{ "metadata": { "ParamSize": 171, "ParamBytes": 1239140352.0, "BitsPerParam": 16.0 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 311164928, "records": [ { "name": "lm_head.weight", "shape": [ 151936, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 311164928, "byteOffset": 0 } ], "md5sum": "9ad841023c938873aacc8dfa7bf3566a" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 311164928, "records": [ { "name": "model.embed_tokens.weight", "shape": [ 151936, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 311164928, "byteOffset": 0 } ], "md5sum": "9ad841023c938873aacc8dfa7bf3566a" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 31469568, "records": [ { "name": "model.layers.0.input_layernorm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 0 }, { "name": "model.layers.0.mlp.down_proj.weight", "shape": [ 1024, 2816 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 2048 }, { "name": "model.layers.0.mlp.gate_up_proj.weight", "shape": [ 5632, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 5769216 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 17303552 }, { "name": "model.layers.0.self_attn.c_attn.bias", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 17305600 }, { "name": "model.layers.0.self_attn.c_attn.weight", "shape": [ 3072, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 17311744 }, { "name": "model.layers.0.self_attn.o_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 23603200 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25700352 }, { "name": "model.layers.1.mlp.down_proj.weight", "shape": [ 1024, 2816 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 25702400 } ], "md5sum": "c83307e4bf50d2e47a2a452caf6502b4" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 25700352, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.weight", "shape": [ 5632, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 11534336 }, { "name": "model.layers.1.self_attn.c_attn.bias", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 11536384 }, { "name": "model.layers.1.self_attn.c_attn.weight", "shape": [ 3072, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 11542528 }, { "name": "model.layers.1.self_attn.o_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 17833984 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 19931136 }, { "name": "model.layers.10.mlp.down_proj.weight", "shape": [ 1024, 2816 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 19933184 } ], "md5sum": "40ec9a6cf11496051e8eb99ad47b508a" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 25700352, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.weight", "shape": [ 5632, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 11534336 }, { "name": "model.layers.10.self_attn.c_attn.bias", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 11536384 }, { "name": "model.layers.10.self_attn.c_attn.weight", "shape": [ 3072, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 11542528 }, { "name": "model.layers.10.self_attn.o_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 17833984 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 19931136 }, { "name": "model.layers.11.mlp.down_proj.weight", "shape": [ 1024, 2816 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 19933184 } ], "md5sum": "8c3f85d877c238dd743f6f1b2b03ba8a" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 25700352, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.weight", "shape": [ 5632, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 11534336 }, { "name": "model.layers.11.self_attn.c_attn.bias", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 11536384 }, { "name": "model.layers.11.self_attn.c_attn.weight", "shape": [ 3072, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 11542528 }, { "name": "model.layers.11.self_attn.o_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 17833984 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 19931136 }, { "name": "model.layers.12.mlp.down_proj.weight", "shape": [ 1024, 2816 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 19933184 } ], "md5sum": "04478e6bf88bd0157de04733e0501599" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 25700352, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.weight", "shape": [ 5632, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 11534336 }, { "name": "model.layers.12.self_attn.c_attn.bias", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 11536384 }, { "name": "model.layers.12.self_attn.c_attn.weight", "shape": [ 3072, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 11542528 }, { "name": "model.layers.12.self_attn.o_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 17833984 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 19931136 }, { "name": "model.layers.13.mlp.down_proj.weight", "shape": [ 1024, 2816 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 19933184 } ], "md5sum": "c0c36c829d9a50aaa962d9a4542bf4dc" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 25700352, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.weight", "shape": [ 5632, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 11534336 }, { "name": "model.layers.13.self_attn.c_attn.bias", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 11536384 }, { "name": "model.layers.13.self_attn.c_attn.weight", "shape": [ 3072, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 11542528 }, { "name": "model.layers.13.self_attn.o_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 17833984 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 19931136 }, { "name": "model.layers.14.mlp.down_proj.weight", "shape": [ 1024, 2816 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 19933184 } ], "md5sum": "c4ef41fe310776e417ebf57681f5aa85" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 25700352, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.weight", "shape": [ 5632, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 11534336 }, { "name": "model.layers.14.self_attn.c_attn.bias", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 11536384 }, { "name": "model.layers.14.self_attn.c_attn.weight", "shape": [ 3072, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 11542528 }, { "name": "model.layers.14.self_attn.o_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 17833984 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 19931136 }, { "name": "model.layers.15.mlp.down_proj.weight", "shape": [ 1024, 2816 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 19933184 } ], "md5sum": "dff83490a4e7a16cd2b905b92b2a1eda" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 25700352, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.weight", "shape": [ 5632, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 11534336 }, { "name": "model.layers.15.self_attn.c_attn.bias", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 11536384 }, { "name": "model.layers.15.self_attn.c_attn.weight", "shape": [ 3072, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 11542528 }, { "name": "model.layers.15.self_attn.o_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 17833984 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 19931136 }, { "name": "model.layers.16.mlp.down_proj.weight", "shape": [ 1024, 2816 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 19933184 } ], "md5sum": "68a5d47ad021ef139e7b57db6bce2204" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 25700352, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.weight", "shape": [ 5632, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 11534336 }, { "name": "model.layers.16.self_attn.c_attn.bias", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 11536384 }, { "name": "model.layers.16.self_attn.c_attn.weight", "shape": [ 3072, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 11542528 }, { "name": "model.layers.16.self_attn.o_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 17833984 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 19931136 }, { "name": "model.layers.17.mlp.down_proj.weight", "shape": [ 1024, 2816 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 19933184 } ], "md5sum": "afee818b99782f1be66296f5679a5a96" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 25700352, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.weight", "shape": [ 5632, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 11534336 }, { "name": "model.layers.17.self_attn.c_attn.bias", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 11536384 }, { "name": "model.layers.17.self_attn.c_attn.weight", "shape": [ 3072, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 11542528 }, { "name": "model.layers.17.self_attn.o_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 17833984 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 19931136 }, { "name": "model.layers.18.mlp.down_proj.weight", "shape": [ 1024, 2816 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 19933184 } ], "md5sum": "4930a3e6478ee30cd437add5fedfe060" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 25700352, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.weight", "shape": [ 5632, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 11534336 }, { "name": "model.layers.18.self_attn.c_attn.bias", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 11536384 }, { "name": "model.layers.18.self_attn.c_attn.weight", "shape": [ 3072, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 11542528 }, { "name": "model.layers.18.self_attn.o_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 17833984 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 19931136 }, { "name": "model.layers.19.mlp.down_proj.weight", "shape": [ 1024, 2816 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 19933184 } ], "md5sum": "e8b152a6bc0b7318999a7ecf4758a4ae" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 25700352, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.weight", "shape": [ 5632, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 11534336 }, { "name": "model.layers.19.self_attn.c_attn.bias", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 11536384 }, { "name": "model.layers.19.self_attn.c_attn.weight", "shape": [ 3072, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 11542528 }, { "name": "model.layers.19.self_attn.o_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 17833984 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 19931136 }, { "name": "model.layers.2.mlp.down_proj.weight", "shape": [ 1024, 2816 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 19933184 } ], "md5sum": "6c9a16660d168d0013f211264c973faf" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 25700352, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.weight", "shape": [ 5632, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 11534336 }, { "name": "model.layers.2.self_attn.c_attn.bias", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 11536384 }, { "name": "model.layers.2.self_attn.c_attn.weight", "shape": [ 3072, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 11542528 }, { "name": "model.layers.2.self_attn.o_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 17833984 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 19931136 }, { "name": "model.layers.20.mlp.down_proj.weight", "shape": [ 1024, 2816 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 19933184 } ], "md5sum": "2135bcb7dc23c91c41f641cd518d9dac" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 25700352, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.weight", "shape": [ 5632, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 11534336 }, { "name": "model.layers.20.self_attn.c_attn.bias", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 11536384 }, { "name": "model.layers.20.self_attn.c_attn.weight", "shape": [ 3072, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 11542528 }, { "name": "model.layers.20.self_attn.o_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 17833984 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 19931136 }, { "name": "model.layers.21.mlp.down_proj.weight", "shape": [ 1024, 2816 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 19933184 } ], "md5sum": "4fb95fba954bdca80dddb47cf6f38955" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 25700352, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.weight", "shape": [ 5632, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 11534336 }, { "name": "model.layers.21.self_attn.c_attn.bias", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 11536384 }, { "name": "model.layers.21.self_attn.c_attn.weight", "shape": [ 3072, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 11542528 }, { "name": "model.layers.21.self_attn.o_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 17833984 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 19931136 }, { "name": "model.layers.22.mlp.down_proj.weight", "shape": [ 1024, 2816 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 19933184 } ], "md5sum": "99cf1ab9f9f3873d10b23074aab226ca" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 25700352, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.weight", "shape": [ 5632, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 11534336 }, { "name": "model.layers.22.self_attn.c_attn.bias", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 11536384 }, { "name": "model.layers.22.self_attn.c_attn.weight", "shape": [ 3072, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 11542528 }, { "name": "model.layers.22.self_attn.o_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 17833984 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 19931136 }, { "name": "model.layers.23.mlp.down_proj.weight", "shape": [ 1024, 2816 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 19933184 } ], "md5sum": "af41b41da2365dd9e67788a2bbf4133f" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 25700352, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.weight", "shape": [ 5632, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 11534336 }, { "name": "model.layers.23.self_attn.c_attn.bias", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 11536384 }, { "name": "model.layers.23.self_attn.c_attn.weight", "shape": [ 3072, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 11542528 }, { "name": "model.layers.23.self_attn.o_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 17833984 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 19931136 }, { "name": "model.layers.3.mlp.down_proj.weight", "shape": [ 1024, 2816 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 19933184 } ], "md5sum": "e8209ecdf7ce06c90d2c18783dc940e3" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 25700352, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.weight", "shape": [ 5632, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 11534336 }, { "name": "model.layers.3.self_attn.c_attn.bias", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 11536384 }, { "name": "model.layers.3.self_attn.c_attn.weight", "shape": [ 3072, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 11542528 }, { "name": "model.layers.3.self_attn.o_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 17833984 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 19931136 }, { "name": "model.layers.4.mlp.down_proj.weight", "shape": [ 1024, 2816 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 19933184 } ], "md5sum": "6d10940312736cb810f03379ad0eaacb" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 25700352, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.weight", "shape": [ 5632, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 11534336 }, { "name": "model.layers.4.self_attn.c_attn.bias", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 11536384 }, { "name": "model.layers.4.self_attn.c_attn.weight", "shape": [ 3072, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 11542528 }, { "name": "model.layers.4.self_attn.o_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 17833984 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 19931136 }, { "name": "model.layers.5.mlp.down_proj.weight", "shape": [ 1024, 2816 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 19933184 } ], "md5sum": "66ba043038bbfa34c5071fcd2fc80477" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 25700352, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.weight", "shape": [ 5632, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 11534336 }, { "name": "model.layers.5.self_attn.c_attn.bias", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 11536384 }, { "name": "model.layers.5.self_attn.c_attn.weight", "shape": [ 3072, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 11542528 }, { "name": "model.layers.5.self_attn.o_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 17833984 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 19931136 }, { "name": "model.layers.6.mlp.down_proj.weight", "shape": [ 1024, 2816 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 19933184 } ], "md5sum": "8efd4c932df27b614e0297c8f4863b6c" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 25700352, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.weight", "shape": [ 5632, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 11534336 }, { "name": "model.layers.6.self_attn.c_attn.bias", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 11536384 }, { "name": "model.layers.6.self_attn.c_attn.weight", "shape": [ 3072, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 11542528 }, { "name": "model.layers.6.self_attn.o_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 17833984 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 19931136 }, { "name": "model.layers.7.mlp.down_proj.weight", "shape": [ 1024, 2816 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 19933184 } ], "md5sum": "c9cc4bbf32d4d3cd71fc3d9aac0e8d09" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 25700352, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.weight", "shape": [ 5632, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 11534336 }, { "name": "model.layers.7.self_attn.c_attn.bias", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 11536384 }, { "name": "model.layers.7.self_attn.c_attn.weight", "shape": [ 3072, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 11542528 }, { "name": "model.layers.7.self_attn.o_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 17833984 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 19931136 }, { "name": "model.layers.8.mlp.down_proj.weight", "shape": [ 1024, 2816 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 19933184 } ], "md5sum": "0349c6929c5eb51dceeadd09a33df500" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 25700352, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.weight", "shape": [ 5632, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 11534336 }, { "name": "model.layers.8.self_attn.c_attn.bias", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 11536384 }, { "name": "model.layers.8.self_attn.c_attn.weight", "shape": [ 3072, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 11542528 }, { "name": "model.layers.8.self_attn.o_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 17833984 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 19931136 }, { "name": "model.layers.9.mlp.down_proj.weight", "shape": [ 1024, 2816 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 19933184 } ], "md5sum": "5027c555bd33d3a6ee38ae82c4dcf8fe" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 19933184, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.weight", "shape": [ 5632, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 11534336 }, { "name": "model.layers.9.self_attn.c_attn.bias", "shape": [ 3072 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 11536384 }, { "name": "model.layers.9.self_attn.c_attn.weight", "shape": [ 3072, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 11542528 }, { "name": "model.layers.9.self_attn.o_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 17833984 }, { "name": "model.norm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 19931136 } ], "md5sum": "31f107dcd7122933055d18604f4a83e9" } ] }