ColossalAI/examples/tutorial/opt/inference/script/process-opt-175b/flat-meta.json

{"flat_param_0": {"names": ["decoder.embed_tokens.weight", "decoder.embed_positions.weight", "decoder.layer_norm.weight", "decoder.layer_norm.bias"], "shapes": [[6284, 12288], [2050, 12288], [12288], [12288]], "numels": [77217792, 25190400, 12288, 12288]}, "decoder.layers.0.flat_param_0": {"names": ["decoder.layers.0.self_attn.qkv_proj.weight", "decoder.layers.0.self_attn.qkv_proj.bias", "decoder.layers.0.self_attn.out_proj.weight", "decoder.layers.0.self_attn.out_proj.bias", "decoder.layers.0.self_attn_layer_norm.weight", "decoder.layers.0.self_attn_layer_norm.bias", "decoder.layers.0.fc1.weight", "decoder.layers.0.fc1.bias", "decoder.layers.0.fc2.weight", "decoder.layers.0.fc2.bias", "decoder.layers.0.final_layer_norm.weight", "decoder.layers.0.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.1.flat_param_0": {"names": ["decoder.layers.1.self_attn.qkv_proj.weight", "decoder.layers.1.self_attn.qkv_proj.bias", "decoder.layers.1.self_attn.out_proj.weight", "decoder.layers.1.self_attn.out_proj.bias", "decoder.layers.1.self_attn_layer_norm.weight", "decoder.layers.1.self_attn_layer_norm.bias", "decoder.layers.1.fc1.weight", "decoder.layers.1.fc1.bias", "decoder.layers.1.fc2.weight", "decoder.layers.1.fc2.bias", "decoder.layers.1.final_layer_norm.weight", "decoder.layers.1.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.2.flat_param_0": {"names": ["decoder.layers.2.self_attn.qkv_proj.weight", "decoder.layers.2.self_attn.qkv_proj.bias", "decoder.layers.2.self_attn.out_proj.weight", "decoder.layers.2.self_attn.out_proj.bias", "decoder.layers.2.self_attn_layer_norm.weight", "decoder.layers.2.self_attn_layer_norm.bias", "decoder.layers.2.fc1.weight", "decoder.layers.2.fc1.bias", "decoder.layers.2.fc2.weight", "decoder.layers.2.fc2.bias", "decoder.layers.2.final_layer_norm.weight", "decoder.layers.2.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.3.flat_param_0": {"names": ["decoder.layers.3.self_attn.qkv_proj.weight", "decoder.layers.3.self_attn.qkv_proj.bias", "decoder.layers.3.self_attn.out_proj.weight", "decoder.layers.3.self_attn.out_proj.bias", "decoder.layers.3.self_attn_layer_norm.weight", "decoder.layers.3.self_attn_layer_norm.bias", "decoder.layers.3.fc1.weight", "decoder.layers.3.fc1.bias", "decoder.layers.3.fc2.weight", "decoder.layers.3.fc2.bias", "decoder.layers.3.final_layer_norm.weight", "decoder.layers.3.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.4.flat_param_0": {"names": ["decoder.layers.4.self_attn.qkv_proj.weight", "decoder.layers.4.self_attn.qkv_proj.bias", "decoder.layers.4.self_attn.out_proj.weight", "decoder.layers.4.self_attn.out_proj.bias", "decoder.layers.4.self_attn_layer_norm.weight", "decoder.layers.4.self_attn_layer_norm.bias", "decoder.layers.4.fc1.weight", "decoder.layers.4.fc1.bias", "decoder.layers.4.fc2.weight", "decoder.layers.4.fc2.bias", "decoder.layers.4.final_layer_norm.weight", "decoder.layers.4.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.5.flat_param_0": {"names": ["decoder.layers.5.self_attn.qkv_proj.weight", "decoder.layers.5.self_attn.qkv_proj.bias", "decoder.layers.5.self_attn.out_proj.weight", "decoder.layers.5.self_attn.out_proj.bias", "decoder.layers.5.self_attn_layer_norm.weight", "decoder.layers.5.self_attn_layer_norm.bias", "decoder.layers.5.fc1.weight", "decoder.layers.5.fc1.bias", "decoder.layers.5.fc2.weight", "decoder.layers.5.fc2.bias", "decoder.layers.5.final_layer_norm.weight", "decoder.layers.5.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.6.flat_param_0": {"names": ["decoder.layers.6.self_attn.qkv_proj.weight", "decoder.layers.6.self_attn.qkv_proj.bias", "decoder.layers.6.self_attn.out_proj.weight", "decoder.layers.6.self_attn.out_proj.bias", "decoder.layers.6.self_attn_layer_norm.weight", "decoder.layers.6.self_attn_layer_norm.bias", "decoder.layers.6.fc1.weight", "decoder.layers.6.fc1.bias", "decoder.layers.6.fc2.weight", "decoder.layers.6.fc2.bias", "decoder.layers.6.final_layer_norm.weight", "decoder.layers.6.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.7.flat_param_0": {"names": ["decoder.layers.7.self_attn.qkv_proj.weight", "decoder.layers.7.self_attn.qkv_proj.bias", "decoder.layers.7.self_attn.out_proj.weight", "decoder.layers.7.self_attn.out_proj.bias", "decoder.layers.7.self_attn_layer_norm.weight", "decoder.layers.7.self_attn_layer_norm.bias", "decoder.layers.7.fc1.weight", "decoder.layers.7.fc1.bias", "decoder.layers.7.fc2.weight", "decoder.layers.7.fc2.bias", "decoder.layers.7.final_layer_norm.weight", "decoder.layers.7.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.8.flat_param_0": {"names": ["decoder.layers.8.self_attn.qkv_proj.weight", "decoder.layers.8.self_attn.qkv_proj.bias", "decoder.layers.8.self_attn.out_proj.weight", "decoder.layers.8.self_attn.out_proj.bias", "decoder.layers.8.self_attn_layer_norm.weight", "decoder.layers.8.self_attn_layer_norm.bias", "decoder.layers.8.fc1.weight", "decoder.layers.8.fc1.bias", "decoder.layers.8.fc2.weight", "decoder.layers.8.fc2.bias", "decoder.layers.8.final_layer_norm.weight", "decoder.layers.8.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.9.flat_param_0": {"names": ["decoder.layers.9.self_attn.qkv_proj.weight", "decoder.layers.9.self_attn.qkv_proj.bias", "decoder.layers.9.self_attn.out_proj.weight", "decoder.layers.9.self_attn.out_proj.bias", "decoder.layers.9.self_attn_layer_norm.weight", "decoder.layers.9.self_attn_layer_norm.bias", "decoder.layers.9.fc1.weight", "decoder.layers.9.fc1.bias", "decoder.layers.9.fc2.weight", "decoder.layers.9.fc2.bias", "decoder.layers.9.final_layer_norm.weight", "decoder.layers.9.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.10.flat_param_0": {"names": ["decoder.layers.10.self_attn.qkv_proj.weight", "decoder.layers.10.self_attn.qkv_proj.bias", "decoder.layers.10.self_attn.out_proj.weight", "decoder.layers.10.self_attn.out_proj.bias", "decoder.layers.10.self_attn_layer_norm.weight", "decoder.layers.10.self_attn_layer_norm.bias", "decoder.layers.10.fc1.weight", "decoder.layers.10.fc1.bias", "decoder.layers.10.fc2.weight", "decoder.layers.10.fc2.bias", "decoder.layers.10.final_layer_norm.weight", "decoder.layers.10.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.11.flat_param_0": {"names": ["decoder.layers.11.self_attn.qkv_proj.weight", "decoder.layers.11.self_attn.qkv_proj.bias", "decoder.layers.11.self_attn.out_proj.weight", "decoder.layers.11.self_attn.out_proj.bias", "decoder.layers.11.self_attn_layer_norm.weight", "decoder.layers.11.self_attn_layer_norm.bias", "decoder.layers.11.fc1.weight", "decoder.layers.11.fc1.bias", "decoder.layers.11.fc2.weight", "decoder.layers.11.fc2.bias", "decoder.layers.11.final_layer_norm.weight", "decoder.layers.11.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.12.flat_param_0": {"names": ["decoder.layers.12.self_attn.qkv_proj.weight", "decoder.layers.12.self_attn.qkv_proj.bias", "decoder.layers.12.self_attn.out_proj.weight", "decoder.layers.12.self_attn.out_proj.bias", "decoder.layers.12.self_attn_layer_norm.weight", "decoder.layers.12.self_attn_layer_norm.bias", "decoder.layers.12.fc1.weight", "decoder.layers.12.fc1.bias", "decoder.layers.12.fc2.weight", "decoder.layers.12.fc2.bias", "decoder.layers.12.final_layer_norm.weight", "decoder.layers.12.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.13.flat_param_0": {"names": ["decoder.layers.13.self_attn.qkv_proj.weight", "decoder.layers.13.self_attn.qkv_proj.bias", "decoder.layers.13.self_attn.out_proj.weight", "decoder.layers.13.self_attn.out_proj.bias", "decoder.layers.13.self_attn_layer_norm.weight", "decoder.layers.13.self_attn_layer_norm.bias", "decoder.layers.13.fc1.weight", "decoder.layers.13.fc1.bias", "decoder.layers.13.fc2.weight", "decoder.layers.13.fc2.bias", "decoder.layers.13.final_layer_norm.weight", "decoder.layers.13.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.14.flat_param_0": {"names": ["decoder.layers.14.self_attn.qkv_proj.weight", "decoder.layers.14.self_attn.qkv_proj.bias", "decoder.layers.14.self_attn.out_proj.weight", "decoder.layers.14.self_attn.out_proj.bias", "decoder.layers.14.self_attn_layer_norm.weight", "decoder.layers.14.self_attn_layer_norm.bias", "decoder.layers.14.fc1.weight", "decoder.layers.14.fc1.bias", "decoder.layers.14.fc2.weight", "decoder.layers.14.fc2.bias", "decoder.layers.14.final_layer_norm.weight", "decoder.layers.14.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.15.flat_param_0": {"names": ["decoder.layers.15.self_attn.qkv_proj.weight", "decoder.layers.15.self_attn.qkv_proj.bias", "decoder.layers.15.self_attn.out_proj.weight", "decoder.layers.15.self_attn.out_proj.bias", "decoder.layers.15.self_attn_layer_norm.weight", "decoder.layers.15.self_attn_layer_norm.bias", "decoder.layers.15.fc1.weight", "decoder.layers.15.fc1.bias", "decoder.layers.15.fc2.weight", "decoder.layers.15.fc2.bias", "decoder.layers.15.final_layer_norm.weight", "decoder.layers.15.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.16.flat_param_0": {"names": ["decoder.layers.16.self_attn.qkv_proj.weight", "decoder.layers.16.self_attn.qkv_proj.bias", "decoder.layers.16.self_attn.out_proj.weight", "decoder.layers.16.self_attn.out_proj.bias", "decoder.layers.16.self_attn_layer_norm.weight", "decoder.layers.16.self_attn_layer_norm.bias", "decoder.layers.16.fc1.weight", "decoder.layers.16.fc1.bias", "decoder.layers.16.fc2.weight", "decoder.layers.16.fc2.bias", "decoder.layers.16.final_layer_norm.weight", "decoder.layers.16.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.17.flat_param_0": {"names": ["decoder.layers.17.self_attn.qkv_proj.weight", "decoder.layers.17.self_attn.qkv_proj.bias", "decoder.layers.17.self_attn.out_proj.weight", "decoder.layers.17.self_attn.out_proj.bias", "decoder.layers.17.self_attn_layer_norm.weight", "decoder.layers.17.self_attn_layer_norm.bias", "decoder.layers.17.fc1.weight", "decoder.layers.17.fc1.bias", "decoder.layers.17.fc2.weight", "decoder.layers.17.fc2.bias", "decoder.layers.17.final_layer_norm.weight", "decoder.layers.17.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.18.flat_param_0": {"names": ["decoder.layers.18.self_attn.qkv_proj.weight", "decoder.layers.18.self_attn.qkv_proj.bias", "decoder.layers.18.self_attn.out_proj.weight", "decoder.layers.18.self_attn.out_proj.bias", "decoder.layers.18.self_attn_layer_norm.weight", "decoder.layers.18.self_attn_layer_norm.bias", "decoder.layers.18.fc1.weight", "decoder.layers.18.fc1.bias", "decoder.layers.18.fc2.weight", "decoder.layers.18.fc2.bias", "decoder.layers.18.final_layer_norm.weight", "decoder.layers.18.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.19.flat_param_0": {"names": ["decoder.layers.19.self_attn.qkv_proj.weight", "decoder.layers.19.self_attn.qkv_proj.bias", "decoder.layers.19.self_attn.out_proj.weight", "decoder.layers.19.self_attn.out_proj.bias", "decoder.layers.19.self_attn_layer_norm.weight", "decoder.layers.19.self_attn_layer_norm.bias", "decoder.layers.19.fc1.weight", "decoder.layers.19.fc1.bias", "decoder.layers.19.fc2.weight", "decoder.layers.19.fc2.bias", "decoder.layers.19.final_layer_norm.weight", "decoder.layers.19.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.20.flat_param_0": {"names": ["decoder.layers.20.self_attn.qkv_proj.weight", "decoder.layers.20.self_attn.qkv_proj.bias", "decoder.layers.20.self_attn.out_proj.weight", "decoder.layers.20.self_attn.out_proj.bias", "decoder.layers.20.self_attn_layer_norm.weight", "decoder.layers.20.self_attn_layer_norm.bias", "decoder.layers.20.fc1.weight", "decoder.layers.20.fc1.bias", "decoder.layers.20.fc2.weight", "decoder.layers.20.fc2.bias", "decoder.layers.20.final_layer_norm.weight", "decoder.layers.20.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.21.flat_param_0": {"names": ["decoder.layers.21.self_attn.qkv_proj.weight", "decoder.layers.21.self_attn.qkv_proj.bias", "decoder.layers.21.self_attn.out_proj.weight", "decoder.layers.21.self_attn.out_proj.bias", "decoder.layers.21.self_attn_layer_norm.weight", "decoder.layers.21.self_attn_layer_norm.bias", "decoder.layers.21.fc1.weight", "decoder.layers.21.fc1.bias", "decoder.layers.21.fc2.weight", "decoder.layers.21.fc2.bias", "decoder.layers.21.final_layer_norm.weight", "decoder.layers.21.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.22.flat_param_0": {"names": ["decoder.layers.22.self_attn.qkv_proj.weight", "decoder.layers.22.self_attn.qkv_proj.bias", "decoder.layers.22.self_attn.out_proj.weight", "decoder.layers.22.self_attn.out_proj.bias", "decoder.layers.22.self_attn_layer_norm.weight", "decoder.layers.22.self_attn_layer_norm.bias", "decoder.layers.22.fc1.weight", "decoder.layers.22.fc1.bias", "decoder.layers.22.fc2.weight", "decoder.layers.22.fc2.bias", "decoder.layers.22.final_layer_norm.weight", "decoder.layers.22.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.23.flat_param_0": {"names": ["decoder.layers.23.self_attn.qkv_proj.weight", "decoder.layers.23.self_attn.qkv_proj.bias", "decoder.layers.23.self_attn.out_proj.weight", "decoder.layers.23.self_attn.out_proj.bias", "decoder.layers.23.self_attn_layer_norm.weight", "decoder.layers.23.self_attn_layer_norm.bias", "decoder.layers.23.fc1.weight", "decoder.layers.23.fc1.bias", "decoder.layers.23.fc2.weight", "decoder.layers.23.fc2.bias", "decoder.layers.23.final_layer_norm.weight", "decoder.layers.23.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.24.flat_param_0": {"names": ["decoder.layers.24.self_attn.qkv_proj.weight", "decoder.layers.24.self_attn.qkv_proj.bias", "decoder.layers.24.self_attn.out_proj.weight", "decoder.layers.24.self_attn.out_proj.bias", "decoder.layers.24.self_attn_layer_norm.weight", "decoder.layers.24.self_attn_layer_norm.bias", "decoder.layers.24.fc1.weight", "decoder.layers.24.fc1.bias", "decoder.layers.24.fc2.weight", "decoder.layers.24.fc2.bias", "decoder.layers.24.final_layer_norm.weight", "decoder.layers.24.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.25.flat_param_0": {"names": ["decoder.layers.25.self_attn.qkv_proj.weight", "decoder.layers.25.self_attn.qkv_proj.bias", "decoder.layers.25.self_attn.out_proj.weight", "decoder.layers.25.self_attn.out_proj.bias", "decoder.layers.25.self_attn_layer_norm.weight", "decoder.layers.25.self_attn_layer_norm.bias", "decoder.layers.25.fc1.weight", "decoder.layers.25.fc1.bias", "decoder.layers.25.fc2.weight", "decoder.layers.25.fc2.bias", "decoder.layers.25.final_layer_norm.weight", "decoder.layers.25.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.26.flat_param_0": {"names": ["decoder.layers.26.self_attn.qkv_proj.weight", "decoder.layers.26.self_attn.qkv_proj.bias", "decoder.layers.26.self_attn.out_proj.weight", "decoder.layers.26.self_attn.out_proj.bias", "decoder.layers.26.self_attn_layer_norm.weight", "decoder.layers.26.self_attn_layer_norm.bias", "decoder.layers.26.fc1.weight", "decoder.layers.26.fc1.bias", "decoder.layers.26.fc2.weight", "decoder.layers.26.fc2.bias", "decoder.layers.26.final_layer_norm.weight", "decoder.layers.26.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.27.flat_param_0": {"names": ["decoder.layers.27.self_attn.qkv_proj.weight", "decoder.layers.27.self_attn.qkv_proj.bias", "decoder.layers.27.self_attn.out_proj.weight", "decoder.layers.27.self_attn.out_proj.bias", "decoder.layers.27.self_attn_layer_norm.weight", "decoder.layers.27.self_attn_layer_norm.bias", "decoder.layers.27.fc1.weight", "decoder.layers.27.fc1.bias", "decoder.layers.27.fc2.weight", "decoder.layers.27.fc2.bias", "decoder.layers.27.final_layer_norm.weight", "decoder.layers.27.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.28.flat_param_0": {"names": ["decoder.layers.28.self_attn.qkv_proj.weight", "decoder.layers.28.self_attn.qkv_proj.bias", "decoder.layers.28.self_attn.out_proj.weight", "decoder.layers.28.self_attn.out_proj.bias", "decoder.layers.28.self_attn_layer_norm.weight", "decoder.layers.28.self_attn_layer_norm.bias", "decoder.layers.28.fc1.weight", "decoder.layers.28.fc1.bias", "decoder.layers.28.fc2.weight", "decoder.layers.28.fc2.bias", "decoder.layers.28.final_layer_norm.weight", "decoder.layers.28.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.29.flat_param_0": {"names": ["decoder.layers.29.self_attn.qkv_proj.weight", "decoder.layers.29.self_attn.qkv_proj.bias", "decoder.layers.29.self_attn.out_proj.weight", "decoder.layers.29.self_attn.out_proj.bias", "decoder.layers.29.self_attn_layer_norm.weight", "decoder.layers.29.self_attn_layer_norm.bias", "decoder.layers.29.fc1.weight", "decoder.layers.29.fc1.bias", "decoder.layers.29.fc2.weight", "decoder.layers.29.fc2.bias", "decoder.layers.29.final_layer_norm.weight", "decoder.layers.29.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.30.flat_param_0": {"names": ["decoder.layers.30.self_attn.qkv_proj.weight", "decoder.layers.30.self_attn.qkv_proj.bias", "decoder.layers.30.self_attn.out_proj.weight", "decoder.layers.30.self_attn.out_proj.bias", "decoder.layers.30.self_attn_layer_norm.weight", "decoder.layers.30.self_attn_layer_norm.bias", "decoder.layers.30.fc1.weight", "decoder.layers.30.fc1.bias", "decoder.layers.30.fc2.weight", "decoder.layers.30.fc2.bias", "decoder.layers.30.final_layer_norm.weight", "decoder.layers.30.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.31.flat_param_0": {"names": ["decoder.layers.31.self_attn.qkv_proj.weight", "decoder.layers.31.self_attn.qkv_proj.bias", "decoder.layers.31.self_attn.out_proj.weight", "decoder.layers.31.self_attn.out_proj.bias", "decoder.layers.31.self_attn_layer_norm.weight", "decoder.layers.31.self_attn_layer_norm.bias", "decoder.layers.31.fc1.weight", "decoder.layers.31.fc1.bias", "decoder.layers.31.fc2.weight", "decoder.layers.31.fc2.bias", "decoder.layers.31.final_layer_norm.weight", "decoder.layers.31.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.32.flat_param_0": {"names": ["decoder.layers.32.self_attn.qkv_proj.weight", "decoder.layers.32.self_attn.qkv_proj.bias", "decoder.layers.32.self_attn.out_proj.weight", "decoder.layers.32.self_attn.out_proj.bias", "decoder.layers.32.self_attn_layer_norm.weight", "decoder.layers.32.self_attn_layer_norm.bias", "decoder.layers.32.fc1.weight", "decoder.layers.32.fc1.bias", "decoder.layers.32.fc2.weight", "decoder.layers.32.fc2.bias", "decoder.layers.32.final_layer_norm.weight", "decoder.layers.32.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.33.flat_param_0": {"names": ["decoder.layers.33.self_attn.qkv_proj.weight", "decoder.layers.33.self_attn.qkv_proj.bias", "decoder.layers.33.self_attn.out_proj.weight", "decoder.layers.33.self_attn.out_proj.bias", "decoder.layers.33.self_attn_layer_norm.weight", "decoder.layers.33.self_attn_layer_norm.bias", "decoder.layers.33.fc1.weight", "decoder.layers.33.fc1.bias", "decoder.layers.33.fc2.weight", "decoder.layers.33.fc2.bias", "decoder.layers.33.final_layer_norm.weight", "decoder.layers.33.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.34.flat_param_0": {"names": ["decoder.layers.34.self_attn.qkv_proj.weight", "decoder.layers.34.self_attn.qkv_proj.bias", "decoder.layers.34.self_attn.out_proj.weight", "decoder.layers.34.self_attn.out_proj.bias", "decoder.layers.34.self_attn_layer_norm.weight", "decoder.layers.34.self_attn_layer_norm.bias", "decoder.layers.34.fc1.weight", "decoder.layers.34.fc1.bias", "decoder.layers.34.fc2.weight", "decoder.layers.34.fc2.bias", "decoder.layers.34.final_layer_norm.weight", "decoder.layers.34.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.35.flat_param_0": {"names": ["decoder.layers.35.self_attn.qkv_proj.weight", "decoder.layers.35.self_attn.qkv_proj.bias", "decoder.layers.35.self_attn.out_proj.weight", "decoder.layers.35.self_attn.out_proj.bias", "decoder.layers.35.self_attn_layer_norm.weight", "decoder.layers.35.self_attn_layer_norm.bias", "decoder.layers.35.fc1.weight", "decoder.layers.35.fc1.bias", "decoder.layers.35.fc2.weight", "decoder.layers.35.fc2.bias", "decoder.layers.35.final_layer_norm.weight", "decoder.layers.35.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.36.flat_param_0": {"names": ["decoder.layers.36.self_attn.qkv_proj.weight", "decoder.layers.36.self_attn.qkv_proj.bias", "decoder.layers.36.self_attn.out_proj.weight", "decoder.layers.36.self_attn.out_proj.bias", "decoder.layers.36.self_attn_layer_norm.weight", "decoder.layers.36.self_attn_layer_norm.bias", "decoder.layers.36.fc1.weight", "decoder.layers.36.fc1.bias", "decoder.layers.36.fc2.weight", "decoder.layers.36.fc2.bias", "decoder.layers.36.final_layer_norm.weight", "decoder.layers.36.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.37.flat_param_0": {"names": ["decoder.layers.37.self_attn.qkv_proj.weight", "decoder.layers.37.self_attn.qkv_proj.bias", "decoder.layers.37.self_attn.out_proj.weight", "decoder.layers.37.self_attn.out_proj.bias", "decoder.layers.37.self_attn_layer_norm.weight", "decoder.layers.37.self_attn_layer_norm.bias", "decoder.layers.37.fc1.weight", "decoder.layers.37.fc1.bias", "decoder.layers.37.fc2.weight", "decoder.layers.37.fc2.bias", "decoder.layers.37.final_layer_norm.weight", "decoder.layers.37.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.38.flat_param_0": {"names": ["decoder.layers.38.self_attn.qkv_proj.weight", "decoder.layers.38.self_attn.qkv_proj.bias", "decoder.layers.38.self_attn.out_proj.weight", "decoder.layers.38.self_attn.out_proj.bias", "decoder.layers.38.self_attn_layer_norm.weight", "decoder.layers.38.self_attn_layer_norm.bias", "decoder.layers.38.fc1.weight", "decoder.layers.38.fc1.bias", "decoder.layers.38.fc2.weight", "decoder.layers.38.fc2.bias", "decoder.layers.38.final_layer_norm.weight", "decoder.layers.38.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.39.flat_param_0": {"names": ["decoder.layers.39.self_attn.qkv_proj.weight", "decoder.layers.39.self_attn.qkv_proj.bias", "decoder.layers.39.self_attn.out_proj.weight", "decoder.layers.39.self_attn.out_proj.bias", "decoder.layers.39.self_attn_layer_norm.weight", "decoder.layers.39.self_attn_layer_norm.bias", "decoder.layers.39.fc1.weight", "decoder.layers.39.fc1.bias", "decoder.layers.39.fc2.weight", "decoder.layers.39.fc2.bias", "decoder.layers.39.final_layer_norm.weight", "decoder.layers.39.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.40.flat_param_0": {"names": ["decoder.layers.40.self_attn.qkv_proj.weight", "decoder.layers.40.self_attn.qkv_proj.bias", "decoder.layers.40.self_attn.out_proj.weight", "decoder.layers.40.self_attn.out_proj.bias", "decoder.layers.40.self_attn_layer_norm.weight", "decoder.layers.40.self_attn_layer_norm.bias", "decoder.layers.40.fc1.weight", "decoder.layers.40.fc1.bias", "decoder.layers.40.fc2.weight", "decoder.layers.40.fc2.bias", "decoder.layers.40.final_layer_norm.weight", "decoder.layers.40.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.41.flat_param_0": {"names": ["decoder.layers.41.self_attn.qkv_proj.weight", "decoder.layers.41.self_attn.qkv_proj.bias", "decoder.layers.41.self_attn.out_proj.weight", "decoder.layers.41.self_attn.out_proj.bias", "decoder.layers.41.self_attn_layer_norm.weight", "decoder.layers.41.self_attn_layer_norm.bias", "decoder.layers.41.fc1.weight", "decoder.layers.41.fc1.bias", "decoder.layers.41.fc2.weight", "decoder.layers.41.fc2.bias", "decoder.layers.41.final_layer_norm.weight", "decoder.layers.41.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.42.flat_param_0": {"names": ["decoder.layers.42.self_attn.qkv_proj.weight", "decoder.layers.42.self_attn.qkv_proj.bias", "decoder.layers.42.self_attn.out_proj.weight", "decoder.layers.42.self_attn.out_proj.bias", "decoder.layers.42.self_attn_layer_norm.weight", "decoder.layers.42.self_attn_layer_norm.bias", "decoder.layers.42.fc1.weight", "decoder.layers.42.fc1.bias", "decoder.layers.42.fc2.weight", "decoder.layers.42.fc2.bias", "decoder.layers.42.final_layer_norm.weight", "decoder.layers.42.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.43.flat_param_0": {"names": ["decoder.layers.43.self_attn.qkv_proj.weight", "decoder.layers.43.self_attn.qkv_proj.bias", "decoder.layers.43.self_attn.out_proj.weight", "decoder.layers.43.self_attn.out_proj.bias", "decoder.layers.43.self_attn_layer_norm.weight", "decoder.layers.43.self_attn_layer_norm.bias", "decoder.layers.43.fc1.weight", "decoder.layers.43.fc1.bias", "decoder.layers.43.fc2.weight", "decoder.layers.43.fc2.bias", "decoder.layers.43.final_layer_norm.weight", "decoder.layers.43.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.44.flat_param_0": {"names": ["decoder.layers.44.self_attn.qkv_proj.weight", "decoder.layers.44.self_attn.qkv_proj.bias", "decoder.layers.44.self_attn.out_proj.weight", "decoder.layers.44.self_attn.out_proj.bias", "decoder.layers.44.self_attn_layer_norm.weight", "decoder.layers.44.self_attn_layer_norm.bias", "decoder.layers.44.fc1.weight", "decoder.layers.44.fc1.bias", "decoder.layers.44.fc2.weight", "decoder.layers.44.fc2.bias", "decoder.layers.44.final_layer_norm.weight", "decoder.layers.44.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.45.flat_param_0": {"names": ["decoder.layers.45.self_attn.qkv_proj.weight", "decoder.layers.45.self_attn.qkv_proj.bias", "decoder.layers.45.self_attn.out_proj.weight", "decoder.layers.45.self_attn.out_proj.bias", "decoder.layers.45.self_attn_layer_norm.weight", "decoder.layers.45.self_attn_layer_norm.bias", "decoder.layers.45.fc1.weight", "decoder.layers.45.fc1.bias", "decoder.layers.45.fc2.weight", "decoder.layers.45.fc2.bias", "decoder.layers.45.final_layer_norm.weight", "decoder.layers.45.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.46.flat_param_0": {"names": ["decoder.layers.46.self_attn.qkv_proj.weight", "decoder.layers.46.self_attn.qkv_proj.bias", "decoder.layers.46.self_attn.out_proj.weight", "decoder.layers.46.self_attn.out_proj.bias", "decoder.layers.46.self_attn_layer_norm.weight", "decoder.layers.46.self_attn_layer_norm.bias", "decoder.layers.46.fc1.weight", "decoder.layers.46.fc1.bias", "decoder.layers.46.fc2.weight", "decoder.layers.46.fc2.bias", "decoder.layers.46.final_layer_norm.weight", "decoder.layers.46.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.47.flat_param_0": {"names": ["decoder.layers.47.self_attn.qkv_proj.weight", "decoder.layers.47.self_attn.qkv_proj.bias", "decoder.layers.47.self_attn.out_proj.weight", "decoder.layers.47.self_attn.out_proj.bias", "decoder.layers.47.self_attn_layer_norm.weight", "decoder.layers.47.self_attn_layer_norm.bias", "decoder.layers.47.fc1.weight", "decoder.layers.47.fc1.bias", "decoder.layers.47.fc2.weight", "decoder.layers.47.fc2.bias", "decoder.layers.47.final_layer_norm.weight", "decoder.layers.47.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.48.flat_param_0": {"names": ["decoder.layers.48.self_attn.qkv_proj.weight", "decoder.layers.48.self_attn.qkv_proj.bias", "decoder.layers.48.self_attn.out_proj.weight", "decoder.layers.48.self_attn.out_proj.bias", "decoder.layers.48.self_attn_layer_norm.weight", "decoder.layers.48.self_attn_layer_norm.bias", "decoder.layers.48.fc1.weight", "decoder.layers.48.fc1.bias", "decoder.layers.48.fc2.weight", "decoder.layers.48.fc2.bias", "decoder.layers.48.final_layer_norm.weight", "decoder.layers.48.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.49.flat_param_0": {"names": ["decoder.layers.49.self_attn.qkv_proj.weight", "decoder.layers.49.self_attn.qkv_proj.bias", "decoder.layers.49.self_attn.out_proj.weight", "decoder.layers.49.self_attn.out_proj.bias", "decoder.layers.49.self_attn_layer_norm.weight", "decoder.layers.49.self_attn_layer_norm.bias", "decoder.layers.49.fc1.weight", "decoder.layers.49.fc1.bias", "decoder.layers.49.fc2.weight", "decoder.layers.49.fc2.bias", "decoder.layers.49.final_layer_norm.weight", "decoder.layers.49.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.50.flat_param_0": {"names": ["decoder.layers.50.self_attn.qkv_proj.weight", "decoder.layers.50.self_attn.qkv_proj.bias", "decoder.layers.50.self_attn.out_proj.weight", "decoder.layers.50.self_attn.out_proj.bias", "decoder.layers.50.self_attn_layer_norm.weight", "decoder.layers.50.self_attn_layer_norm.bias", "decoder.layers.50.fc1.weight", "decoder.layers.50.fc1.bias", "decoder.layers.50.fc2.weight", "decoder.layers.50.fc2.bias", "decoder.layers.50.final_layer_norm.weight", "decoder.layers.50.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.51.flat_param_0": {"names": ["decoder.layers.51.self_attn.qkv_proj.weight", "decoder.layers.51.self_attn.qkv_proj.bias", "decoder.layers.51.self_attn.out_proj.weight", "decoder.layers.51.self_attn.out_proj.bias", "decoder.layers.51.self_attn_layer_norm.weight", "decoder.layers.51.self_attn_layer_norm.bias", "decoder.layers.51.fc1.weight", "decoder.layers.51.fc1.bias", "decoder.layers.51.fc2.weight", "decoder.layers.51.fc2.bias", "decoder.layers.51.final_layer_norm.weight", "decoder.layers.51.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.52.flat_param_0": {"names": ["decoder.layers.52.self_attn.qkv_proj.weight", "decoder.layers.52.self_attn.qkv_proj.bias", "decoder.layers.52.self_attn.out_proj.weight", "decoder.layers.52.self_attn.out_proj.bias", "decoder.layers.52.self_attn_layer_norm.weight", "decoder.layers.52.self_attn_layer_norm.bias", "decoder.layers.52.fc1.weight", "decoder.layers.52.fc1.bias", "decoder.layers.52.fc2.weight", "decoder.layers.52.fc2.bias", "decoder.layers.52.final_layer_norm.weight", "decoder.layers.52.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.53.flat_param_0": {"names": ["decoder.layers.53.self_attn.qkv_proj.weight", "decoder.layers.53.self_attn.qkv_proj.bias", "decoder.layers.53.self_attn.out_proj.weight", "decoder.layers.53.self_attn.out_proj.bias", "decoder.layers.53.self_attn_layer_norm.weight", "decoder.layers.53.self_attn_layer_norm.bias", "decoder.layers.53.fc1.weight", "decoder.layers.53.fc1.bias", "decoder.layers.53.fc2.weight", "decoder.layers.53.fc2.bias", "decoder.layers.53.final_layer_norm.weight", "decoder.layers.53.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.54.flat_param_0": {"names": ["decoder.layers.54.self_attn.qkv_proj.weight", "decoder.layers.54.self_attn.qkv_proj.bias", "decoder.layers.54.self_attn.out_proj.weight", "decoder.layers.54.self_attn.out_proj.bias", "decoder.layers.54.self_attn_layer_norm.weight", "decoder.layers.54.self_attn_layer_norm.bias", "decoder.layers.54.fc1.weight", "decoder.layers.54.fc1.bias", "decoder.layers.54.fc2.weight", "decoder.layers.54.fc2.bias", "decoder.layers.54.final_layer_norm.weight", "decoder.layers.54.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.55.flat_param_0": {"names": ["decoder.layers.55.self_attn.qkv_proj.weight", "decoder.layers.55.self_attn.qkv_proj.bias", "decoder.layers.55.self_attn.out_proj.weight", "decoder.layers.55.self_attn.out_proj.bias", "decoder.layers.55.self_attn_layer_norm.weight", "decoder.layers.55.self_attn_layer_norm.bias", "decoder.layers.55.fc1.weight", "decoder.layers.55.fc1.bias", "decoder.layers.55.fc2.weight", "decoder.layers.55.fc2.bias", "decoder.layers.55.final_layer_norm.weight", "decoder.layers.55.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.56.flat_param_0": {"names": ["decoder.layers.56.self_attn.qkv_proj.weight", "decoder.layers.56.self_attn.qkv_proj.bias", "decoder.layers.56.self_attn.out_proj.weight", "decoder.layers.56.self_attn.out_proj.bias", "decoder.layers.56.self_attn_layer_norm.weight", "decoder.layers.56.self_attn_layer_norm.bias", "decoder.layers.56.fc1.weight", "decoder.layers.56.fc1.bias", "decoder.layers.56.fc2.weight", "decoder.layers.56.fc2.bias", "decoder.layers.56.final_layer_norm.weight", "decoder.layers.56.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.57.flat_param_0": {"names": ["decoder.layers.57.self_attn.qkv_proj.weight", "decoder.layers.57.self_attn.qkv_proj.bias", "decoder.layers.57.self_attn.out_proj.weight", "decoder.layers.57.self_attn.out_proj.bias", "decoder.layers.57.self_attn_layer_norm.weight", "decoder.layers.57.self_attn_layer_norm.bias", "decoder.layers.57.fc1.weight", "decoder.layers.57.fc1.bias", "decoder.layers.57.fc2.weight", "decoder.layers.57.fc2.bias", "decoder.layers.57.final_layer_norm.weight", "decoder.layers.57.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.58.flat_param_0": {"names": ["decoder.layers.58.self_attn.qkv_proj.weight", "decoder.layers.58.self_attn.qkv_proj.bias", "decoder.layers.58.self_attn.out_proj.weight", "decoder.layers.58.self_attn.out_proj.bias", "decoder.layers.58.self_attn_layer_norm.weight", "decoder.layers.58.self_attn_layer_norm.bias", "decoder.layers.58.fc1.weight", "decoder.layers.58.fc1.bias", "decoder.layers.58.fc2.weight", "decoder.layers.58.fc2.bias", "decoder.layers.58.final_layer_norm.weight", "decoder.layers.58.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.59.flat_param_0": {"names": ["decoder.layers.59.self_attn.qkv_proj.weight", "decoder.layers.59.self_attn.qkv_proj.bias", "decoder.layers.59.self_attn.out_proj.weight", "decoder.layers.59.self_attn.out_proj.bias", "decoder.layers.59.self_attn_layer_norm.weight", "decoder.layers.59.self_attn_layer_norm.bias", "decoder.layers.59.fc1.weight", "decoder.layers.59.fc1.bias", "decoder.layers.59.fc2.weight", "decoder.layers.59.fc2.bias", "decoder.layers.59.final_layer_norm.weight", "decoder.layers.59.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.60.flat_param_0": {"names": ["decoder.layers.60.self_attn.qkv_proj.weight", "decoder.layers.60.self_attn.qkv_proj.bias", "decoder.layers.60.self_attn.out_proj.weight", "decoder.layers.60.self_attn.out_proj.bias", "decoder.layers.60.self_attn_layer_norm.weight", "decoder.layers.60.self_attn_layer_norm.bias", "decoder.layers.60.fc1.weight", "decoder.layers.60.fc1.bias", "decoder.layers.60.fc2.weight", "decoder.layers.60.fc2.bias", "decoder.layers.60.final_layer_norm.weight", "decoder.layers.60.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.61.flat_param_0": {"names": ["decoder.layers.61.self_attn.qkv_proj.weight", "decoder.layers.61.self_attn.qkv_proj.bias", "decoder.layers.61.self_attn.out_proj.weight", "decoder.layers.61.self_attn.out_proj.bias", "decoder.layers.61.self_attn_layer_norm.weight", "decoder.layers.61.self_attn_layer_norm.bias", "decoder.layers.61.fc1.weight", "decoder.layers.61.fc1.bias", "decoder.layers.61.fc2.weight", "decoder.layers.61.fc2.bias", "decoder.layers.61.final_layer_norm.weight", "decoder.layers.61.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.62.flat_param_0": {"names": ["decoder.layers.62.self_attn.qkv_proj.weight", "decoder.layers.62.self_attn.qkv_proj.bias", "decoder.layers.62.self_attn.out_proj.weight", "decoder.layers.62.self_attn.out_proj.bias", "decoder.layers.62.self_attn_layer_norm.weight", "decoder.layers.62.self_attn_layer_norm.bias", "decoder.layers.62.fc1.weight", "decoder.layers.62.fc1.bias", "decoder.layers.62.fc2.weight", "decoder.layers.62.fc2.bias", "decoder.layers.62.final_layer_norm.weight", "decoder.layers.62.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.63.flat_param_0": {"names": ["decoder.layers.63.self_attn.qkv_proj.weight", "decoder.layers.63.self_attn.qkv_proj.bias", "decoder.layers.63.self_attn.out_proj.weight", "decoder.layers.63.self_attn.out_proj.bias", "decoder.layers.63.self_attn_layer_norm.weight", "decoder.layers.63.self_attn_layer_norm.bias", "decoder.layers.63.fc1.weight", "decoder.layers.63.fc1.bias", "decoder.layers.63.fc2.weight", "decoder.layers.63.fc2.bias", "decoder.layers.63.final_layer_norm.weight", "decoder.layers.63.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.64.flat_param_0": {"names": ["decoder.layers.64.self_attn.qkv_proj.weight", "decoder.layers.64.self_attn.qkv_proj.bias", "decoder.layers.64.self_attn.out_proj.weight", "decoder.layers.64.self_attn.out_proj.bias", "decoder.layers.64.self_attn_layer_norm.weight", "decoder.layers.64.self_attn_layer_norm.bias", "decoder.layers.64.fc1.weight", "decoder.layers.64.fc1.bias", "decoder.layers.64.fc2.weight", "decoder.layers.64.fc2.bias", "decoder.layers.64.final_layer_norm.weight", "decoder.layers.64.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.65.flat_param_0": {"names": ["decoder.layers.65.self_attn.qkv_proj.weight", "decoder.layers.65.self_attn.qkv_proj.bias", "decoder.layers.65.self_attn.out_proj.weight", "decoder.layers.65.self_attn.out_proj.bias", "decoder.layers.65.self_attn_layer_norm.weight", "decoder.layers.65.self_attn_layer_norm.bias", "decoder.layers.65.fc1.weight", "decoder.layers.65.fc1.bias", "decoder.layers.65.fc2.weight", "decoder.layers.65.fc2.bias", "decoder.layers.65.final_layer_norm.weight", "decoder.layers.65.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.66.flat_param_0": {"names": ["decoder.layers.66.self_attn.qkv_proj.weight", "decoder.layers.66.self_attn.qkv_proj.bias", "decoder.layers.66.self_attn.out_proj.weight", "decoder.layers.66.self_attn.out_proj.bias", "decoder.layers.66.self_attn_layer_norm.weight", "decoder.layers.66.self_attn_layer_norm.bias", "decoder.layers.66.fc1.weight", "decoder.layers.66.fc1.bias", "decoder.layers.66.fc2.weight", "decoder.layers.66.fc2.bias", "decoder.layers.66.final_layer_norm.weight", "decoder.layers.66.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.67.flat_param_0": {"names": ["decoder.layers.67.self_attn.qkv_proj.weight", "decoder.layers.67.self_attn.qkv_proj.bias", "decoder.layers.67.self_attn.out_proj.weight", "decoder.layers.67.self_attn.out_proj.bias", "decoder.layers.67.self_attn_layer_norm.weight", "decoder.layers.67.self_attn_layer_norm.bias", "decoder.layers.67.fc1.weight", "decoder.layers.67.fc1.bias", "decoder.layers.67.fc2.weight", "decoder.layers.67.fc2.bias", "decoder.layers.67.final_layer_norm.weight", "decoder.layers.67.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.68.flat_param_0": {"names": ["decoder.layers.68.self_attn.qkv_proj.weight", "decoder.layers.68.self_attn.qkv_proj.bias", "decoder.layers.68.self_attn.out_proj.weight", "decoder.layers.68.self_attn.out_proj.bias", "decoder.layers.68.self_attn_layer_norm.weight", "decoder.layers.68.self_attn_layer_norm.bias", "decoder.layers.68.fc1.weight", "decoder.layers.68.fc1.bias", "decoder.layers.68.fc2.weight", "decoder.layers.68.fc2.bias", "decoder.layers.68.final_layer_norm.weight", "decoder.layers.68.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.69.flat_param_0": {"names": ["decoder.layers.69.self_attn.qkv_proj.weight", "decoder.layers.69.self_attn.qkv_proj.bias", "decoder.layers.69.self_attn.out_proj.weight", "decoder.layers.69.self_attn.out_proj.bias", "decoder.layers.69.self_attn_layer_norm.weight", "decoder.layers.69.self_attn_layer_norm.bias", "decoder.layers.69.fc1.weight", "decoder.layers.69.fc1.bias", "decoder.layers.69.fc2.weight", "decoder.layers.69.fc2.bias", "decoder.layers.69.final_layer_norm.weight", "decoder.layers.69.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.70.flat_param_0": {"names": ["decoder.layers.70.self_attn.qkv_proj.weight", "decoder.layers.70.self_attn.qkv_proj.bias", "decoder.layers.70.self_attn.out_proj.weight", "decoder.layers.70.self_attn.out_proj.bias", "decoder.layers.70.self_attn_layer_norm.weight", "decoder.layers.70.self_attn_layer_norm.bias", "decoder.layers.70.fc1.weight", "decoder.layers.70.fc1.bias", "decoder.layers.70.fc2.weight", "decoder.layers.70.fc2.bias", "decoder.layers.70.final_layer_norm.weight", "decoder.layers.70.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.71.flat_param_0": {"names": ["decoder.layers.71.self_attn.qkv_proj.weight", "decoder.layers.71.self_attn.qkv_proj.bias", "decoder.layers.71.self_attn.out_proj.weight", "decoder.layers.71.self_attn.out_proj.bias", "decoder.layers.71.self_attn_layer_norm.weight", "decoder.layers.71.self_attn_layer_norm.bias", "decoder.layers.71.fc1.weight", "decoder.layers.71.fc1.bias", "decoder.layers.71.fc2.weight", "decoder.layers.71.fc2.bias", "decoder.layers.71.final_layer_norm.weight", "decoder.layers.71.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.72.flat_param_0": {"names": ["decoder.layers.72.self_attn.qkv_proj.weight", "decoder.layers.72.self_attn.qkv_proj.bias", "decoder.layers.72.self_attn.out_proj.weight", "decoder.layers.72.self_attn.out_proj.bias", "decoder.layers.72.self_attn_layer_norm.weight", "decoder.layers.72.self_attn_layer_norm.bias", "decoder.layers.72.fc1.weight", "decoder.layers.72.fc1.bias", "decoder.layers.72.fc2.weight", "decoder.layers.72.fc2.bias", "decoder.layers.72.final_layer_norm.weight", "decoder.layers.72.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.73.flat_param_0": {"names": ["decoder.layers.73.self_attn.qkv_proj.weight", "decoder.layers.73.self_attn.qkv_proj.bias", "decoder.layers.73.self_attn.out_proj.weight", "decoder.layers.73.self_attn.out_proj.bias", "decoder.layers.73.self_attn_layer_norm.weight", "decoder.layers.73.self_attn_layer_norm.bias", "decoder.layers.73.fc1.weight", "decoder.layers.73.fc1.bias", "decoder.layers.73.fc2.weight", "decoder.layers.73.fc2.bias", "decoder.layers.73.final_layer_norm.weight", "decoder.layers.73.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.74.flat_param_0": {"names": ["decoder.layers.74.self_attn.qkv_proj.weight", "decoder.layers.74.self_attn.qkv_proj.bias", "decoder.layers.74.self_attn.out_proj.weight", "decoder.layers.74.self_attn.out_proj.bias", "decoder.layers.74.self_attn_layer_norm.weight", "decoder.layers.74.self_attn_layer_norm.bias", "decoder.layers.74.fc1.weight", "decoder.layers.74.fc1.bias", "decoder.layers.74.fc2.weight", "decoder.layers.74.fc2.bias", "decoder.layers.74.final_layer_norm.weight", "decoder.layers.74.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.75.flat_param_0": {"names": ["decoder.layers.75.self_attn.qkv_proj.weight", "decoder.layers.75.self_attn.qkv_proj.bias", "decoder.layers.75.self_attn.out_proj.weight", "decoder.layers.75.self_attn.out_proj.bias", "decoder.layers.75.self_attn_layer_norm.weight", "decoder.layers.75.self_attn_layer_norm.bias", "decoder.layers.75.fc1.weight", "decoder.layers.75.fc1.bias", "decoder.layers.75.fc2.weight", "decoder.layers.75.fc2.bias", "decoder.layers.75.final_layer_norm.weight", "decoder.layers.75.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.76.flat_param_0": {"names": ["decoder.layers.76.self_attn.qkv_proj.weight", "decoder.layers.76.self_attn.qkv_proj.bias", "decoder.layers.76.self_attn.out_proj.weight", "decoder.layers.76.self_attn.out_proj.bias", "decoder.layers.76.self_attn_layer_norm.weight", "decoder.layers.76.self_attn_layer_norm.bias", "decoder.layers.76.fc1.weight", "decoder.layers.76.fc1.bias", "decoder.layers.76.fc2.weight", "decoder.layers.76.fc2.bias", "decoder.layers.76.final_layer_norm.weight", "decoder.layers.76.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.77.flat_param_0": {"names": ["decoder.layers.77.self_attn.qkv_proj.weight", "decoder.layers.77.self_attn.qkv_proj.bias", "decoder.layers.77.self_attn.out_proj.weight", "decoder.layers.77.self_attn.out_proj.bias", "decoder.layers.77.self_attn_layer_norm.weight", "decoder.layers.77.self_attn_layer_norm.bias", "decoder.layers.77.fc1.weight", "decoder.layers.77.fc1.bias", "decoder.layers.77.fc2.weight", "decoder.layers.77.fc2.bias", "decoder.layers.77.final_layer_norm.weight", "decoder.layers.77.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.78.flat_param_0": {"names": ["decoder.layers.78.self_attn.qkv_proj.weight", "decoder.layers.78.self_attn.qkv_proj.bias", "decoder.layers.78.self_attn.out_proj.weight", "decoder.layers.78.self_attn.out_proj.bias", "decoder.layers.78.self_attn_layer_norm.weight", "decoder.layers.78.self_attn_layer_norm.bias", "decoder.layers.78.fc1.weight", "decoder.layers.78.fc1.bias", "decoder.layers.78.fc2.weight", "decoder.layers.78.fc2.bias", "decoder.layers.78.final_layer_norm.weight", "decoder.layers.78.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.79.flat_param_0": {"names": ["decoder.layers.79.self_attn.qkv_proj.weight", "decoder.layers.79.self_attn.qkv_proj.bias", "decoder.layers.79.self_attn.out_proj.weight", "decoder.layers.79.self_attn.out_proj.bias", "decoder.layers.79.self_attn_layer_norm.weight", "decoder.layers.79.self_attn_layer_norm.bias", "decoder.layers.79.fc1.weight", "decoder.layers.79.fc1.bias", "decoder.layers.79.fc2.weight", "decoder.layers.79.fc2.bias", "decoder.layers.79.final_layer_norm.weight", "decoder.layers.79.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.80.flat_param_0": {"names": ["decoder.layers.80.self_attn.qkv_proj.weight", "decoder.layers.80.self_attn.qkv_proj.bias", "decoder.layers.80.self_attn.out_proj.weight", "decoder.layers.80.self_attn.out_proj.bias", "decoder.layers.80.self_attn_layer_norm.weight", "decoder.layers.80.self_attn_layer_norm.bias", "decoder.layers.80.fc1.weight", "decoder.layers.80.fc1.bias", "decoder.layers.80.fc2.weight", "decoder.layers.80.fc2.bias", "decoder.layers.80.final_layer_norm.weight", "decoder.layers.80.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.81.flat_param_0": {"names": ["decoder.layers.81.self_attn.qkv_proj.weight", "decoder.layers.81.self_attn.qkv_proj.bias", "decoder.layers.81.self_attn.out_proj.weight", "decoder.layers.81.self_attn.out_proj.bias", "decoder.layers.81.self_attn_layer_norm.weight", "decoder.layers.81.self_attn_layer_norm.bias", "decoder.layers.81.fc1.weight", "decoder.layers.81.fc1.bias", "decoder.layers.81.fc2.weight", "decoder.layers.81.fc2.bias", "decoder.layers.81.final_layer_norm.weight", "decoder.layers.81.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.82.flat_param_0": {"names": ["decoder.layers.82.self_attn.qkv_proj.weight", "decoder.layers.82.self_attn.qkv_proj.bias", "decoder.layers.82.self_attn.out_proj.weight", "decoder.layers.82.self_attn.out_proj.bias", "decoder.layers.82.self_attn_layer_norm.weight", "decoder.layers.82.self_attn_layer_norm.bias", "decoder.layers.82.fc1.weight", "decoder.layers.82.fc1.bias", "decoder.layers.82.fc2.weight", "decoder.layers.82.fc2.bias", "decoder.layers.82.final_layer_norm.weight", "decoder.layers.82.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.83.flat_param_0": {"names": ["decoder.layers.83.self_attn.qkv_proj.weight", "decoder.layers.83.self_attn.qkv_proj.bias", "decoder.layers.83.self_attn.out_proj.weight", "decoder.layers.83.self_attn.out_proj.bias", "decoder.layers.83.self_attn_layer_norm.weight", "decoder.layers.83.self_attn_layer_norm.bias", "decoder.layers.83.fc1.weight", "decoder.layers.83.fc1.bias", "decoder.layers.83.fc2.weight", "decoder.layers.83.fc2.bias", "decoder.layers.83.final_layer_norm.weight", "decoder.layers.83.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.84.flat_param_0": {"names": ["decoder.layers.84.self_attn.qkv_proj.weight", "decoder.layers.84.self_attn.qkv_proj.bias", "decoder.layers.84.self_attn.out_proj.weight", "decoder.layers.84.self_attn.out_proj.bias", "decoder.layers.84.self_attn_layer_norm.weight", "decoder.layers.84.self_attn_layer_norm.bias", "decoder.layers.84.fc1.weight", "decoder.layers.84.fc1.bias", "decoder.layers.84.fc2.weight", "decoder.layers.84.fc2.bias", "decoder.layers.84.final_layer_norm.weight", "decoder.layers.84.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.85.flat_param_0": {"names": ["decoder.layers.85.self_attn.qkv_proj.weight", "decoder.layers.85.self_attn.qkv_proj.bias", "decoder.layers.85.self_attn.out_proj.weight", "decoder.layers.85.self_attn.out_proj.bias", "decoder.layers.85.self_attn_layer_norm.weight", "decoder.layers.85.self_attn_layer_norm.bias", "decoder.layers.85.fc1.weight", "decoder.layers.85.fc1.bias", "decoder.layers.85.fc2.weight", "decoder.layers.85.fc2.bias", "decoder.layers.85.final_layer_norm.weight", "decoder.layers.85.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.86.flat_param_0": {"names": ["decoder.layers.86.self_attn.qkv_proj.weight", "decoder.layers.86.self_attn.qkv_proj.bias", "decoder.layers.86.self_attn.out_proj.weight", "decoder.layers.86.self_attn.out_proj.bias", "decoder.layers.86.self_attn_layer_norm.weight", "decoder.layers.86.self_attn_layer_norm.bias", "decoder.layers.86.fc1.weight", "decoder.layers.86.fc1.bias", "decoder.layers.86.fc2.weight", "decoder.layers.86.fc2.bias", "decoder.layers.86.final_layer_norm.weight", "decoder.layers.86.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.87.flat_param_0": {"names": ["decoder.layers.87.self_attn.qkv_proj.weight", "decoder.layers.87.self_attn.qkv_proj.bias", "decoder.layers.87.self_attn.out_proj.weight", "decoder.layers.87.self_attn.out_proj.bias", "decoder.layers.87.self_attn_layer_norm.weight", "decoder.layers.87.self_attn_layer_norm.bias", "decoder.layers.87.fc1.weight", "decoder.layers.87.fc1.bias", "decoder.layers.87.fc2.weight", "decoder.layers.87.fc2.bias", "decoder.layers.87.final_layer_norm.weight", "decoder.layers.87.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.88.flat_param_0": {"names": ["decoder.layers.88.self_attn.qkv_proj.weight", "decoder.layers.88.self_attn.qkv_proj.bias", "decoder.layers.88.self_attn.out_proj.weight", "decoder.layers.88.self_attn.out_proj.bias", "decoder.layers.88.self_attn_layer_norm.weight", "decoder.layers.88.self_attn_layer_norm.bias", "decoder.layers.88.fc1.weight", "decoder.layers.88.fc1.bias", "decoder.layers.88.fc2.weight", "decoder.layers.88.fc2.bias", "decoder.layers.88.final_layer_norm.weight", "decoder.layers.88.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.89.flat_param_0": {"names": ["decoder.layers.89.self_attn.qkv_proj.weight", "decoder.layers.89.self_attn.qkv_proj.bias", "decoder.layers.89.self_attn.out_proj.weight", "decoder.layers.89.self_attn.out_proj.bias", "decoder.layers.89.self_attn_layer_norm.weight", "decoder.layers.89.self_attn_layer_norm.bias", "decoder.layers.89.fc1.weight", "decoder.layers.89.fc1.bias", "decoder.layers.89.fc2.weight", "decoder.layers.89.fc2.bias", "decoder.layers.89.final_layer_norm.weight", "decoder.layers.89.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.90.flat_param_0": {"names": ["decoder.layers.90.self_attn.qkv_proj.weight", "decoder.layers.90.self_attn.qkv_proj.bias", "decoder.layers.90.self_attn.out_proj.weight", "decoder.layers.90.self_attn.out_proj.bias", "decoder.layers.90.self_attn_layer_norm.weight", "decoder.layers.90.self_attn_layer_norm.bias", "decoder.layers.90.fc1.weight", "decoder.layers.90.fc1.bias", "decoder.layers.90.fc2.weight", "decoder.layers.90.fc2.bias", "decoder.layers.90.final_layer_norm.weight", "decoder.layers.90.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.91.flat_param_0": {"names": ["decoder.layers.91.self_attn.qkv_proj.weight", "decoder.layers.91.self_attn.qkv_proj.bias", "decoder.layers.91.self_attn.out_proj.weight", "decoder.layers.91.self_attn.out_proj.bias", "decoder.layers.91.self_attn_layer_norm.weight", "decoder.layers.91.self_attn_layer_norm.bias", "decoder.layers.91.fc1.weight", "decoder.layers.91.fc1.bias", "decoder.layers.91.fc2.weight", "decoder.layers.91.fc2.bias", "decoder.layers.91.final_layer_norm.weight", "decoder.layers.91.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.92.flat_param_0": {"names": ["decoder.layers.92.self_attn.qkv_proj.weight", "decoder.layers.92.self_attn.qkv_proj.bias", "decoder.layers.92.self_attn.out_proj.weight", "decoder.layers.92.self_attn.out_proj.bias", "decoder.layers.92.self_attn_layer_norm.weight", "decoder.layers.92.self_attn_layer_norm.bias", "decoder.layers.92.fc1.weight", "decoder.layers.92.fc1.bias", "decoder.layers.92.fc2.weight", "decoder.layers.92.fc2.bias", "decoder.layers.92.final_layer_norm.weight", "decoder.layers.92.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.93.flat_param_0": {"names": ["decoder.layers.93.self_attn.qkv_proj.weight", "decoder.layers.93.self_attn.qkv_proj.bias", "decoder.layers.93.self_attn.out_proj.weight", "decoder.layers.93.self_attn.out_proj.bias", "decoder.layers.93.self_attn_layer_norm.weight", "decoder.layers.93.self_attn_layer_norm.bias", "decoder.layers.93.fc1.weight", "decoder.layers.93.fc1.bias", "decoder.layers.93.fc2.weight", "decoder.layers.93.fc2.bias", "decoder.layers.93.final_layer_norm.weight", "decoder.layers.93.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.94.flat_param_0": {"names": ["decoder.layers.94.self_attn.qkv_proj.weight", "decoder.layers.94.self_attn.qkv_proj.bias", "decoder.layers.94.self_attn.out_proj.weight", "decoder.layers.94.self_attn.out_proj.bias", "decoder.layers.94.self_attn_layer_norm.weight", "decoder.layers.94.self_attn_layer_norm.bias", "decoder.layers.94.fc1.weight", "decoder.layers.94.fc1.bias", "decoder.layers.94.fc2.weight", "decoder.layers.94.fc2.bias", "decoder.layers.94.final_layer_norm.weight", "decoder.layers.94.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}, "decoder.layers.95.flat_param_0": {"names": ["decoder.layers.95.self_attn.qkv_proj.weight", "decoder.layers.95.self_attn.qkv_proj.bias", "decoder.layers.95.self_attn.out_proj.weight", "decoder.layers.95.self_attn.out_proj.bias", "decoder.layers.95.self_attn_layer_norm.weight", "decoder.layers.95.self_attn_layer_norm.bias", "decoder.layers.95.fc1.weight", "decoder.layers.95.fc1.bias", "decoder.layers.95.fc2.weight", "decoder.layers.95.fc2.bias", "decoder.layers.95.final_layer_norm.weight", "decoder.layers.95.final_layer_norm.bias"], "shapes": [[4608, 12288], [4608], [12288, 1536], [12288], [12288], [12288], [6144, 12288], [6144], [12288, 6144], [12288], [12288], [12288]], "numels": [56623104, 4608, 18874368, 12288, 12288, 12288, 75497472, 6144, 75497472, 12288, 12288, 12288]}}