{ "metadata": { "total_size": 30191321088 }, "weight_map": { "model.transformer.blocks.0.att_proj.weight": "model-00001-of-00007.safetensors", "model.transformer.blocks.0.attn_out.weight": "model-00001-of-00007.safetensors", "model.transformer.blocks.0.experts.0.ff_out.weight": "model-00001-of-00007.safetensors", "model.transformer.blocks.0.experts.0.ff_proj.weight": "model-00001-of-00007.safetensors", "model.transformer.blocks.0.experts.1.ff_out.weight": "model-00001-of-00007.safetensors", "model.transformer.blocks.0.experts.1.ff_proj.weight": "model-00001-of-00007.safetensors", "model.transformer.blocks.0.experts.2.ff_out.weight": "model-00001-of-00007.safetensors", "model.transformer.blocks.0.experts.2.ff_proj.weight": "model-00001-of-00007.safetensors", "model.transformer.blocks.0.experts.3.ff_out.weight": "model-00001-of-00007.safetensors", "model.transformer.blocks.0.experts.3.ff_proj.weight": "model-00001-of-00007.safetensors", "model.transformer.blocks.0.gate.wg.weight": "model-00001-of-00007.safetensors", "model.transformer.blocks.1.att_proj.weight": "model-00001-of-00007.safetensors", "model.transformer.blocks.1.attn_out.weight": "model-00001-of-00007.safetensors", "model.transformer.blocks.1.ff_out.weight": "model-00001-of-00007.safetensors", "model.transformer.blocks.1.ff_proj.weight": "model-00001-of-00007.safetensors", "model.transformer.blocks.10.att_proj.weight": "model-00003-of-00007.safetensors", "model.transformer.blocks.10.attn_out.weight": "model-00003-of-00007.safetensors", "model.transformer.blocks.10.experts.0.ff_out.weight": "model-00003-of-00007.safetensors", "model.transformer.blocks.10.experts.0.ff_proj.weight": "model-00003-of-00007.safetensors", "model.transformer.blocks.10.experts.1.ff_out.weight": "model-00004-of-00007.safetensors", "model.transformer.blocks.10.experts.1.ff_proj.weight": "model-00003-of-00007.safetensors", "model.transformer.blocks.10.experts.2.ff_out.weight": "model-00004-of-00007.safetensors", "model.transformer.blocks.10.experts.2.ff_proj.weight": "model-00004-of-00007.safetensors", "model.transformer.blocks.10.experts.3.ff_out.weight": "model-00004-of-00007.safetensors", "model.transformer.blocks.10.experts.3.ff_proj.weight": "model-00004-of-00007.safetensors", "model.transformer.blocks.10.gate.wg.weight": "model-00003-of-00007.safetensors", "model.transformer.blocks.11.att_proj.weight": "model-00004-of-00007.safetensors", "model.transformer.blocks.11.attn_out.weight": "model-00004-of-00007.safetensors", "model.transformer.blocks.11.ff_out.weight": "model-00004-of-00007.safetensors", "model.transformer.blocks.11.ff_proj.weight": "model-00004-of-00007.safetensors", "model.transformer.blocks.12.att_proj.weight": "model-00004-of-00007.safetensors", "model.transformer.blocks.12.attn_out.weight": "model-00004-of-00007.safetensors", "model.transformer.blocks.12.experts.0.ff_out.weight": "model-00004-of-00007.safetensors", "model.transformer.blocks.12.experts.0.ff_proj.weight": "model-00004-of-00007.safetensors", "model.transformer.blocks.12.experts.1.ff_out.weight": "model-00004-of-00007.safetensors", "model.transformer.blocks.12.experts.1.ff_proj.weight": "model-00004-of-00007.safetensors", "model.transformer.blocks.12.experts.2.ff_out.weight": "model-00004-of-00007.safetensors", "model.transformer.blocks.12.experts.2.ff_proj.weight": "model-00004-of-00007.safetensors", "model.transformer.blocks.12.experts.3.ff_out.weight": "model-00004-of-00007.safetensors", "model.transformer.blocks.12.experts.3.ff_proj.weight": "model-00004-of-00007.safetensors", "model.transformer.blocks.12.gate.wg.weight": "model-00004-of-00007.safetensors", "model.transformer.blocks.13.att_proj.weight": "model-00004-of-00007.safetensors", "model.transformer.blocks.13.attn_out.weight": "model-00004-of-00007.safetensors", "model.transformer.blocks.13.ff_out.weight": "model-00004-of-00007.safetensors", "model.transformer.blocks.13.ff_proj.weight": "model-00004-of-00007.safetensors", "model.transformer.blocks.14.att_proj.weight": "model-00004-of-00007.safetensors", "model.transformer.blocks.14.attn_out.weight": "model-00004-of-00007.safetensors", "model.transformer.blocks.14.experts.0.ff_out.weight": "model-00004-of-00007.safetensors", "model.transformer.blocks.14.experts.0.ff_proj.weight": "model-00004-of-00007.safetensors", "model.transformer.blocks.14.experts.1.ff_out.weight": "model-00005-of-00007.safetensors", "model.transformer.blocks.14.experts.1.ff_proj.weight": "model-00005-of-00007.safetensors", "model.transformer.blocks.14.experts.2.ff_out.weight": "model-00005-of-00007.safetensors", "model.transformer.blocks.14.experts.2.ff_proj.weight": "model-00005-of-00007.safetensors", "model.transformer.blocks.14.experts.3.ff_out.weight": "model-00005-of-00007.safetensors", "model.transformer.blocks.14.experts.3.ff_proj.weight": "model-00005-of-00007.safetensors", "model.transformer.blocks.14.gate.wg.weight": "model-00004-of-00007.safetensors", "model.transformer.blocks.15.att_proj.weight": "model-00005-of-00007.safetensors", "model.transformer.blocks.15.attn_out.weight": "model-00005-of-00007.safetensors", "model.transformer.blocks.15.ff_out.weight": "model-00005-of-00007.safetensors", "model.transformer.blocks.15.ff_proj.weight": "model-00005-of-00007.safetensors", "model.transformer.blocks.16.att_proj.weight": "model-00005-of-00007.safetensors", "model.transformer.blocks.16.attn_out.weight": "model-00005-of-00007.safetensors", "model.transformer.blocks.16.experts.0.ff_out.weight": "model-00005-of-00007.safetensors", "model.transformer.blocks.16.experts.0.ff_proj.weight": "model-00005-of-00007.safetensors", "model.transformer.blocks.16.experts.1.ff_out.weight": "model-00005-of-00007.safetensors", "model.transformer.blocks.16.experts.1.ff_proj.weight": "model-00005-of-00007.safetensors", "model.transformer.blocks.16.experts.2.ff_out.weight": "model-00005-of-00007.safetensors", "model.transformer.blocks.16.experts.2.ff_proj.weight": "model-00005-of-00007.safetensors", "model.transformer.blocks.16.experts.3.ff_out.weight": "model-00005-of-00007.safetensors", "model.transformer.blocks.16.experts.3.ff_proj.weight": "model-00005-of-00007.safetensors", "model.transformer.blocks.16.gate.wg.weight": "model-00005-of-00007.safetensors", "model.transformer.blocks.17.att_proj.weight": "model-00005-of-00007.safetensors", "model.transformer.blocks.17.attn_out.weight": "model-00005-of-00007.safetensors", "model.transformer.blocks.17.ff_out.weight": "model-00005-of-00007.safetensors", "model.transformer.blocks.17.ff_proj.weight": "model-00005-of-00007.safetensors", "model.transformer.blocks.18.att_proj.weight": "model-00005-of-00007.safetensors", "model.transformer.blocks.18.attn_out.weight": "model-00005-of-00007.safetensors", "model.transformer.blocks.18.experts.0.ff_out.weight": "model-00006-of-00007.safetensors", "model.transformer.blocks.18.experts.0.ff_proj.weight": "model-00005-of-00007.safetensors", "model.transformer.blocks.18.experts.1.ff_out.weight": "model-00006-of-00007.safetensors", "model.transformer.blocks.18.experts.1.ff_proj.weight": "model-00006-of-00007.safetensors", "model.transformer.blocks.18.experts.2.ff_out.weight": "model-00006-of-00007.safetensors", "model.transformer.blocks.18.experts.2.ff_proj.weight": "model-00006-of-00007.safetensors", "model.transformer.blocks.18.experts.3.ff_out.weight": "model-00006-of-00007.safetensors", "model.transformer.blocks.18.experts.3.ff_proj.weight": "model-00006-of-00007.safetensors", "model.transformer.blocks.18.gate.wg.weight": "model-00005-of-00007.safetensors", "model.transformer.blocks.19.att_proj.weight": "model-00006-of-00007.safetensors", "model.transformer.blocks.19.attn_out.weight": "model-00006-of-00007.safetensors", "model.transformer.blocks.19.ff_out.weight": "model-00006-of-00007.safetensors", "model.transformer.blocks.19.ff_proj.weight": "model-00006-of-00007.safetensors", "model.transformer.blocks.2.att_proj.weight": "model-00001-of-00007.safetensors", "model.transformer.blocks.2.attn_out.weight": "model-00001-of-00007.safetensors", "model.transformer.blocks.2.experts.0.ff_out.weight": "model-00001-of-00007.safetensors", "model.transformer.blocks.2.experts.0.ff_proj.weight": "model-00001-of-00007.safetensors", "model.transformer.blocks.2.experts.1.ff_out.weight": "model-00001-of-00007.safetensors", "model.transformer.blocks.2.experts.1.ff_proj.weight": "model-00001-of-00007.safetensors", "model.transformer.blocks.2.experts.2.ff_out.weight": "model-00002-of-00007.safetensors", "model.transformer.blocks.2.experts.2.ff_proj.weight": "model-00001-of-00007.safetensors", "model.transformer.blocks.2.experts.3.ff_out.weight": "model-00002-of-00007.safetensors", "model.transformer.blocks.2.experts.3.ff_proj.weight": "model-00002-of-00007.safetensors", "model.transformer.blocks.2.gate.wg.weight": "model-00001-of-00007.safetensors", "model.transformer.blocks.20.att_proj.weight": "model-00006-of-00007.safetensors", "model.transformer.blocks.20.attn_out.weight": "model-00006-of-00007.safetensors", "model.transformer.blocks.20.experts.0.ff_out.weight": "model-00006-of-00007.safetensors", "model.transformer.blocks.20.experts.0.ff_proj.weight": "model-00006-of-00007.safetensors", "model.transformer.blocks.20.experts.1.ff_out.weight": "model-00006-of-00007.safetensors", "model.transformer.blocks.20.experts.1.ff_proj.weight": "model-00006-of-00007.safetensors", "model.transformer.blocks.20.experts.2.ff_out.weight": "model-00006-of-00007.safetensors", "model.transformer.blocks.20.experts.2.ff_proj.weight": "model-00006-of-00007.safetensors", "model.transformer.blocks.20.experts.3.ff_out.weight": "model-00006-of-00007.safetensors", "model.transformer.blocks.20.experts.3.ff_proj.weight": "model-00006-of-00007.safetensors", "model.transformer.blocks.20.gate.wg.weight": "model-00006-of-00007.safetensors", "model.transformer.blocks.21.att_proj.weight": "model-00006-of-00007.safetensors", "model.transformer.blocks.21.attn_out.weight": "model-00006-of-00007.safetensors", "model.transformer.blocks.21.ff_out.weight": "model-00006-of-00007.safetensors", "model.transformer.blocks.21.ff_proj.weight": "model-00006-of-00007.safetensors", "model.transformer.blocks.3.att_proj.weight": "model-00002-of-00007.safetensors", "model.transformer.blocks.3.attn_out.weight": "model-00002-of-00007.safetensors", "model.transformer.blocks.3.ff_out.weight": "model-00002-of-00007.safetensors", "model.transformer.blocks.3.ff_proj.weight": "model-00002-of-00007.safetensors", "model.transformer.blocks.4.att_proj.weight": "model-00002-of-00007.safetensors", "model.transformer.blocks.4.attn_out.weight": "model-00002-of-00007.safetensors", "model.transformer.blocks.4.experts.0.ff_out.weight": "model-00002-of-00007.safetensors", "model.transformer.blocks.4.experts.0.ff_proj.weight": "model-00002-of-00007.safetensors", "model.transformer.blocks.4.experts.1.ff_out.weight": "model-00002-of-00007.safetensors", "model.transformer.blocks.4.experts.1.ff_proj.weight": "model-00002-of-00007.safetensors", "model.transformer.blocks.4.experts.2.ff_out.weight": "model-00002-of-00007.safetensors", "model.transformer.blocks.4.experts.2.ff_proj.weight": "model-00002-of-00007.safetensors", "model.transformer.blocks.4.experts.3.ff_out.weight": "model-00002-of-00007.safetensors", "model.transformer.blocks.4.experts.3.ff_proj.weight": "model-00002-of-00007.safetensors", "model.transformer.blocks.4.gate.wg.weight": "model-00002-of-00007.safetensors", "model.transformer.blocks.5.att_proj.weight": "model-00002-of-00007.safetensors", "model.transformer.blocks.5.attn_out.weight": "model-00002-of-00007.safetensors", "model.transformer.blocks.5.ff_out.weight": "model-00002-of-00007.safetensors", "model.transformer.blocks.5.ff_proj.weight": "model-00002-of-00007.safetensors", "model.transformer.blocks.6.att_proj.weight": "model-00002-of-00007.safetensors", "model.transformer.blocks.6.attn_out.weight": "model-00002-of-00007.safetensors", "model.transformer.blocks.6.experts.0.ff_out.weight": "model-00002-of-00007.safetensors", "model.transformer.blocks.6.experts.0.ff_proj.weight": "model-00002-of-00007.safetensors", "model.transformer.blocks.6.experts.1.ff_out.weight": "model-00002-of-00007.safetensors", "model.transformer.blocks.6.experts.1.ff_proj.weight": "model-00002-of-00007.safetensors", "model.transformer.blocks.6.experts.2.ff_out.weight": "model-00003-of-00007.safetensors", "model.transformer.blocks.6.experts.2.ff_proj.weight": "model-00003-of-00007.safetensors", "model.transformer.blocks.6.experts.3.ff_out.weight": "model-00003-of-00007.safetensors", "model.transformer.blocks.6.experts.3.ff_proj.weight": "model-00003-of-00007.safetensors", "model.transformer.blocks.6.gate.wg.weight": "model-00002-of-00007.safetensors", "model.transformer.blocks.7.att_proj.weight": "model-00003-of-00007.safetensors", "model.transformer.blocks.7.attn_out.weight": "model-00003-of-00007.safetensors", "model.transformer.blocks.7.ff_out.weight": "model-00003-of-00007.safetensors", "model.transformer.blocks.7.ff_proj.weight": "model-00003-of-00007.safetensors", "model.transformer.blocks.8.att_proj.weight": "model-00003-of-00007.safetensors", "model.transformer.blocks.8.attn_out.weight": "model-00003-of-00007.safetensors", "model.transformer.blocks.8.experts.0.ff_out.weight": "model-00003-of-00007.safetensors", "model.transformer.blocks.8.experts.0.ff_proj.weight": "model-00003-of-00007.safetensors", "model.transformer.blocks.8.experts.1.ff_out.weight": "model-00003-of-00007.safetensors", "model.transformer.blocks.8.experts.1.ff_proj.weight": "model-00003-of-00007.safetensors", "model.transformer.blocks.8.experts.2.ff_out.weight": "model-00003-of-00007.safetensors", "model.transformer.blocks.8.experts.2.ff_proj.weight": "model-00003-of-00007.safetensors", "model.transformer.blocks.8.experts.3.ff_out.weight": "model-00003-of-00007.safetensors", "model.transformer.blocks.8.experts.3.ff_proj.weight": "model-00003-of-00007.safetensors", "model.transformer.blocks.8.gate.wg.weight": "model-00003-of-00007.safetensors", "model.transformer.blocks.9.att_proj.weight": "model-00003-of-00007.safetensors", "model.transformer.blocks.9.attn_out.weight": "model-00003-of-00007.safetensors", "model.transformer.blocks.9.ff_out.weight": "model-00003-of-00007.safetensors", "model.transformer.blocks.9.ff_proj.weight": "model-00003-of-00007.safetensors", "model.transformer.ff_out.weight": "model-00007-of-00007.safetensors", "model.transformer.wte.weight": "model-00001-of-00007.safetensors" } }