_model.model.layers.76.self_attn.v_proj.weight": "pytorch_model-00040-of-00046.bin", - "language_model.model.layers.77.input_layernorm.weight": "pytorch_model-00040-of-00046.bin", - "language_model.model.layers.77.mlp.down_proj.weight": "pytorch_model-00040-of-00046.bin", - "language_model.model.layers.77.mlp.gate_proj.weight": "pytorch_model-00040-of-00046.bin", - "language_model.model.layers.77.mlp.up_proj.weight": "pytorch_model-00040-of-00046.bin", - "language_model.model.layers.77.post_attention_layernorm.weight": "pytorch_model-00040-of-00046.bin", - "language_model.model.layers.77.self_attn.k_proj.bias": "pytorch_model-00040-of-00046.bin", - "language_model.model.layers.77.self_attn.k_proj.weight": "pytorch_model-00040-of-00046.bin", - "language_model.model.layers.77.self_attn.o_proj.weight": "pytorch_model-00040-of-00046.bin", - "language_model.model.layers.77.self_attn.q_proj.bias": "pytorch_model-00040-of-00046.bin", - "language_model.model.layers.77.self_attn.q_proj.weight": "pytorch_model-00040-of-00046.bin", - "language_model.model.layers.77.self_attn.v_proj.bias": "pytorch_model-00040-of-00046.bin", - "language_model.model.layers.77.self_attn.v_proj.weight": "pytorch_model-00040-of-00046.bin", - "language_model.model.layers.78.input_layernorm.weight": "pytorch_model-00040-of-00046.bin", - "language_model.model.layers.78.mlp.down_proj.weight": "pytorch_model-00041-of-00046.bin", - "language_model.model.layers.78.mlp.gate_proj.weight": "pytorch_model-00041-of-00046.bin", - "language_model.model.layers.78.mlp.up_proj.weight": "pytorch_model-00041-of-00046.bin", - "language_model.model.layers.78.post_attention_layernorm.weight": "pytorch_model-00040-of-00046.bin", - "language_model.model.layers.78.self_attn.k_proj.bias": "pytorch_model-00041-of-00046.bin", - "language_model.model.layers.78.self_attn.k_proj.weight": "pytorch_model-00041-of-00046.bin", - "language_model.model.layers.78.self_attn.o_proj.weight": "pytorch_model-00041-of-00046.bin", - "language_model.model.layers.78.self_attn.q_proj.bias": "pytorch_model-00041-of-00046.bin", - "language_model.model.layers.78.self_attn.q_proj.weight": "pytorch_model-00041-of-00046.bin", - "language_model.model.layers.78.self_attn.v_proj.bias": "pytorch_model-00041-of-00046.bin", - "language_model.model.layers.78.self_attn.v_proj.weight": "pytorch_model-00041-of-00046.bin", - "language_model.model.layers.79.input_layernorm.weight": "pytorch_model-00041-of-00046.bin", - "language_model.model.layers.79.mlp.down_proj.weight": "pytorch_model-00041-of-00046.bin", - "language_model.model.layers.79.mlp.gate_proj.weight": "pytorch_model-00041-of-00046.bin", - "language_model.model.layers.79.mlp.up_proj.weight": "pytorch_model-00041-of-00046.bin", - "language_model.model.layers.79.post_attention_layernorm.weight": "pytorch_model-00041-of-00046.bin", - "language_model.model.layers.79.self_attn.k_proj.bias": "pytorch_model-00041-of-00046.bin", - "language_model.model.layers.79.self_attn.k_proj.weight": "pytorch_model-00041-of-00046.bin", - "language_model.model.layers.79.self_attn.o_proj.weight": "pytorch_model-00041-of-00046.bin", - "language_model.model.layers.79.self_attn.q_proj.bias": "pytorch_model-00041-of-00046.bin", - "language_model.model.layers.79.self_attn.q_proj.weight": "pytorch_model-00041-of-00046.bin", - "language_model.model.layers.79.self_attn.v_proj.bias": "pytorch_model-00041-of-00046.bin", - "language_model.model.layers.79.self_attn.v_proj.weight": "pytorch_model-00041-of-00046.bin", - "language_model.model.layers.8.input_layernorm.weight": "pytorch_model-00005-of-00046.bin", - "language_model.model.layers.8.mlp.down_proj.weight": "pytorch_model-00006-of-00046.bin", - "language_model.model.layers.8.mlp.gate_proj.weight": "pytorch_model-00006-of-00046.bin", - "language_model.model.layers.8.mlp.up_proj.weight": "pytorch_model-00006-of-00046.bin", - "language_model.model.layers.8.post_attention_layernorm.weight": "pytorch_model-00005-of-00046.bin", - "language_model.model.layers.8.self_attn.k_proj.bias": "pytorch_model-00006-of-00046.bin", - "language_model.model.layers.8.self_attn.k_proj.weight": "pytorch_model-00006-of-00046.bin", - "language_model.model.layers.8.self_attn.o_proj.weight": "pytorch_model-00006-of-00046.bin", - "language_model.model.layers.8.self_attn.q_proj.bias": "pytorch_model-00006-of-00046.bin", - "language_model.model.layers.8.self_attn.q_proj.weight": "pytorch_model-00006-of-00046.bin", - "language_model.model.layers.8.self_attn.v_proj.bias": "pytorch_model-00006-of-00046.bin", - "language_model.model.layers.8.self_attn.v_proj.weight": "pytorch_model-00006-of-00046.bin", - "language_model.model.layers.9.input_layernorm.weight": "pytorch_model-00006-of-00046.bin", - "language_model.model.layers.9.mlp.down_proj.weight": "pytorch_model-00006-of-00046.bin", - "language_model.model.layers.9.mlp.gate_proj.weight": "pytorch_model-00006-of-00046.bin", - "language_model.model.layers.9.mlp.up_proj.weight": "pytorch_model-00006-of-00046.bin", - "language_model.model.layers.9.post_attention_layernorm.weight": "pytorch_model-00006-of-00046.bin", - "language_model.model.layers.9.self_attn.k_proj.bias": "pytorch_model-00006-of-00046.bin", - "language_model.model.layers.9.self_attn.k_proj.weight": "pytorch_model-00006-of-00046.bin", - "language_model.model.layers.9.self_attn.o_proj.weight": "pytorch_model-00006-of-00046.bin", - "language_model.model.layers.9.self_attn.q_proj.bias": "pytorch_model-00006-of-00046.bin", - "language_model.model.layers.9.self_attn.q_proj.weight": "pytorch_model-00006-of-00046.bin", - "language_model.model.layers.9.self_attn.v_proj.bias": "pytorch_model-00006-of-00046.bin", - "language_model.model.layers.9.self_attn.v_proj.weight": "pytorch_model-00006-of-00046.bin", - "language_model.model.norm.weight": "pytorch_model-00041-of-00046.bin", - "mlp1.0.bias": "pytorch_model-00001-of-00046.bin", - "mlp1.0.weight": "pytorch_model-00001-of-00046.bin", - "mlp1.1.weight": "pytorch_model-00001-of-00046.bin", - "mlp1.3.weight": "pytorch_model-00001-of-00046.bin", - "vision_model.embeddings.class_embedding": "pytorch_model-00042-of-00046.bin", - "vision_model.embeddings.patch_embedding.bias": "pytorch_model-00042-of-00046.bin", - "vision_model.embeddings.patch_embedding.weight": "pytorch_model-00042-of-00046.bin", - "vision_model.embeddings.position_embedding": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.0.attn.k_norm.weight": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.0.attn.proj.bias": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.0.attn.proj.weight": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.0.attn.q_norm.weight": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.0.attn.qkv.weight": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.0.ls1": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.0.ls2": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.0.norm1.weight": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.0.norm2.weight": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.1.attn.k_norm.weight": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.1.attn.proj.bias": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.1.attn.proj.weight": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.1.attn.q_norm.weight": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.1.attn.qkv.weight": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.1.ls1": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.1.ls2": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.1.norm1.weight": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.1.norm2.weight": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.10.attn.k_norm.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.10.attn.proj.bias": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.10.attn.proj.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.10.attn.q_norm.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.10.attn.qkv.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.10.ls1": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.10.ls2": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.10.norm1.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.10.norm2.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.11.attn.k_norm.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.11.attn.proj.bias": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.11.attn.proj.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.11.attn.q_norm.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.11.attn.qkv.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.11.ls1": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.11.ls2": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.11.norm1.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.11.norm2.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.12.attn.k_norm.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.12.attn.proj.bias": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.12.attn.proj.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.12.attn.q_norm.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.12.attn.qkv.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.12.ls1": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.12.ls2": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.12.mlp.fc1.bias": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.12.mlp.fc1.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.12.mlp.fc2.bias": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.12.norm1.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.12.norm2.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.13.attn.k_norm.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.13.attn.proj.bias": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.13.attn.proj.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.13.attn.q_norm.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.13.attn.qkv.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.13.ls1": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.13.ls2": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.13.mlp.fc1.bias": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.13.mlp.fc1.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.13.mlp.fc2.bias": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.13.norm1.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.13.norm2.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.14.attn.k_norm.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.14.attn.proj.bias": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.14.attn.proj.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.14.attn.q_norm.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.14.attn.qkv.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.14.ls1": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.14.ls2": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.14.mlp.fc1.bias": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.14.mlp.fc1.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.14.mlp.fc2.bias": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.14.norm1.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.14.norm2.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.15.attn.k_norm.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.15.attn.proj.bias": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.15.attn.proj.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.15.attn.q_norm.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.15.attn.qkv.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.15.ls1": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.15.ls2": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.15.mlp.fc1.bias": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.15.mlp.fc1.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.15.mlp.fc2.bias": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.15.norm1.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.15.norm2.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.16.attn.k_norm.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.16.attn.proj.bias": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.16.attn.proj.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.16.attn.q_norm.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.16.attn.qkv.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.16.ls1": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.16.ls2": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.16.mlp.fc1.bias": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.16.mlp.fc1.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.16.mlp.fc2.bias": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.16.norm1.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.16.norm2.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.17.attn.k_norm.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.17.attn.proj.bias": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.17.attn.proj.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.17.attn.q_norm.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.17.attn.qkv.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.17.ls1": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.17.ls2": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.17.mlp.fc1.bias": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.17.mlp.fc1.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.17.mlp.fc2.bias": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.17.norm1.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.17.norm2.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.18.attn.k_norm.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.18.attn.proj.bias": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.18.attn.proj.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.18.attn.q_norm.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.18.attn.qkv.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.18.ls1": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.18.ls2": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.18.mlp.fc1.bias": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.18.mlp.fc1.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.18.mlp.fc2.bias": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.18.norm1.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.18.norm2.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.19.attn.k_norm.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.19.attn.proj.bias": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.19.attn.proj.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.19.attn.q_norm.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.19.attn.qkv.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.19.ls1": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.19.ls2": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.19.mlp.fc1.bias": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.19.mlp.fc1.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.19.mlp.fc2.bias": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.19.norm1.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.19.norm2.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.2.attn.k_norm.weight": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.2.attn.proj.bias": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.2.attn.proj.weight": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.2.attn.q_norm.weight": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.2.attn.qkv.weight": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.2.ls1": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.2.ls2": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.2.norm1.weight": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.2.norm2.weight": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.20.attn.k_norm.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.20.attn.proj.bias": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.20.attn.proj.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.20.attn.q_norm.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.20.attn.qkv.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.20.ls1": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.20.ls2": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.20.mlp.fc1.bias": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.20.mlp.fc1.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.20.mlp.fc2.bias": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.20.norm1.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.20.norm2.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.21.attn.k_norm.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.21.attn.proj.bias": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.21.attn.proj.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.21.attn.q_norm.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.21.attn.qkv.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.21.ls1": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.21.ls2": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.21.mlp.fc1.bias": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.21.mlp.fc1.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.21.mlp.fc2.bias": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.21.norm1.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.21.norm2.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.22.attn.k_norm.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.22.attn.proj.bias": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.22.attn.proj.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.22.attn.q_norm.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.22.attn.qkv.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.22.ls1": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.22.ls2": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.22.mlp.fc1.bias": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.22.mlp.fc1.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.22.mlp.fc2.bias": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.22.norm1.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.22.norm2.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.23.attn.k_norm.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.23.attn.proj.bias": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.23.attn.proj.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.23.attn.q_norm.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.23.attn.qkv.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.23.ls1": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.23.ls2": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.23.mlp.fc1.bias": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.23.mlp.fc1.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.23.mlp.fc2.bias": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.23.norm1.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.23.norm2.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.24.attn.k_norm.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.24.attn.proj.bias": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.24.attn.proj.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.24.attn.q_norm.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.24.attn.qkv.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.24.ls1": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.24.ls2": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.24.mlp.fc1.bias": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.24.mlp.fc1.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.24.mlp.fc2.bias": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.24.mlp.fc2.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.24.norm1.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.24.norm2.weight": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.25.attn.k_norm.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.25.attn.proj.bias": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.25.attn.proj.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.25.attn.q_norm.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.25.attn.qkv.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.25.ls1": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.25.ls2": "pytorch_model-00044-of-00046.bin", - "vision_model.encoder.layers.25.mlp.fc1.bias": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.25.mlp.fc1.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.25.mlp.fc2.bias": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.25.mlp.fc2.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.25.norm1.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.25.norm2.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.26.attn.k_norm.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.26.attn.proj.bias": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.26.attn.proj.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.26.attn.q_norm.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.26.attn.qkv.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.26.ls1": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.26.ls2": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.26.mlp.fc1.bias": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.26.mlp.fc1.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.26.mlp.fc2.bias": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.26.mlp.fc2.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.26.norm1.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.26.norm2.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.27.attn.k_norm.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.27.attn.proj.bias": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.27.attn.proj.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.27.attn.q_norm.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.27.attn.qkv.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.27.ls1": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.27.ls2": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.27.mlp.fc1.bias": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.27.mlp.fc1.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.27.mlp.fc2.bias": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.27.mlp.fc2.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.27.norm1.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.27.norm2.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.28.attn.k_norm.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.28.attn.proj.bias": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.28.attn.proj.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.28.attn.q_norm.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.28.attn.qkv.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.28.ls1": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.28.ls2": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.28.mlp.fc1.bias": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.28.mlp.fc1.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.28.mlp.fc2.bias": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.28.mlp.fc2.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.28.norm1.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.28.norm2.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.29.attn.k_norm.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.29.attn.proj.bias": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.29.attn.proj.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.29.attn.q_norm.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.29.attn.qkv.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.29.ls1": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.29.ls2": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.29.mlp.fc1.bias": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.29.mlp.fc1.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.29.mlp.fc2.bias": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.29.mlp.fc2.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.29.norm1.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.29.norm2.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.3.attn.k_norm.weight": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.3.attn.proj.bias": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.3.attn.proj.weight": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.3.attn.q_norm.weight": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.3.attn.qkv.weight": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.3.ls1": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.3.ls2": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.3.norm1.weight": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.3.norm2.weight": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.30.attn.k_norm.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.30.attn.proj.bias": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.30.attn.proj.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.30.attn.q_norm.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.30.attn.qkv.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.30.ls1": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.30.ls2": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.30.mlp.fc1.bias": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.30.mlp.fc1.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.30.mlp.fc2.bias": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.30.mlp.fc2.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.30.norm1.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.30.norm2.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.31.attn.k_norm.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.31.attn.proj.bias": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.31.attn.proj.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.31.attn.q_norm.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.31.attn.qkv.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.31.ls1": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.31.ls2": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.31.mlp.fc1.bias": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.31.mlp.fc1.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.31.mlp.fc2.bias": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.31.mlp.fc2.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.31.norm1.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.31.norm2.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.32.attn.k_norm.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.32.attn.proj.bias": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.32.attn.proj.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.32.attn.q_norm.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.32.attn.qkv.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.32.ls1": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.32.ls2": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.32.mlp.fc1.bias": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.32.mlp.fc1.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.32.mlp.fc2.bias": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.32.mlp.fc2.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.32.norm1.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.32.norm2.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.33.attn.k_norm.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.33.attn.proj.bias": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.33.attn.proj.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.33.attn.q_norm.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.33.attn.qkv.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.33.ls1": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.33.ls2": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.33.mlp.fc1.bias": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.33.mlp.fc1.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.33.mlp.fc2.bias": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.33.mlp.fc2.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.33.norm1.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.33.norm2.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.34.attn.k_norm.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.34.attn.proj.bias": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.34.attn.proj.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.34.attn.q_norm.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.34.attn.qkv.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.34.ls1": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.34.ls2": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.34.mlp.fc1.bias": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.34.mlp.fc1.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.34.mlp.fc2.bias": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.34.mlp.fc2.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.34.norm1.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.34.norm2.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.35.attn.k_norm.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.35.attn.proj.bias": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.35.attn.proj.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.35.attn.q_norm.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.35.attn.qkv.weight": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.35.ls1": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.35.ls2": "pytorch_model-00045-of-00046.bin", - "vision_model.encoder.layers.35.mlp.fc1.bias": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.35.mlp.fc1.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.35.mlp.fc2.bias": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.35.mlp.fc2.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.35.norm1.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.35.norm2.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.36.attn.k_norm.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.36.attn.proj.bias": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.36.attn.proj.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.36.attn.q_norm.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.36.attn.qkv.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.36.ls1": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.36.ls2": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.36.mlp.fc1.bias": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.36.mlp.fc1.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.36.mlp.fc2.bias": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.36.mlp.fc2.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.36.norm1.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.36.norm2.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.37.attn.k_norm.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.37.attn.proj.bias": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.37.attn.proj.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.37.attn.q_norm.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.37.attn.qkv.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.37.ls1": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.37.ls2": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.37.mlp.fc1.bias": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.37.mlp.fc1.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.37.mlp.fc2.bias": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.37.mlp.fc2.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.37.norm1.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.37.norm2.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.38.attn.k_norm.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.38.attn.proj.bias": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.38.attn.proj.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.38.attn.q_norm.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.38.attn.qkv.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.38.ls1": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.38.ls2": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.38.mlp.fc1.bias": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.38.mlp.fc1.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.38.mlp.fc2.bias": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.38.mlp.fc2.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.38.norm1.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.38.norm2.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.39.attn.k_norm.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.39.attn.proj.bias": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.39.attn.proj.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.39.attn.q_norm.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.39.attn.qkv.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.39.ls1": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.39.ls2": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.39.mlp.fc1.bias": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.39.mlp.fc1.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.39.mlp.fc2.bias": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.39.mlp.fc2.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.39.norm1.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.39.norm2.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.4.attn.k_norm.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.4.attn.proj.bias": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.4.attn.proj.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.4.attn.q_norm.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.4.attn.qkv.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.4.ls1": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.4.ls2": "pytorch_model-00042-of-00046.bin", - "vision_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.4.norm1.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.4.norm2.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.40.attn.k_norm.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.40.attn.proj.bias": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.40.attn.proj.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.40.attn.q_norm.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.40.attn.qkv.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.40.ls1": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.40.ls2": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.40.mlp.fc1.bias": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.40.mlp.fc1.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.40.mlp.fc2.bias": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.40.mlp.fc2.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.40.norm1.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.40.norm2.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.41.attn.k_norm.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.41.attn.proj.bias": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.41.attn.proj.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.41.attn.q_norm.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.41.attn.qkv.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.41.ls1": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.41.ls2": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.41.mlp.fc1.bias": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.41.mlp.fc1.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.41.mlp.fc2.bias": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.41.mlp.fc2.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.41.norm1.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.41.norm2.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.42.attn.k_norm.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.42.attn.proj.bias": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.42.attn.proj.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.42.attn.q_norm.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.42.attn.qkv.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.42.ls1": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.42.ls2": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.42.mlp.fc1.bias": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.42.mlp.fc1.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.42.mlp.fc2.bias": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.42.mlp.fc2.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.42.norm1.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.42.norm2.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.43.attn.k_norm.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.43.attn.proj.bias": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.43.attn.proj.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.43.attn.q_norm.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.43.attn.qkv.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.43.ls1": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.43.ls2": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.43.mlp.fc1.bias": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.43.mlp.fc1.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.43.mlp.fc2.bias": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.43.mlp.fc2.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.43.norm1.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.43.norm2.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.44.attn.k_norm.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.44.attn.proj.bias": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.44.attn.proj.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.44.attn.q_norm.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.44.attn.qkv.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.44.ls1": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.44.ls2": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.44.mlp.fc1.bias": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.44.mlp.fc1.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.44.mlp.fc2.bias": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.44.mlp.fc2.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.44.norm1.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.44.norm2.weight": "pytorch_model-00046-of-00046.bin", - "vision_model.encoder.layers.5.attn.k_norm.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.5.attn.proj.bias": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.5.attn.proj.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.5.attn.q_norm.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.5.attn.qkv.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.5.ls1": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.5.ls2": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.5.norm1.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.5.norm2.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.6.attn.k_norm.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.6.attn.proj.bias": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.6.attn.proj.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.6.attn.q_norm.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.6.attn.qkv.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.6.ls1": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.6.ls2": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.6.norm1.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.6.norm2.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.7.attn.k_norm.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.7.attn.proj.bias": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.7.attn.proj.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.7.attn.q_norm.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.7.attn.qkv.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.7.ls1": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.7.ls2": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.7.norm1.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.7.norm2.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.8.attn.k_norm.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.8.attn.proj.bias": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.8.attn.proj.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.8.attn.q_norm.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.8.attn.qkv.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.8.ls1": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.8.ls2": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.8.norm1.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.8.norm2.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.9.attn.k_norm.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.9.attn.proj.bias": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.9.attn.proj.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.9.attn.q_norm.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.9.attn.qkv.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.9.ls1": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.9.ls2": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.9.norm1.weight": "pytorch_model-00043-of-00046.bin", - "vision_model.encoder.layers.9.norm2.weight": "pytorch_model-00043-of-00046.bin" - } -}