{ "metadata": { "ParamSize": 146, "ParamBytes": 6845505536.0, "BitsPerParam": 32.0 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 201326592, "records": [ { "name": "model.embed_tokens.weight", "shape": [ 49152, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 201326592, "byteOffset": 0 } ], "md5sum": "619fe00f8a1db3dd69bd2250a99077ba" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.0.mlp.down_proj.weight", "shape": [ 2048, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "81e4c76100cf1b77e061a9a1f476aadf" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 67108864, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.weight", "shape": [ 16384, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 67108864, "byteOffset": 0 } ], "md5sum": "d2249e4d7947b83c61a919e030d90338" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 25174016, "records": [ { "name": "model.layers.0.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 0 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 4096 }, { "name": "model.layers.0.self_attn.qkv_proj.weight", "shape": [ 6144, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 8192 } ], "md5sum": "2a4ce8c6302659da01ae3203451d37d6" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.1.mlp.down_proj.weight", "shape": [ 2048, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "b5338da21b5355ddc0564392fff8a104" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 67108864, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.weight", "shape": [ 16384, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 67108864, "byteOffset": 0 } ], "md5sum": "000320cdf280cb1647d056b7f732da8c" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.1.self_attn.qkv_proj.weight", "shape": [ 6144, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "02d4e122f37b0caac96d2218b307ef6f" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.10.mlp.down_proj.weight", "shape": [ 2048, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "c412a943b69067c9964903811cbbb111" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 67108864, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.weight", "shape": [ 16384, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 67108864, "byteOffset": 0 } ], "md5sum": "a7ba87e71e5603a6f89e86ca45df9397" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.10.self_attn.qkv_proj.weight", "shape": [ 6144, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "ef93cb0a6db251ac455eea80a34ea7d1" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.11.mlp.down_proj.weight", "shape": [ 2048, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "af2a85fa90291b1e1c9fbac91feda80b" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 67108864, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.weight", "shape": [ 16384, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 67108864, "byteOffset": 0 } ], "md5sum": "1bced4da21c4097ed2478b10a625a82b" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.11.self_attn.qkv_proj.weight", "shape": [ 6144, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "6d86f6f1cd819755d5634cf5388d0735" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 25190400, "records": [ { "name": "model.layers.0.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8388608 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8392704 }, { "name": "model.layers.1.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 8396800 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 16785408 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 16789504 }, { "name": "model.layers.10.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 16793600 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 25182208 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 25186304 } ], "md5sum": "37f08fc7ff618c01711143a42c40e09a" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.12.mlp.down_proj.weight", "shape": [ 2048, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "f7e8121029e8fd577026105e250d89f7" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 67108864, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.weight", "shape": [ 16384, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 67108864, "byteOffset": 0 } ], "md5sum": "d30f936f8c5457b48674d6bbf3076f39" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.12.self_attn.qkv_proj.weight", "shape": [ 6144, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "23482a45c483351937182e20a14159e6" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.13.mlp.down_proj.weight", "shape": [ 2048, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "f36f8ceb44d1e86adc4efe3a69b52d34" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 67108864, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.weight", "shape": [ 16384, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 67108864, "byteOffset": 0 } ], "md5sum": "cc664f1de429c6fbae41a7451b3e6d4c" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.13.self_attn.qkv_proj.weight", "shape": [ 6144, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "7a9369a83b9cd3dd9aa53ec502465831" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.14.mlp.down_proj.weight", "shape": [ 2048, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "363f6200f9a39eaf36d33546ab083b5d" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 67108864, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.weight", "shape": [ 16384, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 67108864, "byteOffset": 0 } ], "md5sum": "986c46c83143a3b454302005f4a9816c" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.14.self_attn.qkv_proj.weight", "shape": [ 6144, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "68e129bee2c7b84eceeb554389ef1311" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 25190400, "records": [ { "name": "model.layers.11.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8388608 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8392704 }, { "name": "model.layers.12.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 8396800 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 16785408 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 16789504 }, { "name": "model.layers.13.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 16793600 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 25182208 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 25186304 } ], "md5sum": "e3b2be73a4762ff5da34eee7f66bd2a9" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.15.mlp.down_proj.weight", "shape": [ 2048, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "fc79b5298517b9a39471bed9819bf007" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 67108864, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.weight", "shape": [ 16384, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 67108864, "byteOffset": 0 } ], "md5sum": "5b8711110d4c65a3f585d964c04c22fc" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.15.self_attn.qkv_proj.weight", "shape": [ 6144, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "e944415e6931dcab3cbc94c392e60322" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.16.mlp.down_proj.weight", "shape": [ 2048, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "c6b51114c5848b698a35735574ee919c" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 67108864, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.weight", "shape": [ 16384, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 67108864, "byteOffset": 0 } ], "md5sum": "a601b8ea458507db61b521b04f3c67cc" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.16.self_attn.qkv_proj.weight", "shape": [ 6144, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "b2387bd7192f173c102a634bd66f8fca" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.17.mlp.down_proj.weight", "shape": [ 2048, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "366d0df060ba655fea3051d4768cd22b" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 67108864, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.weight", "shape": [ 16384, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 67108864, "byteOffset": 0 } ], "md5sum": "71b16a66c85387a6ca619106c248b1fc" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.17.self_attn.qkv_proj.weight", "shape": [ 6144, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "4f722a08d5b0dc010f09c307163ae3c8" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 25190400, "records": [ { "name": "model.layers.14.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8388608 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8392704 }, { "name": "model.layers.15.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 8396800 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 16785408 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 16789504 }, { "name": "model.layers.16.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 16793600 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 25182208 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 25186304 } ], "md5sum": "7d62377efb35fa0f32eca64757bfd2af" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.18.mlp.down_proj.weight", "shape": [ 2048, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "38c2521c49164523487a40214689edcf" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 67108864, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.weight", "shape": [ 16384, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 67108864, "byteOffset": 0 } ], "md5sum": "f6fc5a9df85d426a962665926e696f0e" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.18.self_attn.qkv_proj.weight", "shape": [ 6144, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "beb16e6cf3213adbf92954df659ed450" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.19.mlp.down_proj.weight", "shape": [ 2048, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "7f1dfe0a5f2f9a1568139c206fc17200" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 67108864, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.weight", "shape": [ 16384, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 67108864, "byteOffset": 0 } ], "md5sum": "0faa5983b21cc65140dd3495d2450a38" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.19.self_attn.qkv_proj.weight", "shape": [ 6144, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "772ba89541d24fd423ce6c91c5611f84" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.2.mlp.down_proj.weight", "shape": [ 2048, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "a6c6fa74b14dfb4c615202394ae2643a" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 67108864, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.weight", "shape": [ 16384, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 67108864, "byteOffset": 0 } ], "md5sum": "180bfaeea4861883d53b72d2228e6ad2" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.2.self_attn.qkv_proj.weight", "shape": [ 6144, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "1465833e13e689b3c7febb6fde43b5f9" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 25190400, "records": [ { "name": "model.layers.17.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8388608 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8392704 }, { "name": "model.layers.18.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 8396800 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 16785408 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 16789504 }, { "name": "model.layers.19.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 16793600 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 25182208 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 25186304 } ], "md5sum": "6131631fd7d7b37e38b28bf9db0c1da6" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.20.mlp.down_proj.weight", "shape": [ 2048, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "a334ee83aa48ce779170a19e4d11f312" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 67108864, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.weight", "shape": [ 16384, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 67108864, "byteOffset": 0 } ], "md5sum": "8896f3caf4c2dc0197206afeb8fed244" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.20.self_attn.qkv_proj.weight", "shape": [ 6144, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "a3826936cf5440035a9d758b92d1bb82" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.21.mlp.down_proj.weight", "shape": [ 2048, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "1e6b71a6f4506e990731403d87d85a64" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 67108864, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.weight", "shape": [ 16384, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 67108864, "byteOffset": 0 } ], "md5sum": "2da1fb003dcd8d19a86235c7b8575e3d" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.21.self_attn.qkv_proj.weight", "shape": [ 6144, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "bf850c6bd34bd1421fd54a5de3404a6e" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.22.mlp.down_proj.weight", "shape": [ 2048, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "b101a58f8019037525434d20584d2e9d" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 67108864, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.weight", "shape": [ 16384, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 67108864, "byteOffset": 0 } ], "md5sum": "78752ba30ad62b220ed633bf33b84188" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.22.self_attn.qkv_proj.weight", "shape": [ 6144, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "487079701a7bcaccb6cf16f557799ee3" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 25190400, "records": [ { "name": "model.layers.2.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8388608 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8392704 }, { "name": "model.layers.20.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 8396800 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 16785408 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 16789504 }, { "name": "model.layers.21.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 16793600 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 25182208 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 25186304 } ], "md5sum": "7a5a5287ddde4a53d29ab2388929ba1c" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.23.mlp.down_proj.weight", "shape": [ 2048, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "809feb3d0cae9357c081a201d6b73f84" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 67108864, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.weight", "shape": [ 16384, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 67108864, "byteOffset": 0 } ], "md5sum": "bf33b5db242f3272120a1af2c3dc07e1" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.23.self_attn.qkv_proj.weight", "shape": [ 6144, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "7dab76575a38d819a89f95d9ef16cd6d" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.3.mlp.down_proj.weight", "shape": [ 2048, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "bf21269950f29424fd677f2bf275b0e4" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 67108864, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.weight", "shape": [ 16384, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 67108864, "byteOffset": 0 } ], "md5sum": "0ca7c97d1783bbcf657c64aa57b3a9ce" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.3.self_attn.qkv_proj.weight", "shape": [ 6144, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "1a4ff49d66479edbb83d7c752cd995e1" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.4.mlp.down_proj.weight", "shape": [ 2048, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "b0dc04c436342870b9b62c250e8f13fc" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 67108864, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.weight", "shape": [ 16384, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 67108864, "byteOffset": 0 } ], "md5sum": "102b6c29f6d72a2a7d3490f6dc9d0c4e" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.4.self_attn.qkv_proj.weight", "shape": [ 6144, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "0f8ca420c538f726c2fd057568ed36ea" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 25190400, "records": [ { "name": "model.layers.22.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8388608 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8392704 }, { "name": "model.layers.23.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 8396800 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 16785408 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 16789504 }, { "name": "model.layers.3.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 16793600 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 25182208 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 25186304 } ], "md5sum": "321e676fd086cc519dde06569fb88514" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.5.mlp.down_proj.weight", "shape": [ 2048, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "ba8a2c1e2d224f9479198bb052d58a77" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 67108864, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.weight", "shape": [ 16384, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 67108864, "byteOffset": 0 } ], "md5sum": "c7cd8a0de6c8e1e07dafcc8040dae8e6" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.5.self_attn.qkv_proj.weight", "shape": [ 6144, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "816cde6d38527ca799b3721481d6276f" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.6.mlp.down_proj.weight", "shape": [ 2048, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "2f337d1620bf04e2e59cbf4f6d1aba00" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 67108864, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.weight", "shape": [ 16384, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 67108864, "byteOffset": 0 } ], "md5sum": "584689d4ab51bc7bdac5c631fee70bc5" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.6.self_attn.qkv_proj.weight", "shape": [ 6144, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "1c6c2c40d3678f690d5ba14b7f205be6" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.7.mlp.down_proj.weight", "shape": [ 2048, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "21348afae5381b780f5c733967037dc4" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 67108864, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.weight", "shape": [ 16384, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 67108864, "byteOffset": 0 } ], "md5sum": "79402d2ad9f31ba5a4afbc378768bd6a" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.7.self_attn.qkv_proj.weight", "shape": [ 6144, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "2c8379e0f3a48cadd4fc72733bb03513" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 25190400, "records": [ { "name": "model.layers.4.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8388608 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8392704 }, { "name": "model.layers.5.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 8396800 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 16785408 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 16789504 }, { "name": "model.layers.6.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 16793600 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 25182208 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 25186304 } ], "md5sum": "c03250857914fb5416b9f92e96495a9e" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.8.mlp.down_proj.weight", "shape": [ 2048, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "1ca61427d8c66ee09d07305777b5578a" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 67108864, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.weight", "shape": [ 16384, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 67108864, "byteOffset": 0 } ], "md5sum": "0f5c4845da1b952268136ae2fdc5d489" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.8.self_attn.qkv_proj.weight", "shape": [ 6144, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "b318478646711f9bed797b29c9786a96" }, { "dataPath": "params_shard_77.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.9.mlp.down_proj.weight", "shape": [ 2048, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "d6e4aeea77763a47221f7aa7ec01ae33" }, { "dataPath": "params_shard_78.bin", "format": "raw-shard", "nbytes": 67108864, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.weight", "shape": [ 16384, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 67108864, "byteOffset": 0 } ], "md5sum": "ff4a581febe252d1f5b775d312169f61" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.9.self_attn.qkv_proj.weight", "shape": [ 6144, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "82ec445f48189fc071404b4df5251344" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 25186304, "records": [ { "name": "model.layers.7.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8388608 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8392704 }, { "name": "model.layers.8.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 8396800 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 16785408 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 16789504 }, { "name": "model.layers.9.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 16793600 }, { "name": "model.norm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 25182208 } ], "md5sum": "5559809f78b993208347a1c8869fb722" } ] }