{ "metadata": { "total_size": 29666764800 }, "weight_map": { "lm_head.weight": "pytorch_model-00001-of-00011.bin", "model.embed_tokens.weight": "pytorch_model-00001-of-00011.bin", "model.layers.0.channel_mixer.l1.weight": "pytorch_model-00001-of-00011.bin", "model.layers.0.channel_mixer.l2.weight": "pytorch_model-00001-of-00011.bin", "model.layers.0.channel_mixer.l3.weight": "pytorch_model-00001-of-00011.bin", "model.layers.0.token_mixer.lrpe.theta": "pytorch_model-00001-of-00011.bin", "model.layers.0.token_mixer.out_proj.weight": "pytorch_model-00001-of-00011.bin", "model.layers.0.token_mixer.output_gate.0.weight": "pytorch_model-00001-of-00011.bin", "model.layers.0.token_mixer.output_gate.1.weight": "pytorch_model-00001-of-00011.bin", "model.layers.0.token_mixer.qkv_proj.weight": "pytorch_model-00001-of-00011.bin", "model.layers.1.channel_mixer.l1.weight": "pytorch_model-00001-of-00011.bin", "model.layers.1.channel_mixer.l2.weight": "pytorch_model-00001-of-00011.bin", "model.layers.1.channel_mixer.l3.weight": "pytorch_model-00001-of-00011.bin", "model.layers.1.token_mixer.out_proj.weight": "pytorch_model-00001-of-00011.bin", "model.layers.1.token_mixer.output_gate.0.weight": "pytorch_model-00001-of-00011.bin", "model.layers.1.token_mixer.output_gate.1.weight": "pytorch_model-00001-of-00011.bin", "model.layers.1.token_mixer.qkv_proj.weight": "pytorch_model-00001-of-00011.bin", "model.layers.10.channel_mixer.l1.weight": "pytorch_model-00003-of-00011.bin", "model.layers.10.channel_mixer.l2.weight": "pytorch_model-00003-of-00011.bin", "model.layers.10.channel_mixer.l3.weight": "pytorch_model-00003-of-00011.bin", "model.layers.10.token_mixer.out_proj.weight": "pytorch_model-00003-of-00011.bin", "model.layers.10.token_mixer.output_gate.0.weight": "pytorch_model-00003-of-00011.bin", "model.layers.10.token_mixer.output_gate.1.weight": "pytorch_model-00003-of-00011.bin", "model.layers.10.token_mixer.qkv_proj.weight": "pytorch_model-00003-of-00011.bin", "model.layers.11.channel_mixer.l1.weight": "pytorch_model-00004-of-00011.bin", "model.layers.11.channel_mixer.l2.weight": "pytorch_model-00004-of-00011.bin", "model.layers.11.channel_mixer.l3.weight": "pytorch_model-00004-of-00011.bin", "model.layers.11.token_mixer.out_proj.weight": "pytorch_model-00003-of-00011.bin", "model.layers.11.token_mixer.output_gate.0.weight": "pytorch_model-00003-of-00011.bin", "model.layers.11.token_mixer.output_gate.1.weight": "pytorch_model-00003-of-00011.bin", "model.layers.11.token_mixer.qkv_proj.weight": "pytorch_model-00003-of-00011.bin", "model.layers.12.channel_mixer.l1.weight": "pytorch_model-00004-of-00011.bin", "model.layers.12.channel_mixer.l2.weight": "pytorch_model-00004-of-00011.bin", "model.layers.12.channel_mixer.l3.weight": "pytorch_model-00004-of-00011.bin", "model.layers.12.token_mixer.out_proj.weight": "pytorch_model-00004-of-00011.bin", "model.layers.12.token_mixer.output_gate.0.weight": "pytorch_model-00004-of-00011.bin", "model.layers.12.token_mixer.output_gate.1.weight": "pytorch_model-00004-of-00011.bin", "model.layers.12.token_mixer.qkv_proj.weight": "pytorch_model-00004-of-00011.bin", "model.layers.13.channel_mixer.l1.weight": "pytorch_model-00004-of-00011.bin", "model.layers.13.channel_mixer.l2.weight": "pytorch_model-00004-of-00011.bin", "model.layers.13.channel_mixer.l3.weight": "pytorch_model-00004-of-00011.bin", "model.layers.13.token_mixer.out_proj.weight": "pytorch_model-00004-of-00011.bin", "model.layers.13.token_mixer.output_gate.0.weight": "pytorch_model-00004-of-00011.bin", "model.layers.13.token_mixer.output_gate.1.weight": "pytorch_model-00004-of-00011.bin", "model.layers.13.token_mixer.qkv_proj.weight": "pytorch_model-00004-of-00011.bin", "model.layers.14.channel_mixer.l1.weight": "pytorch_model-00004-of-00011.bin", "model.layers.14.channel_mixer.l2.weight": "pytorch_model-00004-of-00011.bin", "model.layers.14.channel_mixer.l3.weight": "pytorch_model-00004-of-00011.bin", "model.layers.14.token_mixer.out_proj.weight": "pytorch_model-00004-of-00011.bin", "model.layers.14.token_mixer.output_gate.0.weight": "pytorch_model-00004-of-00011.bin", "model.layers.14.token_mixer.output_gate.1.weight": "pytorch_model-00004-of-00011.bin", "model.layers.14.token_mixer.qkv_proj.weight": "pytorch_model-00004-of-00011.bin", "model.layers.15.channel_mixer.l1.weight": "pytorch_model-00004-of-00011.bin", "model.layers.15.channel_mixer.l2.weight": "pytorch_model-00005-of-00011.bin", "model.layers.15.channel_mixer.l3.weight": "pytorch_model-00005-of-00011.bin", "model.layers.15.token_mixer.out_proj.weight": "pytorch_model-00004-of-00011.bin", "model.layers.15.token_mixer.output_gate.0.weight": "pytorch_model-00004-of-00011.bin", "model.layers.15.token_mixer.output_gate.1.weight": "pytorch_model-00004-of-00011.bin", "model.layers.15.token_mixer.qkv_proj.weight": "pytorch_model-00004-of-00011.bin", "model.layers.16.channel_mixer.l1.weight": "pytorch_model-00005-of-00011.bin", "model.layers.16.channel_mixer.l2.weight": "pytorch_model-00005-of-00011.bin", "model.layers.16.channel_mixer.l3.weight": "pytorch_model-00005-of-00011.bin", "model.layers.16.token_mixer.out_proj.weight": "pytorch_model-00005-of-00011.bin", "model.layers.16.token_mixer.output_gate.0.weight": "pytorch_model-00005-of-00011.bin", "model.layers.16.token_mixer.output_gate.1.weight": "pytorch_model-00005-of-00011.bin", "model.layers.16.token_mixer.qkv_proj.weight": "pytorch_model-00005-of-00011.bin", "model.layers.17.channel_mixer.l1.weight": "pytorch_model-00005-of-00011.bin", "model.layers.17.channel_mixer.l2.weight": "pytorch_model-00005-of-00011.bin", "model.layers.17.channel_mixer.l3.weight": "pytorch_model-00005-of-00011.bin", "model.layers.17.token_mixer.out_proj.weight": "pytorch_model-00005-of-00011.bin", "model.layers.17.token_mixer.output_gate.0.weight": "pytorch_model-00005-of-00011.bin", "model.layers.17.token_mixer.output_gate.1.weight": "pytorch_model-00005-of-00011.bin", "model.layers.17.token_mixer.qkv_proj.weight": "pytorch_model-00005-of-00011.bin", "model.layers.18.channel_mixer.l1.weight": "pytorch_model-00005-of-00011.bin", "model.layers.18.channel_mixer.l2.weight": "pytorch_model-00005-of-00011.bin", "model.layers.18.channel_mixer.l3.weight": "pytorch_model-00005-of-00011.bin", "model.layers.18.token_mixer.out_proj.weight": "pytorch_model-00005-of-00011.bin", "model.layers.18.token_mixer.output_gate.0.weight": "pytorch_model-00005-of-00011.bin", "model.layers.18.token_mixer.output_gate.1.weight": "pytorch_model-00005-of-00011.bin", "model.layers.18.token_mixer.qkv_proj.weight": "pytorch_model-00005-of-00011.bin", "model.layers.19.channel_mixer.l1.weight": "pytorch_model-00005-of-00011.bin", "model.layers.19.channel_mixer.l2.weight": "pytorch_model-00005-of-00011.bin", "model.layers.19.channel_mixer.l3.weight": "pytorch_model-00006-of-00011.bin", "model.layers.19.token_mixer.out_proj.weight": "pytorch_model-00005-of-00011.bin", "model.layers.19.token_mixer.output_gate.0.weight": "pytorch_model-00005-of-00011.bin", "model.layers.19.token_mixer.output_gate.1.weight": "pytorch_model-00005-of-00011.bin", "model.layers.19.token_mixer.qkv_proj.weight": "pytorch_model-00005-of-00011.bin", "model.layers.2.channel_mixer.l1.weight": "pytorch_model-00001-of-00011.bin", "model.layers.2.channel_mixer.l2.weight": "pytorch_model-00001-of-00011.bin", "model.layers.2.channel_mixer.l3.weight": "pytorch_model-00002-of-00011.bin", "model.layers.2.token_mixer.out_proj.weight": "pytorch_model-00001-of-00011.bin", "model.layers.2.token_mixer.output_gate.0.weight": "pytorch_model-00001-of-00011.bin", "model.layers.2.token_mixer.output_gate.1.weight": "pytorch_model-00001-of-00011.bin", "model.layers.2.token_mixer.qkv_proj.weight": "pytorch_model-00001-of-00011.bin", "model.layers.20.channel_mixer.l1.weight": "pytorch_model-00006-of-00011.bin", "model.layers.20.channel_mixer.l2.weight": "pytorch_model-00006-of-00011.bin", "model.layers.20.channel_mixer.l3.weight": "pytorch_model-00006-of-00011.bin", "model.layers.20.token_mixer.out_proj.weight": "pytorch_model-00006-of-00011.bin", "model.layers.20.token_mixer.output_gate.0.weight": "pytorch_model-00006-of-00011.bin", "model.layers.20.token_mixer.output_gate.1.weight": "pytorch_model-00006-of-00011.bin", "model.layers.20.token_mixer.qkv_proj.weight": "pytorch_model-00006-of-00011.bin", "model.layers.21.channel_mixer.l1.weight": "pytorch_model-00006-of-00011.bin", "model.layers.21.channel_mixer.l2.weight": "pytorch_model-00006-of-00011.bin", "model.layers.21.channel_mixer.l3.weight": "pytorch_model-00006-of-00011.bin", "model.layers.21.token_mixer.out_proj.weight": "pytorch_model-00006-of-00011.bin", "model.layers.21.token_mixer.output_gate.0.weight": "pytorch_model-00006-of-00011.bin", "model.layers.21.token_mixer.output_gate.1.weight": "pytorch_model-00006-of-00011.bin", "model.layers.21.token_mixer.qkv_proj.weight": "pytorch_model-00006-of-00011.bin", "model.layers.22.channel_mixer.l1.weight": "pytorch_model-00006-of-00011.bin", "model.layers.22.channel_mixer.l2.weight": "pytorch_model-00006-of-00011.bin", "model.layers.22.channel_mixer.l3.weight": "pytorch_model-00006-of-00011.bin", "model.layers.22.token_mixer.out_proj.weight": "pytorch_model-00006-of-00011.bin", "model.layers.22.token_mixer.output_gate.0.weight": "pytorch_model-00006-of-00011.bin", "model.layers.22.token_mixer.output_gate.1.weight": "pytorch_model-00006-of-00011.bin", "model.layers.22.token_mixer.qkv_proj.weight": "pytorch_model-00006-of-00011.bin", "model.layers.23.channel_mixer.l1.weight": "pytorch_model-00006-of-00011.bin", "model.layers.23.channel_mixer.l2.weight": "pytorch_model-00006-of-00011.bin", "model.layers.23.channel_mixer.l3.weight": "pytorch_model-00006-of-00011.bin", "model.layers.23.token_mixer.out_proj.weight": "pytorch_model-00006-of-00011.bin", "model.layers.23.token_mixer.output_gate.0.weight": "pytorch_model-00006-of-00011.bin", "model.layers.23.token_mixer.output_gate.1.weight": "pytorch_model-00006-of-00011.bin", "model.layers.23.token_mixer.qkv_proj.weight": "pytorch_model-00006-of-00011.bin", "model.layers.24.channel_mixer.l1.weight": "pytorch_model-00007-of-00011.bin", "model.layers.24.channel_mixer.l2.weight": "pytorch_model-00007-of-00011.bin", "model.layers.24.channel_mixer.l3.weight": "pytorch_model-00007-of-00011.bin", "model.layers.24.token_mixer.out_proj.weight": "pytorch_model-00006-of-00011.bin", "model.layers.24.token_mixer.output_gate.0.weight": "pytorch_model-00007-of-00011.bin", "model.layers.24.token_mixer.output_gate.1.weight": "pytorch_model-00007-of-00011.bin", "model.layers.24.token_mixer.qkv_proj.weight": "pytorch_model-00007-of-00011.bin", "model.layers.25.channel_mixer.l1.weight": "pytorch_model-00007-of-00011.bin", "model.layers.25.channel_mixer.l2.weight": "pytorch_model-00007-of-00011.bin", "model.layers.25.channel_mixer.l3.weight": "pytorch_model-00007-of-00011.bin", "model.layers.25.token_mixer.out_proj.weight": "pytorch_model-00007-of-00011.bin", "model.layers.25.token_mixer.output_gate.0.weight": "pytorch_model-00007-of-00011.bin", "model.layers.25.token_mixer.output_gate.1.weight": "pytorch_model-00007-of-00011.bin", "model.layers.25.token_mixer.qkv_proj.weight": "pytorch_model-00007-of-00011.bin", "model.layers.26.channel_mixer.l1.weight": "pytorch_model-00007-of-00011.bin", "model.layers.26.channel_mixer.l2.weight": "pytorch_model-00007-of-00011.bin", "model.layers.26.channel_mixer.l3.weight": "pytorch_model-00007-of-00011.bin", "model.layers.26.token_mixer.out_proj.weight": "pytorch_model-00007-of-00011.bin", "model.layers.26.token_mixer.output_gate.0.weight": "pytorch_model-00007-of-00011.bin", "model.layers.26.token_mixer.output_gate.1.weight": "pytorch_model-00007-of-00011.bin", "model.layers.26.token_mixer.qkv_proj.weight": "pytorch_model-00007-of-00011.bin", "model.layers.27.channel_mixer.l1.weight": "pytorch_model-00007-of-00011.bin", "model.layers.27.channel_mixer.l2.weight": "pytorch_model-00007-of-00011.bin", "model.layers.27.channel_mixer.l3.weight": "pytorch_model-00007-of-00011.bin", "model.layers.27.token_mixer.out_proj.weight": "pytorch_model-00007-of-00011.bin", "model.layers.27.token_mixer.output_gate.0.weight": "pytorch_model-00007-of-00011.bin", "model.layers.27.token_mixer.output_gate.1.weight": "pytorch_model-00007-of-00011.bin", "model.layers.27.token_mixer.qkv_proj.weight": "pytorch_model-00007-of-00011.bin", "model.layers.28.channel_mixer.l1.weight": "pytorch_model-00008-of-00011.bin", "model.layers.28.channel_mixer.l2.weight": "pytorch_model-00008-of-00011.bin", "model.layers.28.channel_mixer.l3.weight": "pytorch_model-00008-of-00011.bin", "model.layers.28.token_mixer.out_proj.weight": "pytorch_model-00007-of-00011.bin", "model.layers.28.token_mixer.output_gate.0.weight": "pytorch_model-00007-of-00011.bin", "model.layers.28.token_mixer.output_gate.1.weight": "pytorch_model-00007-of-00011.bin", "model.layers.28.token_mixer.qkv_proj.weight": "pytorch_model-00007-of-00011.bin", "model.layers.29.channel_mixer.l1.weight": "pytorch_model-00008-of-00011.bin", "model.layers.29.channel_mixer.l2.weight": "pytorch_model-00008-of-00011.bin", "model.layers.29.channel_mixer.l3.weight": "pytorch_model-00008-of-00011.bin", "model.layers.29.token_mixer.out_proj.weight": "pytorch_model-00008-of-00011.bin", "model.layers.29.token_mixer.output_gate.0.weight": "pytorch_model-00008-of-00011.bin", "model.layers.29.token_mixer.output_gate.1.weight": "pytorch_model-00008-of-00011.bin", "model.layers.29.token_mixer.qkv_proj.weight": "pytorch_model-00008-of-00011.bin", "model.layers.3.channel_mixer.l1.weight": "pytorch_model-00002-of-00011.bin", "model.layers.3.channel_mixer.l2.weight": "pytorch_model-00002-of-00011.bin", "model.layers.3.channel_mixer.l3.weight": "pytorch_model-00002-of-00011.bin", "model.layers.3.token_mixer.out_proj.weight": "pytorch_model-00002-of-00011.bin", "model.layers.3.token_mixer.output_gate.0.weight": "pytorch_model-00002-of-00011.bin", "model.layers.3.token_mixer.output_gate.1.weight": "pytorch_model-00002-of-00011.bin", "model.layers.3.token_mixer.qkv_proj.weight": "pytorch_model-00002-of-00011.bin", "model.layers.30.channel_mixer.l1.weight": "pytorch_model-00008-of-00011.bin", "model.layers.30.channel_mixer.l2.weight": "pytorch_model-00008-of-00011.bin", "model.layers.30.channel_mixer.l3.weight": "pytorch_model-00008-of-00011.bin", "model.layers.30.token_mixer.out_proj.weight": "pytorch_model-00008-of-00011.bin", "model.layers.30.token_mixer.output_gate.0.weight": "pytorch_model-00008-of-00011.bin", "model.layers.30.token_mixer.output_gate.1.weight": "pytorch_model-00008-of-00011.bin", "model.layers.30.token_mixer.qkv_proj.weight": "pytorch_model-00008-of-00011.bin", "model.layers.31.channel_mixer.l1.weight": "pytorch_model-00008-of-00011.bin", "model.layers.31.channel_mixer.l2.weight": "pytorch_model-00008-of-00011.bin", "model.layers.31.channel_mixer.l3.weight": "pytorch_model-00008-of-00011.bin", "model.layers.31.token_mixer.out_proj.weight": "pytorch_model-00008-of-00011.bin", "model.layers.31.token_mixer.output_gate.0.weight": "pytorch_model-00008-of-00011.bin", "model.layers.31.token_mixer.output_gate.1.weight": "pytorch_model-00008-of-00011.bin", "model.layers.31.token_mixer.qkv_proj.weight": "pytorch_model-00008-of-00011.bin", "model.layers.32.channel_mixer.l1.weight": "pytorch_model-00008-of-00011.bin", "model.layers.32.channel_mixer.l2.weight": "pytorch_model-00009-of-00011.bin", "model.layers.32.channel_mixer.l3.weight": "pytorch_model-00009-of-00011.bin", "model.layers.32.token_mixer.out_proj.weight": "pytorch_model-00008-of-00011.bin", "model.layers.32.token_mixer.output_gate.0.weight": "pytorch_model-00008-of-00011.bin", "model.layers.32.token_mixer.output_gate.1.weight": "pytorch_model-00008-of-00011.bin", "model.layers.32.token_mixer.qkv_proj.weight": "pytorch_model-00008-of-00011.bin", "model.layers.33.channel_mixer.l1.weight": "pytorch_model-00009-of-00011.bin", "model.layers.33.channel_mixer.l2.weight": "pytorch_model-00009-of-00011.bin", "model.layers.33.channel_mixer.l3.weight": "pytorch_model-00009-of-00011.bin", "model.layers.33.token_mixer.out_proj.weight": "pytorch_model-00009-of-00011.bin", "model.layers.33.token_mixer.output_gate.0.weight": "pytorch_model-00009-of-00011.bin", "model.layers.33.token_mixer.output_gate.1.weight": "pytorch_model-00009-of-00011.bin", "model.layers.33.token_mixer.qkv_proj.weight": "pytorch_model-00009-of-00011.bin", "model.layers.34.channel_mixer.l1.weight": "pytorch_model-00009-of-00011.bin", "model.layers.34.channel_mixer.l2.weight": "pytorch_model-00009-of-00011.bin", "model.layers.34.channel_mixer.l3.weight": "pytorch_model-00009-of-00011.bin", "model.layers.34.token_mixer.out_proj.weight": "pytorch_model-00009-of-00011.bin", "model.layers.34.token_mixer.output_gate.0.weight": "pytorch_model-00009-of-00011.bin", "model.layers.34.token_mixer.output_gate.1.weight": "pytorch_model-00009-of-00011.bin", "model.layers.34.token_mixer.qkv_proj.weight": "pytorch_model-00009-of-00011.bin", "model.layers.35.channel_mixer.l1.weight": "pytorch_model-00009-of-00011.bin", "model.layers.35.channel_mixer.l2.weight": "pytorch_model-00009-of-00011.bin", "model.layers.35.channel_mixer.l3.weight": "pytorch_model-00009-of-00011.bin", "model.layers.35.token_mixer.out_proj.weight": "pytorch_model-00009-of-00011.bin", "model.layers.35.token_mixer.output_gate.0.weight": "pytorch_model-00009-of-00011.bin", "model.layers.35.token_mixer.output_gate.1.weight": "pytorch_model-00009-of-00011.bin", "model.layers.35.token_mixer.qkv_proj.weight": "pytorch_model-00009-of-00011.bin", "model.layers.36.channel_mixer.l1.weight": "pytorch_model-00009-of-00011.bin", "model.layers.36.channel_mixer.l2.weight": "pytorch_model-00009-of-00011.bin", "model.layers.36.channel_mixer.l3.weight": "pytorch_model-00010-of-00011.bin", "model.layers.36.token_mixer.out_proj.weight": "pytorch_model-00009-of-00011.bin", "model.layers.36.token_mixer.output_gate.0.weight": "pytorch_model-00009-of-00011.bin", "model.layers.36.token_mixer.output_gate.1.weight": "pytorch_model-00009-of-00011.bin", "model.layers.36.token_mixer.qkv_proj.weight": "pytorch_model-00009-of-00011.bin", "model.layers.37.channel_mixer.l1.weight": "pytorch_model-00010-of-00011.bin", "model.layers.37.channel_mixer.l2.weight": "pytorch_model-00010-of-00011.bin", "model.layers.37.channel_mixer.l3.weight": "pytorch_model-00010-of-00011.bin", "model.layers.37.token_mixer.out_proj.weight": "pytorch_model-00010-of-00011.bin", "model.layers.37.token_mixer.output_gate.0.weight": "pytorch_model-00010-of-00011.bin", "model.layers.37.token_mixer.output_gate.1.weight": "pytorch_model-00010-of-00011.bin", "model.layers.37.token_mixer.qkv_proj.weight": "pytorch_model-00010-of-00011.bin", "model.layers.38.channel_mixer.l1.weight": "pytorch_model-00010-of-00011.bin", "model.layers.38.channel_mixer.l2.weight": "pytorch_model-00010-of-00011.bin", "model.layers.38.channel_mixer.l3.weight": "pytorch_model-00010-of-00011.bin", "model.layers.38.token_mixer.out_proj.weight": "pytorch_model-00010-of-00011.bin", "model.layers.38.token_mixer.output_gate.0.weight": "pytorch_model-00010-of-00011.bin", "model.layers.38.token_mixer.output_gate.1.weight": "pytorch_model-00010-of-00011.bin", "model.layers.38.token_mixer.qkv_proj.weight": "pytorch_model-00010-of-00011.bin", "model.layers.39.channel_mixer.l1.weight": "pytorch_model-00010-of-00011.bin", "model.layers.39.channel_mixer.l2.weight": "pytorch_model-00010-of-00011.bin", "model.layers.39.channel_mixer.l3.weight": "pytorch_model-00010-of-00011.bin", "model.layers.39.token_mixer.out_proj.weight": "pytorch_model-00010-of-00011.bin", "model.layers.39.token_mixer.output_gate.0.weight": "pytorch_model-00010-of-00011.bin", "model.layers.39.token_mixer.output_gate.1.weight": "pytorch_model-00010-of-00011.bin", "model.layers.39.token_mixer.qkv_proj.weight": "pytorch_model-00010-of-00011.bin", "model.layers.4.channel_mixer.l1.weight": "pytorch_model-00002-of-00011.bin", "model.layers.4.channel_mixer.l2.weight": "pytorch_model-00002-of-00011.bin", "model.layers.4.channel_mixer.l3.weight": "pytorch_model-00002-of-00011.bin", "model.layers.4.token_mixer.out_proj.weight": "pytorch_model-00002-of-00011.bin", "model.layers.4.token_mixer.output_gate.0.weight": "pytorch_model-00002-of-00011.bin", "model.layers.4.token_mixer.output_gate.1.weight": "pytorch_model-00002-of-00011.bin", "model.layers.4.token_mixer.qkv_proj.weight": "pytorch_model-00002-of-00011.bin", "model.layers.40.channel_mixer.l1.weight": "pytorch_model-00010-of-00011.bin", "model.layers.40.channel_mixer.l2.weight": "pytorch_model-00010-of-00011.bin", "model.layers.40.channel_mixer.l3.weight": "pytorch_model-00010-of-00011.bin", "model.layers.40.token_mixer.out_proj.weight": "pytorch_model-00010-of-00011.bin", "model.layers.40.token_mixer.output_gate.0.weight": "pytorch_model-00010-of-00011.bin", "model.layers.40.token_mixer.output_gate.1.weight": "pytorch_model-00010-of-00011.bin", "model.layers.40.token_mixer.qkv_proj.weight": "pytorch_model-00010-of-00011.bin", "model.layers.41.channel_mixer.l1.weight": "pytorch_model-00011-of-00011.bin", "model.layers.41.channel_mixer.l2.weight": "pytorch_model-00011-of-00011.bin", "model.layers.41.channel_mixer.l3.weight": "pytorch_model-00011-of-00011.bin", "model.layers.41.token_mixer.out_proj.weight": "pytorch_model-00010-of-00011.bin", "model.layers.41.token_mixer.output_gate.0.weight": "pytorch_model-00011-of-00011.bin", "model.layers.41.token_mixer.output_gate.1.weight": "pytorch_model-00011-of-00011.bin", "model.layers.41.token_mixer.qkv_proj.weight": "pytorch_model-00011-of-00011.bin", "model.layers.5.channel_mixer.l1.weight": "pytorch_model-00002-of-00011.bin", "model.layers.5.channel_mixer.l2.weight": "pytorch_model-00002-of-00011.bin", "model.layers.5.channel_mixer.l3.weight": "pytorch_model-00002-of-00011.bin", "model.layers.5.token_mixer.out_proj.weight": "pytorch_model-00002-of-00011.bin", "model.layers.5.token_mixer.output_gate.0.weight": "pytorch_model-00002-of-00011.bin", "model.layers.5.token_mixer.output_gate.1.weight": "pytorch_model-00002-of-00011.bin", "model.layers.5.token_mixer.qkv_proj.weight": "pytorch_model-00002-of-00011.bin", "model.layers.6.channel_mixer.l1.weight": "pytorch_model-00002-of-00011.bin", "model.layers.6.channel_mixer.l2.weight": "pytorch_model-00002-of-00011.bin", "model.layers.6.channel_mixer.l3.weight": "pytorch_model-00002-of-00011.bin", "model.layers.6.token_mixer.out_proj.weight": "pytorch_model-00002-of-00011.bin", "model.layers.6.token_mixer.output_gate.0.weight": "pytorch_model-00002-of-00011.bin", "model.layers.6.token_mixer.output_gate.1.weight": "pytorch_model-00002-of-00011.bin", "model.layers.6.token_mixer.qkv_proj.weight": "pytorch_model-00002-of-00011.bin", "model.layers.7.channel_mixer.l1.weight": "pytorch_model-00003-of-00011.bin", "model.layers.7.channel_mixer.l2.weight": "pytorch_model-00003-of-00011.bin", "model.layers.7.channel_mixer.l3.weight": "pytorch_model-00003-of-00011.bin", "model.layers.7.token_mixer.out_proj.weight": "pytorch_model-00002-of-00011.bin", "model.layers.7.token_mixer.output_gate.0.weight": "pytorch_model-00003-of-00011.bin", "model.layers.7.token_mixer.output_gate.1.weight": "pytorch_model-00003-of-00011.bin", "model.layers.7.token_mixer.qkv_proj.weight": "pytorch_model-00003-of-00011.bin", "model.layers.8.channel_mixer.l1.weight": "pytorch_model-00003-of-00011.bin", "model.layers.8.channel_mixer.l2.weight": "pytorch_model-00003-of-00011.bin", "model.layers.8.channel_mixer.l3.weight": "pytorch_model-00003-of-00011.bin", "model.layers.8.token_mixer.out_proj.weight": "pytorch_model-00003-of-00011.bin", "model.layers.8.token_mixer.output_gate.0.weight": "pytorch_model-00003-of-00011.bin", "model.layers.8.token_mixer.output_gate.1.weight": "pytorch_model-00003-of-00011.bin", "model.layers.8.token_mixer.qkv_proj.weight": "pytorch_model-00003-of-00011.bin", "model.layers.9.channel_mixer.l1.weight": "pytorch_model-00003-of-00011.bin", "model.layers.9.channel_mixer.l2.weight": "pytorch_model-00003-of-00011.bin", "model.layers.9.channel_mixer.l3.weight": "pytorch_model-00003-of-00011.bin", "model.layers.9.token_mixer.out_proj.weight": "pytorch_model-00003-of-00011.bin", "model.layers.9.token_mixer.output_gate.0.weight": "pytorch_model-00003-of-00011.bin", "model.layers.9.token_mixer.output_gate.1.weight": "pytorch_model-00003-of-00011.bin", "model.layers.9.token_mixer.qkv_proj.weight": "pytorch_model-00003-of-00011.bin" } }