{ "metadata": { "ParamSize": 170, "ParamBytes": 1976131072.0, "BitsPerParam": 32.0 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 272269312, "records": [ { "name": "model.embed_tokens.weight", "shape": [ 151936, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 272269312, "byteOffset": 0 } ], "md5sum": "2d6ed0332786cfd9688f94b29bf9e276" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 29826560, "records": [ { "name": "model.layers.0.input_layernorm.weight", "shape": [ 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1792, "byteOffset": 0 }, { "name": "model.layers.0.mlp.down_proj.weight", "shape": [ 896, 4864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8716288, "byteOffset": 1792 }, { "name": "model.layers.0.mlp.gate_up_proj.weight", "shape": [ 9728, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17432576, "byteOffset": 8718080 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1792, "byteOffset": 26150656 }, { "name": "model.layers.0.self_attn.c_attn.bias", "shape": [ 1152 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2304, "byteOffset": 26152448 }, { "name": "model.layers.0.self_attn.c_attn.weight", "shape": [ 1152, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2064384, "byteOffset": 26154752 }, { "name": "model.layers.0.self_attn.o_proj.weight", "shape": [ 896, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1605632, "byteOffset": 28219136 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1792, "byteOffset": 29824768 } ], "md5sum": "2870b97073857a1a0046359c890c124e" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 29824768, "records": [ { "name": "model.layers.1.mlp.down_proj.weight", "shape": [ 896, 4864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8716288, "byteOffset": 0 }, { "name": "model.layers.1.mlp.gate_up_proj.weight", "shape": [ 9728, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17432576, "byteOffset": 8716288 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1792, "byteOffset": 26148864 }, { "name": "model.layers.1.self_attn.c_attn.bias", "shape": [ 1152 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2304, "byteOffset": 26150656 }, { "name": "model.layers.1.self_attn.c_attn.weight", "shape": [ 1152, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2064384, "byteOffset": 26152960 }, { "name": "model.layers.1.self_attn.o_proj.weight", "shape": [ 896, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1605632, "byteOffset": 28217344 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1792, "byteOffset": 29822976 } ], "md5sum": "b47f54a212dc1d563a1929aba19abfae" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 29824768, "records": [ { "name": "model.layers.10.mlp.down_proj.weight", "shape": [ 896, 4864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8716288, "byteOffset": 0 }, { "name": "model.layers.10.mlp.gate_up_proj.weight", "shape": [ 9728, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17432576, "byteOffset": 8716288 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1792, "byteOffset": 26148864 }, { "name": "model.layers.10.self_attn.c_attn.bias", "shape": [ 1152 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2304, "byteOffset": 26150656 }, { "name": "model.layers.10.self_attn.c_attn.weight", "shape": [ 1152, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2064384, "byteOffset": 26152960 }, { "name": "model.layers.10.self_attn.o_proj.weight", "shape": [ 896, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1605632, "byteOffset": 28217344 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1792, "byteOffset": 29822976 } ], "md5sum": "09bce6bfabd4a02ad7c546784341d88c" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 29824768, "records": [ { "name": "model.layers.11.mlp.down_proj.weight", "shape": [ 896, 4864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8716288, "byteOffset": 0 }, { "name": "model.layers.11.mlp.gate_up_proj.weight", "shape": [ 9728, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17432576, "byteOffset": 8716288 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1792, "byteOffset": 26148864 }, { "name": "model.layers.11.self_attn.c_attn.bias", "shape": [ 1152 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2304, "byteOffset": 26150656 }, { "name": "model.layers.11.self_attn.c_attn.weight", "shape": [ 1152, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2064384, "byteOffset": 26152960 }, { "name": "model.layers.11.self_attn.o_proj.weight", "shape": [ 896, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1605632, "byteOffset": 28217344 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1792, "byteOffset": 29822976 } ], "md5sum": "8bfa0e4c2f9cf9648b40e2ec614738bd" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 29824768, "records": [ { "name": "model.layers.12.mlp.down_proj.weight", "shape": [ 896, 4864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8716288, "byteOffset": 0 }, { "name": "model.layers.12.mlp.gate_up_proj.weight", "shape": [ 9728, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17432576, "byteOffset": 8716288 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1792, "byteOffset": 26148864 }, { "name": "model.layers.12.self_attn.c_attn.bias", "shape": [ 1152 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2304, "byteOffset": 26150656 }, { "name": "model.layers.12.self_attn.c_attn.weight", "shape": [ 1152, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2064384, "byteOffset": 26152960 }, { "name": "model.layers.12.self_attn.o_proj.weight", "shape": [ 896, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1605632, "byteOffset": 28217344 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1792, "byteOffset": 29822976 } ], "md5sum": "c916c9168d2c4955d1f9106bd31f6e7c" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 29824768, "records": [ { "name": "model.layers.13.mlp.down_proj.weight", "shape": [ 896, 4864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8716288, "byteOffset": 0 }, { "name": "model.layers.13.mlp.gate_up_proj.weight", "shape": [ 9728, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17432576, "byteOffset": 8716288 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1792, "byteOffset": 26148864 }, { "name": "model.layers.13.self_attn.c_attn.bias", "shape": [ 1152 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2304, "byteOffset": 26150656 }, { "name": "model.layers.13.self_attn.c_attn.weight", "shape": [ 1152, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2064384, "byteOffset": 26152960 }, { "name": "model.layers.13.self_attn.o_proj.weight", "shape": [ 896, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1605632, "byteOffset": 28217344 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1792, "byteOffset": 29822976 } ], "md5sum": "3055cec491cdc8737362f85ea6f0dd1d" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 29824768, "records": [ { "name": "model.layers.14.mlp.down_proj.weight", "shape": [ 896, 4864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8716288, "byteOffset": 0 }, { "name": "model.layers.14.mlp.gate_up_proj.weight", "shape": [ 9728, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17432576, "byteOffset": 8716288 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1792, "byteOffset": 26148864 }, { "name": "model.layers.14.self_attn.c_attn.bias", "shape": [ 1152 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2304, "byteOffset": 26150656 }, { "name": "model.layers.14.self_attn.c_attn.weight", "shape": [ 1152, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2064384, "byteOffset": 26152960 }, { "name": "model.layers.14.self_attn.o_proj.weight", "shape": [ 896, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1605632, "byteOffset": 28217344 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1792, "byteOffset": 29822976 } ], "md5sum": "0b87564f530ca51811dc483c6624929b" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 29824768, "records": [ { "name": "model.layers.15.mlp.down_proj.weight", "shape": [ 896, 4864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8716288, "byteOffset": 0 }, { "name": "model.layers.15.mlp.gate_up_proj.weight", "shape": [ 9728, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17432576, "byteOffset": 8716288 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1792, "byteOffset": 26148864 }, { "name": "model.layers.15.self_attn.c_attn.bias", "shape": [ 1152 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2304, "byteOffset": 26150656 }, { "name": "model.layers.15.self_attn.c_attn.weight", "shape": [ 1152, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2064384, "byteOffset": 26152960 }, { "name": "model.layers.15.self_attn.o_proj.weight", "shape": [ 896, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1605632, "byteOffset": 28217344 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1792, "byteOffset": 29822976 } ], "md5sum": "6faea0e7b6f206b3560ade298d6cff9b" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 29824768, "records": [ { "name": "model.layers.16.mlp.down_proj.weight", "shape": [ 896, 4864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8716288, "byteOffset": 0 }, { "name": "model.layers.16.mlp.gate_up_proj.weight", "shape": [ 9728, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17432576, "byteOffset": 8716288 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1792, "byteOffset": 26148864 }, { "name": "model.layers.16.self_attn.c_attn.bias", "shape": [ 1152 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2304, "byteOffset": 26150656 }, { "name": "model.layers.16.self_attn.c_attn.weight", "shape": [ 1152, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2064384, "byteOffset": 26152960 }, { "name": "model.layers.16.self_attn.o_proj.weight", "shape": [ 896, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1605632, "byteOffset": 28217344 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1792, "byteOffset": 29822976 } ], "md5sum": "09c7f8356956494abc562b9f7408ba60" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 29824768, "records": [ { "name": "model.layers.17.mlp.down_proj.weight", "shape": [ 896, 4864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8716288, "byteOffset": 0 }, { "name": "model.layers.17.mlp.gate_up_proj.weight", "shape": [ 9728, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17432576, "byteOffset": 8716288 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1792, "byteOffset": 26148864 }, { "name": "model.layers.17.self_attn.c_attn.bias", "shape": [ 1152 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2304, "byteOffset": 26150656 }, { "name": "model.layers.17.self_attn.c_attn.weight", "shape": [ 1152, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2064384, "byteOffset": 26152960 }, { "name": "model.layers.17.self_attn.o_proj.weight", "shape": [ 896, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1605632, "byteOffset": 28217344 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1792, "byteOffset": 29822976 } ], "md5sum": "75351214f8048c4600db6e44b0d3cda5" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 29824768, "records": [ { "name": "model.layers.18.mlp.down_proj.weight", "shape": [ 896, 4864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8716288, "byteOffset": 0 }, { "name": "model.layers.18.mlp.gate_up_proj.weight", "shape": [ 9728, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17432576, "byteOffset": 8716288 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1792, "byteOffset": 26148864 }, { "name": "model.layers.18.self_attn.c_attn.bias", "shape": [ 1152 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2304, "byteOffset": 26150656 }, { "name": "model.layers.18.self_attn.c_attn.weight", "shape": [ 1152, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2064384, "byteOffset": 26152960 }, { "name": "model.layers.18.self_attn.o_proj.weight", "shape": [ 896, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1605632, "byteOffset": 28217344 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1792, "byteOffset": 29822976 } ], "md5sum": "ddacb2e4a29cd55b68fd28c993b9cb58" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 29824768, "records": [ { "name": "model.layers.19.mlp.down_proj.weight", "shape": [ 896, 4864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8716288, "byteOffset": 0 }, { "name": "model.layers.19.mlp.gate_up_proj.weight", "shape": [ 9728, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17432576, "byteOffset": 8716288 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1792, "byteOffset": 26148864 }, { "name": "model.layers.19.self_attn.c_attn.bias", "shape": [ 1152 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2304, "byteOffset": 26150656 }, { "name": "model.layers.19.self_attn.c_attn.weight", "shape": [ 1152, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2064384, "byteOffset": 26152960 }, { "name": "model.layers.19.self_attn.o_proj.weight", "shape": [ 896, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1605632, "byteOffset": 28217344 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1792, "byteOffset": 29822976 } ], "md5sum": "7b511e16f19592a4b7420385d8fdfcd7" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 29824768, "records": [ { "name": "model.layers.2.mlp.down_proj.weight", "shape": [ 896, 4864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8716288, "byteOffset": 0 }, { "name": "model.layers.2.mlp.gate_up_proj.weight", "shape": [ 9728, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17432576, "byteOffset": 8716288 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1792, "byteOffset": 26148864 }, { "name": "model.layers.2.self_attn.c_attn.bias", "shape": [ 1152 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2304, "byteOffset": 26150656 }, { "name": "model.layers.2.self_attn.c_attn.weight", "shape": [ 1152, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2064384, "byteOffset": 26152960 }, { "name": "model.layers.2.self_attn.o_proj.weight", "shape": [ 896, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1605632, "byteOffset": 28217344 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1792, "byteOffset": 29822976 } ], "md5sum": "8051fc4e3d5845843c8e95e7e87e12a4" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 29824768, "records": [ { "name": "model.layers.20.mlp.down_proj.weight", "shape": [ 896, 4864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8716288, "byteOffset": 0 }, { "name": "model.layers.20.mlp.gate_up_proj.weight", "shape": [ 9728, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17432576, "byteOffset": 8716288 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1792, "byteOffset": 26148864 }, { "name": "model.layers.20.self_attn.c_attn.bias", "shape": [ 1152 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2304, "byteOffset": 26150656 }, { "name": "model.layers.20.self_attn.c_attn.weight", "shape": [ 1152, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2064384, "byteOffset": 26152960 }, { "name": "model.layers.20.self_attn.o_proj.weight", "shape": [ 896, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1605632, "byteOffset": 28217344 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1792, "byteOffset": 29822976 } ], "md5sum": "9489f85f4751787c63f546e5bc0129f5" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 29824768, "records": [ { "name": "model.layers.21.mlp.down_proj.weight", "shape": [ 896, 4864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8716288, "byteOffset": 0 }, { "name": "model.layers.21.mlp.gate_up_proj.weight", "shape": [ 9728, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17432576, "byteOffset": 8716288 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1792, "byteOffset": 26148864 }, { "name": "model.layers.21.self_attn.c_attn.bias", "shape": [ 1152 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2304, "byteOffset": 26150656 }, { "name": "model.layers.21.self_attn.c_attn.weight", "shape": [ 1152, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2064384, "byteOffset": 26152960 }, { "name": "model.layers.21.self_attn.o_proj.weight", "shape": [ 896, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1605632, "byteOffset": 28217344 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1792, "byteOffset": 29822976 } ], "md5sum": "69922e376c6ffa6a0f65ebcba2069ebc" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 29824768, "records": [ { "name": "model.layers.22.mlp.down_proj.weight", "shape": [ 896, 4864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8716288, "byteOffset": 0 }, { "name": "model.layers.22.mlp.gate_up_proj.weight", "shape": [ 9728, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17432576, "byteOffset": 8716288 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1792, "byteOffset": 26148864 }, { "name": "model.layers.22.self_attn.c_attn.bias", "shape": [ 1152 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2304, "byteOffset": 26150656 }, { "name": "model.layers.22.self_attn.c_attn.weight", "shape": [ 1152, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2064384, "byteOffset": 26152960 }, { "name": "model.layers.22.self_attn.o_proj.weight", "shape": [ 896, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1605632, "byteOffset": 28217344 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1792, "byteOffset": 29822976 } ], "md5sum": "08ed24324cad5fd6677b2d13bc21ea57" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 29824768, "records": [ { "name": "model.layers.23.mlp.down_proj.weight", "shape": [ 896, 4864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8716288, "byteOffset": 0 }, { "name": "model.layers.23.mlp.gate_up_proj.weight", "shape": [ 9728, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17432576, "byteOffset": 8716288 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1792, "byteOffset": 26148864 }, { "name": "model.layers.23.self_attn.c_attn.bias", "shape": [ 1152 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2304, "byteOffset": 26150656 }, { "name": "model.layers.23.self_attn.c_attn.weight", "shape": [ 1152, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2064384, "byteOffset": 26152960 }, { "name": "model.layers.23.self_attn.o_proj.weight", "shape": [ 896, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1605632, "byteOffset": 28217344 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1792, "byteOffset": 29822976 } ], "md5sum": "6dc514572f3d66d929f483e418b85bcc" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 29824768, "records": [ { "name": "model.layers.3.mlp.down_proj.weight", "shape": [ 896, 4864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8716288, "byteOffset": 0 }, { "name": "model.layers.3.mlp.gate_up_proj.weight", "shape": [ 9728, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17432576, "byteOffset": 8716288 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1792, "byteOffset": 26148864 }, { "name": "model.layers.3.self_attn.c_attn.bias", "shape": [ 1152 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2304, "byteOffset": 26150656 }, { "name": "model.layers.3.self_attn.c_attn.weight", "shape": [ 1152, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2064384, "byteOffset": 26152960 }, { "name": "model.layers.3.self_attn.o_proj.weight", "shape": [ 896, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1605632, "byteOffset": 28217344 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1792, "byteOffset": 29822976 } ], "md5sum": "a2018584768d29654692a3d185b5f8c3" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 29824768, "records": [ { "name": "model.layers.4.mlp.down_proj.weight", "shape": [ 896, 4864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8716288, "byteOffset": 0 }, { "name": "model.layers.4.mlp.gate_up_proj.weight", "shape": [ 9728, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17432576, "byteOffset": 8716288 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1792, "byteOffset": 26148864 }, { "name": "model.layers.4.self_attn.c_attn.bias", "shape": [ 1152 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2304, "byteOffset": 26150656 }, { "name": "model.layers.4.self_attn.c_attn.weight", "shape": [ 1152, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2064384, "byteOffset": 26152960 }, { "name": "model.layers.4.self_attn.o_proj.weight", "shape": [ 896, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1605632, "byteOffset": 28217344 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1792, "byteOffset": 29822976 } ], "md5sum": "d332a5c091519c7c265a2a6326524ea4" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 29824768, "records": [ { "name": "model.layers.5.mlp.down_proj.weight", "shape": [ 896, 4864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8716288, "byteOffset": 0 }, { "name": "model.layers.5.mlp.gate_up_proj.weight", "shape": [ 9728, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17432576, "byteOffset": 8716288 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1792, "byteOffset": 26148864 }, { "name": "model.layers.5.self_attn.c_attn.bias", "shape": [ 1152 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2304, "byteOffset": 26150656 }, { "name": "model.layers.5.self_attn.c_attn.weight", "shape": [ 1152, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2064384, "byteOffset": 26152960 }, { "name": "model.layers.5.self_attn.o_proj.weight", "shape": [ 896, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1605632, "byteOffset": 28217344 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1792, "byteOffset": 29822976 } ], "md5sum": "aff3ac1337055aa58e76949a32eafa75" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 29824768, "records": [ { "name": "model.layers.6.mlp.down_proj.weight", "shape": [ 896, 4864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8716288, "byteOffset": 0 }, { "name": "model.layers.6.mlp.gate_up_proj.weight", "shape": [ 9728, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17432576, "byteOffset": 8716288 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1792, "byteOffset": 26148864 }, { "name": "model.layers.6.self_attn.c_attn.bias", "shape": [ 1152 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2304, "byteOffset": 26150656 }, { "name": "model.layers.6.self_attn.c_attn.weight", "shape": [ 1152, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2064384, "byteOffset": 26152960 }, { "name": "model.layers.6.self_attn.o_proj.weight", "shape": [ 896, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1605632, "byteOffset": 28217344 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1792, "byteOffset": 29822976 } ], "md5sum": "d144e41a40c571b1bb4130ef6478a856" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 29824768, "records": [ { "name": "model.layers.7.mlp.down_proj.weight", "shape": [ 896, 4864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8716288, "byteOffset": 0 }, { "name": "model.layers.7.mlp.gate_up_proj.weight", "shape": [ 9728, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17432576, "byteOffset": 8716288 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1792, "byteOffset": 26148864 }, { "name": "model.layers.7.self_attn.c_attn.bias", "shape": [ 1152 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2304, "byteOffset": 26150656 }, { "name": "model.layers.7.self_attn.c_attn.weight", "shape": [ 1152, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2064384, "byteOffset": 26152960 }, { "name": "model.layers.7.self_attn.o_proj.weight", "shape": [ 896, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1605632, "byteOffset": 28217344 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1792, "byteOffset": 29822976 } ], "md5sum": "4aee8d21557eda5853df98d92dc868dd" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 29824768, "records": [ { "name": "model.layers.8.mlp.down_proj.weight", "shape": [ 896, 4864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8716288, "byteOffset": 0 }, { "name": "model.layers.8.mlp.gate_up_proj.weight", "shape": [ 9728, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17432576, "byteOffset": 8716288 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1792, "byteOffset": 26148864 }, { "name": "model.layers.8.self_attn.c_attn.bias", "shape": [ 1152 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2304, "byteOffset": 26150656 }, { "name": "model.layers.8.self_attn.c_attn.weight", "shape": [ 1152, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2064384, "byteOffset": 26152960 }, { "name": "model.layers.8.self_attn.o_proj.weight", "shape": [ 896, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1605632, "byteOffset": 28217344 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1792, "byteOffset": 29822976 } ], "md5sum": "8720858ce3ac5418c7bfc928c9a191bd" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 29824768, "records": [ { "name": "model.layers.9.mlp.down_proj.weight", "shape": [ 896, 4864 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8716288, "byteOffset": 0 }, { "name": "model.layers.9.mlp.gate_up_proj.weight", "shape": [ 9728, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 17432576, "byteOffset": 8716288 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1792, "byteOffset": 26148864 }, { "name": "model.layers.9.self_attn.c_attn.bias", "shape": [ 1152 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2304, "byteOffset": 26150656 }, { "name": "model.layers.9.self_attn.c_attn.weight", "shape": [ 1152, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2064384, "byteOffset": 26152960 }, { "name": "model.layers.9.self_attn.o_proj.weight", "shape": [ 896, 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1605632, "byteOffset": 28217344 }, { "name": "model.norm.weight", "shape": [ 896 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1792, "byteOffset": 29822976 } ], "md5sum": "1c3ee74de373041d694e8afa1243da99" } ] }