{ "metadata": { "total_size": 16087194134 }, "weight_map": { "biobrain_decoder.gpt_model.final_norm.scale": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.0.attn_norm.scale": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.0.fc1.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.0.fc2.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.0.ffn_norm.scale": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.0.self_attn.key_linear.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.0.self_attn.out_linear.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.0.self_attn.query_linear.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.0.self_attn.value_linear.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.1.attn_norm.scale": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.1.fc1.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.1.fc2.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.1.ffn_norm.scale": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.1.self_attn.key_linear.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.1.self_attn.out_linear.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.1.self_attn.query_linear.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.1.self_attn.value_linear.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.10.attn_norm.scale": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.10.fc1.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.10.fc2.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.10.ffn_norm.scale": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.10.self_attn.key_linear.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.10.self_attn.out_linear.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.10.self_attn.query_linear.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.10.self_attn.value_linear.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.11.attn_norm.scale": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.11.fc1.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.11.fc2.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.11.ffn_norm.scale": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.11.self_attn.key_linear.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.11.self_attn.out_linear.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.11.self_attn.query_linear.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.11.self_attn.value_linear.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.12.attn_norm.scale": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.12.fc1.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.12.fc2.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.12.ffn_norm.scale": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.12.self_attn.key_linear.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.12.self_attn.out_linear.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.12.self_attn.query_linear.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.12.self_attn.value_linear.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.13.attn_norm.scale": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.13.fc1.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.13.fc2.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.13.ffn_norm.scale": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.13.self_attn.key_linear.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.13.self_attn.out_linear.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.13.self_attn.query_linear.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.13.self_attn.value_linear.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.14.attn_norm.scale": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.14.fc1.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.14.fc2.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.14.ffn_norm.scale": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.14.self_attn.key_linear.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.14.self_attn.out_linear.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.14.self_attn.query_linear.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.14.self_attn.value_linear.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.15.attn_norm.scale": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.15.fc1.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.15.fc2.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.15.ffn_norm.scale": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.15.self_attn.key_linear.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.15.self_attn.out_linear.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.15.self_attn.query_linear.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.15.self_attn.value_linear.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.16.attn_norm.scale": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.16.fc1.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.16.fc2.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.16.ffn_norm.scale": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.16.self_attn.key_linear.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.16.self_attn.out_linear.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.16.self_attn.query_linear.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.16.self_attn.value_linear.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.17.attn_norm.scale": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.17.fc1.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.17.fc2.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.17.ffn_norm.scale": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.17.self_attn.key_linear.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.17.self_attn.out_linear.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.17.self_attn.query_linear.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.17.self_attn.value_linear.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.18.attn_norm.scale": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.18.fc1.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.18.fc2.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.18.ffn_norm.scale": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.18.self_attn.key_linear.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.18.self_attn.out_linear.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.18.self_attn.query_linear.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.18.self_attn.value_linear.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.19.attn_norm.scale": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.19.fc1.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.19.fc2.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.19.ffn_norm.scale": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.19.self_attn.key_linear.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.19.self_attn.out_linear.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.19.self_attn.query_linear.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.19.self_attn.value_linear.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.2.attn_norm.scale": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.2.fc1.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.2.fc2.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.2.ffn_norm.scale": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.2.self_attn.key_linear.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.2.self_attn.out_linear.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.2.self_attn.query_linear.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.2.self_attn.value_linear.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.20.attn_norm.scale": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.20.fc1.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.20.fc2.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.20.ffn_norm.scale": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.20.self_attn.key_linear.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.20.self_attn.out_linear.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.20.self_attn.query_linear.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.20.self_attn.value_linear.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.21.attn_norm.scale": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.21.fc1.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.21.fc2.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.21.ffn_norm.scale": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.21.self_attn.key_linear.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.21.self_attn.out_linear.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.21.self_attn.query_linear.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.21.self_attn.value_linear.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.22.attn_norm.scale": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.22.fc1.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.22.fc2.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.22.ffn_norm.scale": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.22.self_attn.key_linear.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.22.self_attn.out_linear.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.22.self_attn.query_linear.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.22.self_attn.value_linear.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.23.attn_norm.scale": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.23.fc1.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.23.fc2.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.23.ffn_norm.scale": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.23.self_attn.key_linear.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.23.self_attn.out_linear.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.23.self_attn.query_linear.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.23.self_attn.value_linear.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.24.attn_norm.scale": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.24.fc1.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.24.fc2.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.24.ffn_norm.scale": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.24.self_attn.key_linear.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.24.self_attn.out_linear.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.24.self_attn.query_linear.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.24.self_attn.value_linear.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.25.attn_norm.scale": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.25.fc1.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.25.fc2.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.25.ffn_norm.scale": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.25.self_attn.key_linear.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.25.self_attn.out_linear.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.25.self_attn.query_linear.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.25.self_attn.value_linear.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.26.attn_norm.scale": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.26.fc1.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.26.fc2.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.26.ffn_norm.scale": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.26.self_attn.key_linear.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.26.self_attn.out_linear.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.26.self_attn.query_linear.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.26.self_attn.value_linear.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.27.attn_norm.scale": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.27.fc1.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.27.fc2.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.27.ffn_norm.scale": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.27.self_attn.key_linear.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.27.self_attn.out_linear.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.27.self_attn.query_linear.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.27.self_attn.value_linear.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.28.attn_norm.scale": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.28.fc1.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.28.fc2.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.28.ffn_norm.scale": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.28.self_attn.key_linear.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.28.self_attn.out_linear.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.28.self_attn.query_linear.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.28.self_attn.value_linear.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.29.attn_norm.scale": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.29.fc1.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.29.fc2.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.29.ffn_norm.scale": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.29.self_attn.key_linear.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.29.self_attn.out_linear.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.29.self_attn.query_linear.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.29.self_attn.value_linear.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.3.attn_norm.scale": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.3.fc1.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.3.fc2.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.3.ffn_norm.scale": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.3.self_attn.key_linear.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.3.self_attn.out_linear.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.3.self_attn.query_linear.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.3.self_attn.value_linear.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.30.attn_norm.scale": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.30.fc1.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.30.fc2.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.30.ffn_norm.scale": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.30.self_attn.key_linear.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.30.self_attn.out_linear.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.30.self_attn.query_linear.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.30.self_attn.value_linear.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.31.attn_norm.scale": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.31.fc1.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.31.fc2.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.31.ffn_norm.scale": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.31.self_attn.key_linear.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.31.self_attn.out_linear.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.31.self_attn.query_linear.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.31.self_attn.value_linear.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.4.attn_norm.scale": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.4.fc1.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.4.fc2.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.4.ffn_norm.scale": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.4.self_attn.key_linear.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.4.self_attn.out_linear.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.4.self_attn.query_linear.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.4.self_attn.value_linear.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.5.attn_norm.scale": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.5.fc1.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.5.fc2.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.5.ffn_norm.scale": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.5.self_attn.key_linear.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.5.self_attn.out_linear.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.5.self_attn.query_linear.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.5.self_attn.value_linear.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.6.attn_norm.scale": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.6.fc1.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.6.fc2.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.6.ffn_norm.scale": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.6.self_attn.key_linear.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.6.self_attn.out_linear.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.6.self_attn.query_linear.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.6.self_attn.value_linear.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.7.attn_norm.scale": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.7.fc1.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.7.fc2.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.7.ffn_norm.scale": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.7.self_attn.key_linear.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.7.self_attn.out_linear.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.7.self_attn.query_linear.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.7.self_attn.value_linear.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.8.attn_norm.scale": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.8.fc1.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.8.fc2.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.8.ffn_norm.scale": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.8.self_attn.key_linear.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.8.self_attn.out_linear.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.8.self_attn.query_linear.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.8.self_attn.value_linear.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.9.attn_norm.scale": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.9.fc1.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.9.fc2.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.9.ffn_norm.scale": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.9.self_attn.key_linear.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.9.self_attn.out_linear.weight": "model-00002-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.9.self_attn.query_linear.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.layers.9.self_attn.value_linear.weight": "model-00001-of-00004.safetensors", "biobrain_decoder.gpt_model.lm_head.fc.weight": "model-00003-of-00004.safetensors", "biobrain_decoder.gpt_model.token_embed.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.0.fc1.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.0.fc2.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.0.layer_norm_mlp.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.0.layer_norm_mlp.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.0.layer_norm_self_attention.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.0.layer_norm_self_attention.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.0.mha.output.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.0.mha.output.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.0.mha.w_k.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.0.mha.w_k.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.0.mha.w_q.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.0.mha.w_q.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.0.mha.w_v.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.0.mha.w_v.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.1.fc1.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.1.fc2.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.1.layer_norm_mlp.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.1.layer_norm_mlp.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.1.layer_norm_self_attention.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.1.layer_norm_self_attention.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.1.mha.output.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.1.mha.output.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.1.mha.w_k.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.1.mha.w_k.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.1.mha.w_q.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.1.mha.w_q.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.1.mha.w_v.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.1.mha.w_v.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.10.fc1.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.10.fc2.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.10.layer_norm_mlp.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.10.layer_norm_mlp.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.10.layer_norm_self_attention.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.10.layer_norm_self_attention.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.10.mha.output.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.10.mha.output.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.10.mha.w_k.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.10.mha.w_k.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.10.mha.w_q.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.10.mha.w_q.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.10.mha.w_v.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.10.mha.w_v.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.11.fc1.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.11.fc2.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.11.layer_norm_mlp.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.11.layer_norm_mlp.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.11.layer_norm_self_attention.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.11.layer_norm_self_attention.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.11.mha.output.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.11.mha.output.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.11.mha.w_k.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.11.mha.w_k.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.11.mha.w_q.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.11.mha.w_q.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.11.mha.w_v.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.11.mha.w_v.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.12.fc1.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.12.fc2.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.12.layer_norm_mlp.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.12.layer_norm_mlp.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.12.layer_norm_self_attention.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.12.layer_norm_self_attention.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.12.mha.output.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.12.mha.output.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.12.mha.w_k.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.12.mha.w_k.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.12.mha.w_q.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.12.mha.w_q.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.12.mha.w_v.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.12.mha.w_v.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.13.fc1.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.13.fc2.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.13.layer_norm_mlp.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.13.layer_norm_mlp.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.13.layer_norm_self_attention.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.13.layer_norm_self_attention.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.13.mha.output.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.13.mha.output.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.13.mha.w_k.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.13.mha.w_k.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.13.mha.w_q.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.13.mha.w_q.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.13.mha.w_v.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.13.mha.w_v.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.14.fc1.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.14.fc2.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.14.layer_norm_mlp.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.14.layer_norm_mlp.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.14.layer_norm_self_attention.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.14.layer_norm_self_attention.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.14.mha.output.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.14.mha.output.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.14.mha.w_k.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.14.mha.w_k.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.14.mha.w_q.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.14.mha.w_q.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.14.mha.w_v.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.14.mha.w_v.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.15.fc1.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.15.fc2.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.15.layer_norm_mlp.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.15.layer_norm_mlp.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.15.layer_norm_self_attention.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.15.layer_norm_self_attention.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.15.mha.output.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.15.mha.output.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.15.mha.w_k.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.15.mha.w_k.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.15.mha.w_q.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.15.mha.w_q.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.15.mha.w_v.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.15.mha.w_v.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.16.fc1.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.16.fc2.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.16.layer_norm_mlp.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.16.layer_norm_mlp.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.16.layer_norm_self_attention.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.16.layer_norm_self_attention.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.16.mha.output.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.16.mha.output.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.16.mha.w_k.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.16.mha.w_k.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.16.mha.w_q.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.16.mha.w_q.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.16.mha.w_v.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.16.mha.w_v.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.17.fc1.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.17.fc2.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.17.layer_norm_mlp.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.17.layer_norm_mlp.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.17.layer_norm_self_attention.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.17.layer_norm_self_attention.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.17.mha.output.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.17.mha.output.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.17.mha.w_k.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.17.mha.w_k.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.17.mha.w_q.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.17.mha.w_q.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.17.mha.w_v.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.17.mha.w_v.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.18.fc1.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.18.fc2.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.18.layer_norm_mlp.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.18.layer_norm_mlp.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.18.layer_norm_self_attention.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.18.layer_norm_self_attention.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.18.mha.output.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.18.mha.output.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.18.mha.w_k.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.18.mha.w_k.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.18.mha.w_q.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.18.mha.w_q.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.18.mha.w_v.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.18.mha.w_v.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.19.fc1.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.19.fc2.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.19.layer_norm_mlp.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.19.layer_norm_mlp.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.19.layer_norm_self_attention.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.19.layer_norm_self_attention.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.19.mha.output.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.19.mha.output.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.19.mha.w_k.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.19.mha.w_k.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.19.mha.w_q.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.19.mha.w_q.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.19.mha.w_v.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.19.mha.w_v.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.2.fc1.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.2.fc2.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.2.layer_norm_mlp.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.2.layer_norm_mlp.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.2.layer_norm_self_attention.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.2.layer_norm_self_attention.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.2.mha.output.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.2.mha.output.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.2.mha.w_k.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.2.mha.w_k.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.2.mha.w_q.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.2.mha.w_q.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.2.mha.w_v.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.2.mha.w_v.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.20.fc1.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.20.fc2.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.20.layer_norm_mlp.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.20.layer_norm_mlp.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.20.layer_norm_self_attention.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.20.layer_norm_self_attention.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.20.mha.output.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.20.mha.output.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.20.mha.w_k.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.20.mha.w_k.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.20.mha.w_q.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.20.mha.w_q.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.20.mha.w_v.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.20.mha.w_v.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.21.fc1.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.21.fc2.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.21.layer_norm_mlp.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.21.layer_norm_mlp.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.21.layer_norm_self_attention.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.21.layer_norm_self_attention.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.21.mha.output.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.21.mha.output.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.21.mha.w_k.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.21.mha.w_k.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.21.mha.w_q.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.21.mha.w_q.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.21.mha.w_v.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.21.mha.w_v.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.22.fc1.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.22.fc2.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.22.layer_norm_mlp.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.22.layer_norm_mlp.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.22.layer_norm_self_attention.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.22.layer_norm_self_attention.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.22.mha.output.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.22.mha.output.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.22.mha.w_k.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.22.mha.w_k.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.22.mha.w_q.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.22.mha.w_q.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.22.mha.w_v.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.22.mha.w_v.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.23.fc1.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.23.fc2.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.23.layer_norm_mlp.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.23.layer_norm_mlp.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.23.layer_norm_self_attention.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.23.layer_norm_self_attention.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.23.mha.output.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.23.mha.output.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.23.mha.w_k.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.23.mha.w_k.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.23.mha.w_q.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.23.mha.w_q.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.23.mha.w_v.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.23.mha.w_v.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.24.fc1.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.24.fc2.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.24.layer_norm_mlp.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.24.layer_norm_mlp.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.24.layer_norm_self_attention.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.24.layer_norm_self_attention.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.24.mha.output.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.24.mha.output.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.24.mha.w_k.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.24.mha.w_k.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.24.mha.w_q.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.24.mha.w_q.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.24.mha.w_v.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.24.mha.w_v.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.25.fc1.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.25.fc2.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.25.layer_norm_mlp.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.25.layer_norm_mlp.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.25.layer_norm_self_attention.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.25.layer_norm_self_attention.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.25.mha.output.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.25.mha.output.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.25.mha.w_k.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.25.mha.w_k.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.25.mha.w_q.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.25.mha.w_q.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.25.mha.w_v.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.25.mha.w_v.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.26.fc1.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.26.fc2.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.26.layer_norm_mlp.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.26.layer_norm_mlp.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.26.layer_norm_self_attention.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.26.layer_norm_self_attention.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.26.mha.output.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.26.mha.output.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.26.mha.w_k.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.26.mha.w_k.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.26.mha.w_q.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.26.mha.w_q.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.26.mha.w_v.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.26.mha.w_v.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.27.fc1.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.27.fc2.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.27.layer_norm_mlp.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.27.layer_norm_mlp.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.27.layer_norm_self_attention.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.27.layer_norm_self_attention.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.27.mha.output.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.27.mha.output.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.27.mha.w_k.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.27.mha.w_k.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.27.mha.w_q.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.27.mha.w_q.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.27.mha.w_v.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.27.mha.w_v.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.28.fc1.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.28.fc2.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.28.layer_norm_mlp.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.28.layer_norm_mlp.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.28.layer_norm_self_attention.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.28.layer_norm_self_attention.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.28.mha.output.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.28.mha.output.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.28.mha.w_k.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.28.mha.w_k.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.28.mha.w_q.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.28.mha.w_q.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.28.mha.w_v.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.28.mha.w_v.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.3.fc1.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.3.fc2.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.3.layer_norm_mlp.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.3.layer_norm_mlp.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.3.layer_norm_self_attention.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.3.layer_norm_self_attention.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.3.mha.output.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.3.mha.output.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.3.mha.w_k.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.3.mha.w_k.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.3.mha.w_q.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.3.mha.w_q.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.3.mha.w_v.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.3.mha.w_v.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.4.fc1.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.4.fc2.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.4.layer_norm_mlp.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.4.layer_norm_mlp.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.4.layer_norm_self_attention.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.4.layer_norm_self_attention.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.4.mha.output.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.4.mha.output.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.4.mha.w_k.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.4.mha.w_k.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.4.mha.w_q.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.4.mha.w_q.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.4.mha.w_v.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.4.mha.w_v.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.5.fc1.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.5.fc2.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.5.layer_norm_mlp.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.5.layer_norm_mlp.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.5.layer_norm_self_attention.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.5.layer_norm_self_attention.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.5.mha.output.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.5.mha.output.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.5.mha.w_k.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.5.mha.w_k.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.5.mha.w_q.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.5.mha.w_q.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.5.mha.w_v.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.5.mha.w_v.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.6.fc1.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.6.fc2.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.6.layer_norm_mlp.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.6.layer_norm_mlp.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.6.layer_norm_self_attention.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.6.layer_norm_self_attention.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.6.mha.output.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.6.mha.output.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.6.mha.w_k.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.6.mha.w_k.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.6.mha.w_q.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.6.mha.w_q.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.6.mha.w_v.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.6.mha.w_v.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.7.fc1.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.7.fc2.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.7.layer_norm_mlp.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.7.layer_norm_mlp.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.7.layer_norm_self_attention.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.7.layer_norm_self_attention.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.7.mha.output.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.7.mha.output.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.7.mha.w_k.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.7.mha.w_k.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.7.mha.w_q.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.7.mha.w_q.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.7.mha.w_v.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.7.mha.w_v.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.8.fc1.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.8.fc2.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.8.layer_norm_mlp.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.8.layer_norm_mlp.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.8.layer_norm_self_attention.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.8.layer_norm_self_attention.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.8.mha.output.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.8.mha.output.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.8.mha.w_k.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.8.mha.w_k.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.8.mha.w_q.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.8.mha.w_q.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.8.mha.w_v.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.8.mha.w_v.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.9.fc1.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.9.fc2.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.9.layer_norm_mlp.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.9.layer_norm_mlp.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.9.layer_norm_self_attention.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.9.layer_norm_self_attention.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.9.mha.output.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.9.mha.output.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.9.mha.w_k.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.9.mha.w_k.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.9.mha.w_q.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.9.mha.w_q.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.9.mha.w_v.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.attention_blocks.9.mha.w_v.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.embed_layer.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.lm_head._fc1.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.lm_head._fc1.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.lm_head._final_fc.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.lm_head._final_fc.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.lm_head._first_layer_norm.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.lm_head._first_layer_norm.weight": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.lm_head._second_layer_norm.bias": "model-00001-of-00004.safetensors", "biobrain_encoder.nt_model.lm_head._second_layer_norm.weight": "model-00001-of-00004.safetensors", "projection_model.bio_projection.bias": "model-00003-of-00004.safetensors", "projection_model.bio_projection.weight": "model-00003-of-00004.safetensors", "projection_model.perceiver_resampler.latent_queries": "model-00003-of-00004.safetensors", "projection_model.perceiver_resampler.layers.0.cross_attention_1.output.bias": "model-00003-of-00004.safetensors", "projection_model.perceiver_resampler.layers.0.cross_attention_1.output.weight": "model-00003-of-00004.safetensors", "projection_model.perceiver_resampler.layers.0.cross_attention_1.w_k.bias": "model-00003-of-00004.safetensors", "projection_model.perceiver_resampler.layers.0.cross_attention_1.w_k.weight": "model-00003-of-00004.safetensors", "projection_model.perceiver_resampler.layers.0.cross_attention_1.w_q.bias": "model-00003-of-00004.safetensors", "projection_model.perceiver_resampler.layers.0.cross_attention_1.w_q.weight": "model-00003-of-00004.safetensors", "projection_model.perceiver_resampler.layers.0.cross_attention_1.w_v.bias": "model-00003-of-00004.safetensors", "projection_model.perceiver_resampler.layers.0.cross_attention_1.w_v.weight": "model-00003-of-00004.safetensors", "projection_model.perceiver_resampler.layers.0.cross_attention_2.output.bias": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.0.cross_attention_2.output.weight": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.0.cross_attention_2.w_k.bias": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.0.cross_attention_2.w_k.weight": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.0.cross_attention_2.w_q.bias": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.0.cross_attention_2.w_q.weight": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.0.cross_attention_2.w_v.bias": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.0.cross_attention_2.w_v.weight": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.0.fc1.bias": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.0.fc1.weight": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.0.fc2.bias": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.0.fc2.weight": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.0.norm_cross_attention_1.bias": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.0.norm_cross_attention_1.weight": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.0.norm_cross_attention_2.bias": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.0.norm_cross_attention_2.weight": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.0.norm_mlp.bias": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.0.norm_mlp.weight": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.1.cross_attention_1.output.bias": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.1.cross_attention_1.output.weight": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.1.cross_attention_1.w_k.bias": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.1.cross_attention_1.w_k.weight": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.1.cross_attention_1.w_q.bias": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.1.cross_attention_1.w_q.weight": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.1.cross_attention_1.w_v.bias": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.1.cross_attention_1.w_v.weight": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.1.cross_attention_2.output.bias": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.1.cross_attention_2.output.weight": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.1.cross_attention_2.w_k.bias": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.1.cross_attention_2.w_k.weight": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.1.cross_attention_2.w_q.bias": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.1.cross_attention_2.w_q.weight": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.1.cross_attention_2.w_v.bias": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.1.cross_attention_2.w_v.weight": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.1.fc1.bias": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.1.fc1.weight": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.1.fc2.bias": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.1.fc2.weight": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.1.norm_cross_attention_1.bias": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.1.norm_cross_attention_1.weight": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.1.norm_cross_attention_2.bias": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.1.norm_cross_attention_2.weight": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.1.norm_mlp.bias": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.1.norm_mlp.weight": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.2.cross_attention_1.output.bias": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.2.cross_attention_1.output.weight": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.2.cross_attention_1.w_k.bias": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.2.cross_attention_1.w_k.weight": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.2.cross_attention_1.w_q.bias": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.2.cross_attention_1.w_q.weight": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.2.cross_attention_1.w_v.bias": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.2.cross_attention_1.w_v.weight": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.2.cross_attention_2.output.bias": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.2.cross_attention_2.output.weight": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.2.cross_attention_2.w_k.bias": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.2.cross_attention_2.w_k.weight": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.2.cross_attention_2.w_q.bias": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.2.cross_attention_2.w_q.weight": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.2.cross_attention_2.w_v.bias": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.2.cross_attention_2.w_v.weight": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.2.fc1.bias": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.2.fc1.weight": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.2.fc2.bias": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.2.fc2.weight": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.2.norm_cross_attention_1.bias": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.2.norm_cross_attention_1.weight": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.2.norm_cross_attention_2.bias": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.2.norm_cross_attention_2.weight": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.2.norm_mlp.bias": "model-00004-of-00004.safetensors", "projection_model.perceiver_resampler.layers.2.norm_mlp.weight": "model-00004-of-00004.safetensors", "projection_model.token_embedding.weight": "model-00003-of-00004.safetensors" } }