{ "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": "float32", "format": "f32-to-bf16", "nbytes": 272269312, "byteOffset": 0 } ], "md5sum": "5497790ce65a77668527f0598dc80b83" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 29826560, "records": [ { "name": "model.layers.0.input_layernorm.weight", "shape": [ 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1792, "byteOffset": 0 }, { "name": "model.layers.0.mlp.down_proj.weight", "shape": [ 896, 4864 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8716288, "byteOffset": 1792 }, { "name": "model.layers.0.mlp.gate_up_proj.weight", "shape": [ 9728, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 17432576, "byteOffset": 8718080 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1792, "byteOffset": 26150656 }, { "name": "model.layers.0.self_attn.c_attn.bias", "shape": [ 1152 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 26152448 }, { "name": "model.layers.0.self_attn.c_attn.weight", "shape": [ 1152, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2064384, "byteOffset": 26154752 }, { "name": "model.layers.0.self_attn.o_proj.weight", "shape": [ 896, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 28219136 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1792, "byteOffset": 29824768 } ], "md5sum": "4ce1a6469b248366023676adc0af8ca1" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 29824768, "records": [ { "name": "model.layers.1.mlp.down_proj.weight", "shape": [ 896, 4864 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8716288, "byteOffset": 0 }, { "name": "model.layers.1.mlp.gate_up_proj.weight", "shape": [ 9728, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 17432576, "byteOffset": 8716288 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1792, "byteOffset": 26148864 }, { "name": "model.layers.1.self_attn.c_attn.bias", "shape": [ 1152 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 26150656 }, { "name": "model.layers.1.self_attn.c_attn.weight", "shape": [ 1152, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2064384, "byteOffset": 26152960 }, { "name": "model.layers.1.self_attn.o_proj.weight", "shape": [ 896, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 28217344 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1792, "byteOffset": 29822976 } ], "md5sum": "ac5eb00b6d372f9aee3ceb30777900a8" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 29824768, "records": [ { "name": "model.layers.10.mlp.down_proj.weight", "shape": [ 896, 4864 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8716288, "byteOffset": 0 }, { "name": "model.layers.10.mlp.gate_up_proj.weight", "shape": [ 9728, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 17432576, "byteOffset": 8716288 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1792, "byteOffset": 26148864 }, { "name": "model.layers.10.self_attn.c_attn.bias", "shape": [ 1152 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 26150656 }, { "name": "model.layers.10.self_attn.c_attn.weight", "shape": [ 1152, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2064384, "byteOffset": 26152960 }, { "name": "model.layers.10.self_attn.o_proj.weight", "shape": [ 896, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 28217344 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1792, "byteOffset": 29822976 } ], "md5sum": "a6b7ee08d96af58ff914ac16ca7283e2" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 29824768, "records": [ { "name": "model.layers.11.mlp.down_proj.weight", "shape": [ 896, 4864 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8716288, "byteOffset": 0 }, { "name": "model.layers.11.mlp.gate_up_proj.weight", "shape": [ 9728, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 17432576, "byteOffset": 8716288 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1792, "byteOffset": 26148864 }, { "name": "model.layers.11.self_attn.c_attn.bias", "shape": [ 1152 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 26150656 }, { "name": "model.layers.11.self_attn.c_attn.weight", "shape": [ 1152, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2064384, "byteOffset": 26152960 }, { "name": "model.layers.11.self_attn.o_proj.weight", "shape": [ 896, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 28217344 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1792, "byteOffset": 29822976 } ], "md5sum": "840e9ede04f79dcfd6ba64822b08a753" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 29824768, "records": [ { "name": "model.layers.12.mlp.down_proj.weight", "shape": [ 896, 4864 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8716288, "byteOffset": 0 }, { "name": "model.layers.12.mlp.gate_up_proj.weight", "shape": [ 9728, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 17432576, "byteOffset": 8716288 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1792, "byteOffset": 26148864 }, { "name": "model.layers.12.self_attn.c_attn.bias", "shape": [ 1152 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 26150656 }, { "name": "model.layers.12.self_attn.c_attn.weight", "shape": [ 1152, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2064384, "byteOffset": 26152960 }, { "name": "model.layers.12.self_attn.o_proj.weight", "shape": [ 896, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 28217344 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1792, "byteOffset": 29822976 } ], "md5sum": "cb4763f17c8a57b2448c9fc2a155017f" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 29824768, "records": [ { "name": "model.layers.13.mlp.down_proj.weight", "shape": [ 896, 4864 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8716288, "byteOffset": 0 }, { "name": "model.layers.13.mlp.gate_up_proj.weight", "shape": [ 9728, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 17432576, "byteOffset": 8716288 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1792, "byteOffset": 26148864 }, { "name": "model.layers.13.self_attn.c_attn.bias", "shape": [ 1152 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 26150656 }, { "name": "model.layers.13.self_attn.c_attn.weight", "shape": [ 1152, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2064384, "byteOffset": 26152960 }, { "name": "model.layers.13.self_attn.o_proj.weight", "shape": [ 896, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 28217344 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1792, "byteOffset": 29822976 } ], "md5sum": "1b2c16f565dba1c9caed8d8581c6b40c" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 29824768, "records": [ { "name": "model.layers.14.mlp.down_proj.weight", "shape": [ 896, 4864 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8716288, "byteOffset": 0 }, { "name": "model.layers.14.mlp.gate_up_proj.weight", "shape": [ 9728, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 17432576, "byteOffset": 8716288 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1792, "byteOffset": 26148864 }, { "name": "model.layers.14.self_attn.c_attn.bias", "shape": [ 1152 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 26150656 }, { "name": "model.layers.14.self_attn.c_attn.weight", "shape": [ 1152, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2064384, "byteOffset": 26152960 }, { "name": "model.layers.14.self_attn.o_proj.weight", "shape": [ 896, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 28217344 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1792, "byteOffset": 29822976 } ], "md5sum": "dadf2926023fdd42a83aa1641c4a9bf1" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 29824768, "records": [ { "name": "model.layers.15.mlp.down_proj.weight", "shape": [ 896, 4864 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8716288, "byteOffset": 0 }, { "name": "model.layers.15.mlp.gate_up_proj.weight", "shape": [ 9728, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 17432576, "byteOffset": 8716288 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1792, "byteOffset": 26148864 }, { "name": "model.layers.15.self_attn.c_attn.bias", "shape": [ 1152 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 26150656 }, { "name": "model.layers.15.self_attn.c_attn.weight", "shape": [ 1152, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2064384, "byteOffset": 26152960 }, { "name": "model.layers.15.self_attn.o_proj.weight", "shape": [ 896, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 28217344 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1792, "byteOffset": 29822976 } ], "md5sum": "e50bb7f71796e95f5706b2c058387c29" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 29824768, "records": [ { "name": "model.layers.16.mlp.down_proj.weight", "shape": [ 896, 4864 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8716288, "byteOffset": 0 }, { "name": "model.layers.16.mlp.gate_up_proj.weight", "shape": [ 9728, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 17432576, "byteOffset": 8716288 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1792, "byteOffset": 26148864 }, { "name": "model.layers.16.self_attn.c_attn.bias", "shape": [ 1152 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 26150656 }, { "name": "model.layers.16.self_attn.c_attn.weight", "shape": [ 1152, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2064384, "byteOffset": 26152960 }, { "name": "model.layers.16.self_attn.o_proj.weight", "shape": [ 896, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 28217344 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1792, "byteOffset": 29822976 } ], "md5sum": "bc6e53484efcfc27bafde4debc199984" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 29824768, "records": [ { "name": "model.layers.17.mlp.down_proj.weight", "shape": [ 896, 4864 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8716288, "byteOffset": 0 }, { "name": "model.layers.17.mlp.gate_up_proj.weight", "shape": [ 9728, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 17432576, "byteOffset": 8716288 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1792, "byteOffset": 26148864 }, { "name": "model.layers.17.self_attn.c_attn.bias", "shape": [ 1152 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 26150656 }, { "name": "model.layers.17.self_attn.c_attn.weight", "shape": [ 1152, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2064384, "byteOffset": 26152960 }, { "name": "model.layers.17.self_attn.o_proj.weight", "shape": [ 896, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 28217344 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1792, "byteOffset": 29822976 } ], "md5sum": "b3031056fa2ebb9e1652956bb831c364" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 29824768, "records": [ { "name": "model.layers.18.mlp.down_proj.weight", "shape": [ 896, 4864 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8716288, "byteOffset": 0 }, { "name": "model.layers.18.mlp.gate_up_proj.weight", "shape": [ 9728, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 17432576, "byteOffset": 8716288 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1792, "byteOffset": 26148864 }, { "name": "model.layers.18.self_attn.c_attn.bias", "shape": [ 1152 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 26150656 }, { "name": "model.layers.18.self_attn.c_attn.weight", "shape": [ 1152, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2064384, "byteOffset": 26152960 }, { "name": "model.layers.18.self_attn.o_proj.weight", "shape": [ 896, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 28217344 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1792, "byteOffset": 29822976 } ], "md5sum": "b146bc540a5f75218c8c2b8ab7e3641d" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 29824768, "records": [ { "name": "model.layers.19.mlp.down_proj.weight", "shape": [ 896, 4864 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8716288, "byteOffset": 0 }, { "name": "model.layers.19.mlp.gate_up_proj.weight", "shape": [ 9728, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 17432576, "byteOffset": 8716288 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1792, "byteOffset": 26148864 }, { "name": "model.layers.19.self_attn.c_attn.bias", "shape": [ 1152 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 26150656 }, { "name": "model.layers.19.self_attn.c_attn.weight", "shape": [ 1152, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2064384, "byteOffset": 26152960 }, { "name": "model.layers.19.self_attn.o_proj.weight", "shape": [ 896, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 28217344 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1792, "byteOffset": 29822976 } ], "md5sum": "9594cd1a20c5be6e75188e616bd2a420" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 29824768, "records": [ { "name": "model.layers.2.mlp.down_proj.weight", "shape": [ 896, 4864 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8716288, "byteOffset": 0 }, { "name": "model.layers.2.mlp.gate_up_proj.weight", "shape": [ 9728, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 17432576, "byteOffset": 8716288 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1792, "byteOffset": 26148864 }, { "name": "model.layers.2.self_attn.c_attn.bias", "shape": [ 1152 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 26150656 }, { "name": "model.layers.2.self_attn.c_attn.weight", "shape": [ 1152, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2064384, "byteOffset": 26152960 }, { "name": "model.layers.2.self_attn.o_proj.weight", "shape": [ 896, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 28217344 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1792, "byteOffset": 29822976 } ], "md5sum": "e6370baa5c8fee507980a855afec4df4" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 29824768, "records": [ { "name": "model.layers.20.mlp.down_proj.weight", "shape": [ 896, 4864 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8716288, "byteOffset": 0 }, { "name": "model.layers.20.mlp.gate_up_proj.weight", "shape": [ 9728, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 17432576, "byteOffset": 8716288 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1792, "byteOffset": 26148864 }, { "name": "model.layers.20.self_attn.c_attn.bias", "shape": [ 1152 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 26150656 }, { "name": "model.layers.20.self_attn.c_attn.weight", "shape": [ 1152, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2064384, "byteOffset": 26152960 }, { "name": "model.layers.20.self_attn.o_proj.weight", "shape": [ 896, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 28217344 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1792, "byteOffset": 29822976 } ], "md5sum": "aea247ef96b1c9fc5e6fef092f2684b7" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 29824768, "records": [ { "name": "model.layers.21.mlp.down_proj.weight", "shape": [ 896, 4864 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8716288, "byteOffset": 0 }, { "name": "model.layers.21.mlp.gate_up_proj.weight", "shape": [ 9728, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 17432576, "byteOffset": 8716288 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1792, "byteOffset": 26148864 }, { "name": "model.layers.21.self_attn.c_attn.bias", "shape": [ 1152 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 26150656 }, { "name": "model.layers.21.self_attn.c_attn.weight", "shape": [ 1152, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2064384, "byteOffset": 26152960 }, { "name": "model.layers.21.self_attn.o_proj.weight", "shape": [ 896, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 28217344 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1792, "byteOffset": 29822976 } ], "md5sum": "d88a2711e4d47f58ff8f1e12eeaa70e1" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 29824768, "records": [ { "name": "model.layers.22.mlp.down_proj.weight", "shape": [ 896, 4864 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8716288, "byteOffset": 0 }, { "name": "model.layers.22.mlp.gate_up_proj.weight", "shape": [ 9728, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 17432576, "byteOffset": 8716288 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1792, "byteOffset": 26148864 }, { "name": "model.layers.22.self_attn.c_attn.bias", "shape": [ 1152 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 26150656 }, { "name": "model.layers.22.self_attn.c_attn.weight", "shape": [ 1152, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2064384, "byteOffset": 26152960 }, { "name": "model.layers.22.self_attn.o_proj.weight", "shape": [ 896, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 28217344 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1792, "byteOffset": 29822976 } ], "md5sum": "f057b7a66ce275a711349da87c1bf8b1" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 29824768, "records": [ { "name": "model.layers.23.mlp.down_proj.weight", "shape": [ 896, 4864 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8716288, "byteOffset": 0 }, { "name": "model.layers.23.mlp.gate_up_proj.weight", "shape": [ 9728, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 17432576, "byteOffset": 8716288 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1792, "byteOffset": 26148864 }, { "name": "model.layers.23.self_attn.c_attn.bias", "shape": [ 1152 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 26150656 }, { "name": "model.layers.23.self_attn.c_attn.weight", "shape": [ 1152, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2064384, "byteOffset": 26152960 }, { "name": "model.layers.23.self_attn.o_proj.weight", "shape": [ 896, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 28217344 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1792, "byteOffset": 29822976 } ], "md5sum": "8fdcc01e5cff8b11c60b963a75bd2ce9" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 29824768, "records": [ { "name": "model.layers.3.mlp.down_proj.weight", "shape": [ 896, 4864 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8716288, "byteOffset": 0 }, { "name": "model.layers.3.mlp.gate_up_proj.weight", "shape": [ 9728, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 17432576, "byteOffset": 8716288 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1792, "byteOffset": 26148864 }, { "name": "model.layers.3.self_attn.c_attn.bias", "shape": [ 1152 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 26150656 }, { "name": "model.layers.3.self_attn.c_attn.weight", "shape": [ 1152, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2064384, "byteOffset": 26152960 }, { "name": "model.layers.3.self_attn.o_proj.weight", "shape": [ 896, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 28217344 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1792, "byteOffset": 29822976 } ], "md5sum": "b903944946d48b12ccc0425eda211f9c" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 29824768, "records": [ { "name": "model.layers.4.mlp.down_proj.weight", "shape": [ 896, 4864 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8716288, "byteOffset": 0 }, { "name": "model.layers.4.mlp.gate_up_proj.weight", "shape": [ 9728, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 17432576, "byteOffset": 8716288 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1792, "byteOffset": 26148864 }, { "name": "model.layers.4.self_attn.c_attn.bias", "shape": [ 1152 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 26150656 }, { "name": "model.layers.4.self_attn.c_attn.weight", "shape": [ 1152, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2064384, "byteOffset": 26152960 }, { "name": "model.layers.4.self_attn.o_proj.weight", "shape": [ 896, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 28217344 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1792, "byteOffset": 29822976 } ], "md5sum": "77ac32a5eebff91823a5a2eee5154ec7" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 29824768, "records": [ { "name": "model.layers.5.mlp.down_proj.weight", "shape": [ 896, 4864 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8716288, "byteOffset": 0 }, { "name": "model.layers.5.mlp.gate_up_proj.weight", "shape": [ 9728, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 17432576, "byteOffset": 8716288 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1792, "byteOffset": 26148864 }, { "name": "model.layers.5.self_attn.c_attn.bias", "shape": [ 1152 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 26150656 }, { "name": "model.layers.5.self_attn.c_attn.weight", "shape": [ 1152, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2064384, "byteOffset": 26152960 }, { "name": "model.layers.5.self_attn.o_proj.weight", "shape": [ 896, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 28217344 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1792, "byteOffset": 29822976 } ], "md5sum": "9eb10ab54ce1f25226784e534725090d" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 29824768, "records": [ { "name": "model.layers.6.mlp.down_proj.weight", "shape": [ 896, 4864 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8716288, "byteOffset": 0 }, { "name": "model.layers.6.mlp.gate_up_proj.weight", "shape": [ 9728, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 17432576, "byteOffset": 8716288 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1792, "byteOffset": 26148864 }, { "name": "model.layers.6.self_attn.c_attn.bias", "shape": [ 1152 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 26150656 }, { "name": "model.layers.6.self_attn.c_attn.weight", "shape": [ 1152, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2064384, "byteOffset": 26152960 }, { "name": "model.layers.6.self_attn.o_proj.weight", "shape": [ 896, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 28217344 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1792, "byteOffset": 29822976 } ], "md5sum": "0483ff1fe735d6b7cf22bf39cc8d147e" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 29824768, "records": [ { "name": "model.layers.7.mlp.down_proj.weight", "shape": [ 896, 4864 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8716288, "byteOffset": 0 }, { "name": "model.layers.7.mlp.gate_up_proj.weight", "shape": [ 9728, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 17432576, "byteOffset": 8716288 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1792, "byteOffset": 26148864 }, { "name": "model.layers.7.self_attn.c_attn.bias", "shape": [ 1152 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 26150656 }, { "name": "model.layers.7.self_attn.c_attn.weight", "shape": [ 1152, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2064384, "byteOffset": 26152960 }, { "name": "model.layers.7.self_attn.o_proj.weight", "shape": [ 896, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 28217344 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1792, "byteOffset": 29822976 } ], "md5sum": "e2c379b3900cc954e737c8f39e093cde" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 29824768, "records": [ { "name": "model.layers.8.mlp.down_proj.weight", "shape": [ 896, 4864 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8716288, "byteOffset": 0 }, { "name": "model.layers.8.mlp.gate_up_proj.weight", "shape": [ 9728, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 17432576, "byteOffset": 8716288 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1792, "byteOffset": 26148864 }, { "name": "model.layers.8.self_attn.c_attn.bias", "shape": [ 1152 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 26150656 }, { "name": "model.layers.8.self_attn.c_attn.weight", "shape": [ 1152, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2064384, "byteOffset": 26152960 }, { "name": "model.layers.8.self_attn.o_proj.weight", "shape": [ 896, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 28217344 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1792, "byteOffset": 29822976 } ], "md5sum": "6610c55af35cfa9f0bcdce51bb040cd0" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 29824768, "records": [ { "name": "model.layers.9.mlp.down_proj.weight", "shape": [ 896, 4864 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8716288, "byteOffset": 0 }, { "name": "model.layers.9.mlp.gate_up_proj.weight", "shape": [ 9728, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 17432576, "byteOffset": 8716288 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1792, "byteOffset": 26148864 }, { "name": "model.layers.9.self_attn.c_attn.bias", "shape": [ 1152 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2304, "byteOffset": 26150656 }, { "name": "model.layers.9.self_attn.c_attn.weight", "shape": [ 1152, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2064384, "byteOffset": 26152960 }, { "name": "model.layers.9.self_attn.o_proj.weight", "shape": [ 896, 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 28217344 }, { "name": "model.norm.weight", "shape": [ 896 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1792, "byteOffset": 29822976 } ], "md5sum": "e5959cea04c6f0e736bbdfb004f62f3d" } ] }