{ "metadata": { "ParamSize": 325, "ParamBytes": 4526981120.0, "BitsPerParam": 5.000992646497372 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "lm_head.q_weight", "shape": [ 32000, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "104172733e8585b1878e827612f1d296" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "raw", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "8eaa58f8db6c5fd05338d6bf0f1052c2" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "e8cb546c64f7d9fa3a8a2838c3f8053e" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 23740416, "records": [ { "name": "lm_head.q_scale", "shape": [ 32000, 128 ], "dtype": "float32", "format": "raw", "nbytes": 16384000, "byteOffset": 0 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 16384000 }, { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float32", "format": "raw", "nbytes": 7340032, "byteOffset": 16400384 } ], "md5sum": "56bf1d4d2c90a92f3408544afc15ad7d" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "raw", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "ecdd3738e8deab2a7863de68fe87fbb0" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "0c5ec0a15660f8514797f92d00ab873f" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 22052864, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float32", "format": "raw", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 14696448 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float32", "format": "raw", "nbytes": 7340032, "byteOffset": 14712832 } ], "md5sum": "d72ee9aba7666c6fd6049ceb5ce6fd0c" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 30425088, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float32", "format": "raw", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.23.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 12582912, "byteOffset": 14696448 }, { "name": "model.layers.23.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float32", "format": "raw", "nbytes": 3145728, "byteOffset": 27279360 } ], "md5sum": "10ea144a4f42bded472d44a55299a272" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "raw", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "046cd9ec9fcb5b368a546b22430a9140" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "e6f9d15a5ceb50c7077b5d593e781978" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 32538624, "records": [ { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 8388608 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 10485760 }, { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float32", "format": "raw", "nbytes": 7340032, "byteOffset": 10502144 }, { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float32", "format": "raw", "nbytes": 14680064, "byteOffset": 17842176 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 32522240 } ], "md5sum": "adaa15ab7e99ac434a7c747764b2d747" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "raw", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "1a177d0eb28b3929d4163f972046139e" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 26230784, "records": [ { "name": "model.layers.24.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.24.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float32", "format": "raw", "nbytes": 3145728, "byteOffset": 12582912 }, { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 15728640 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 24117248 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 26214400 } ], "md5sum": "8df51f55f4ab02acdafdd6eb43352d7b" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "b27066f144d03a0141f20ce4761135c0" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 22036480, "records": [ { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float32", "format": "raw", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float32", "format": "raw", "nbytes": 14680064, "byteOffset": 7340032 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 22020096 } ], "md5sum": "a602153d5564f246b96b15dcd5f86ae0" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "raw", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "cd36cd869ec57edd7eb5d14604323081" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 26230784, "records": [ { "name": "model.layers.25.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.25.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float32", "format": "raw", "nbytes": 3145728, "byteOffset": 12582912 }, { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 15728640 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 24117248 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 26214400 } ], "md5sum": "38b2f4f6584a879644fd3b0e8b11201c" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "11ad1f3c2f8cf55620fcdb24e853045c" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 22036480, "records": [ { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float32", "format": "raw", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float32", "format": "raw", "nbytes": 14680064, "byteOffset": 7340032 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 22020096 } ], "md5sum": "57c9b13295acd0c6f77a39cf16a94b7f" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "raw", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "f30023dab5b99e2d734a857057b1f222" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 26230784, "records": [ { "name": "model.layers.26.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.26.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float32", "format": "raw", "nbytes": 3145728, "byteOffset": 12582912 }, { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 15728640 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 24117248 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 26214400 } ], "md5sum": "e4dc849a967bcf914540545376c55d5a" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "af4f167db2deeb1e442ef07b6625b20b" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 22036480, "records": [ { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float32", "format": "raw", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float32", "format": "raw", "nbytes": 14680064, "byteOffset": 7340032 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 22020096 } ], "md5sum": "a01cfd7756a98569026687478b775cda" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.28.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "raw", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "f6ac5a7caa3b34cc9aae74e407e10bbf" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 26230784, "records": [ { "name": "model.layers.27.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.27.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float32", "format": "raw", "nbytes": 3145728, "byteOffset": 12582912 }, { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 15728640 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 24117248 }, { "name": "model.layers.28.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 26214400 } ], "md5sum": "9296806cfee1800c53ccd1b7f5a1b8a0" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "2e36015d5459b58187c800e56dbc9e2a" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 22036480, "records": [ { "name": "model.layers.28.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float32", "format": "raw", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.28.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float32", "format": "raw", "nbytes": 14680064, "byteOffset": 7340032 }, { "name": "model.layers.28.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 22020096 } ], "md5sum": "c6128a0482838c02cee135bf21fe524b" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.29.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "raw", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "c435571de9c736ebb3953d2360890d7a" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 26230784, "records": [ { "name": "model.layers.28.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.28.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float32", "format": "raw", "nbytes": 3145728, "byteOffset": 12582912 }, { "name": "model.layers.28.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 15728640 }, { "name": "model.layers.28.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 24117248 }, { "name": "model.layers.29.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 26214400 } ], "md5sum": "1b3603ea995acd8aa037789380c2c098" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "ce6139e74d562ca5607c37f84a2de784" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 22036480, "records": [ { "name": "model.layers.29.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float32", "format": "raw", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.29.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float32", "format": "raw", "nbytes": 14680064, "byteOffset": 7340032 }, { "name": "model.layers.29.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 22020096 } ], "md5sum": "a01d09021de35fd0c771f21f92ccbc45" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.30.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "raw", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "a0fcca24b6b01ec09ad45a5df02377c1" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 26230784, "records": [ { "name": "model.layers.29.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.29.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float32", "format": "raw", "nbytes": 3145728, "byteOffset": 12582912 }, { "name": "model.layers.29.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 15728640 }, { "name": "model.layers.29.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 24117248 }, { "name": "model.layers.30.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 26214400 } ], "md5sum": "079b6c99ecdbc8f606824393a9e73909" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "9210ff19eaa29fa2ee82a3299082b073" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 22036480, "records": [ { "name": "model.layers.30.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float32", "format": "raw", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.30.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float32", "format": "raw", "nbytes": 14680064, "byteOffset": 7340032 }, { "name": "model.layers.30.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 22020096 } ], "md5sum": "81b28f60c04a7b41d9c1cd3567ac8af3" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.31.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "raw", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "654849955848b8440882beffdb429438" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 26230784, "records": [ { "name": "model.layers.30.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.30.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float32", "format": "raw", "nbytes": 3145728, "byteOffset": 12582912 }, { "name": "model.layers.30.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 15728640 }, { "name": "model.layers.30.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 24117248 }, { "name": "model.layers.31.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 26214400 } ], "md5sum": "5bf1ea661d1300056c41ac922ebcbd58" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "dd51f49cd88383ad5f4f0ec23b6433f5" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 22036480, "records": [ { "name": "model.layers.31.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float32", "format": "raw", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.31.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float32", "format": "raw", "nbytes": 14680064, "byteOffset": 7340032 }, { "name": "model.layers.31.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 22020096 } ], "md5sum": "9d5961705348147beeaf2b07172f7eaa" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 32000, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "4b4c2ca48a40051df7b808d600fe2b64" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 26230784, "records": [ { "name": "model.layers.31.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.31.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float32", "format": "raw", "nbytes": 3145728, "byteOffset": 12582912 }, { "name": "model.layers.31.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 15728640 }, { "name": "model.layers.31.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 24117248 }, { "name": "model.norm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 26214400 } ], "md5sum": "c91e461e5c74323c4a643acb8bf0a663" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "raw", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "87f1341a63028ca0af5a5135498c32e4" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "d61aef33770b3950ebf8c0da59051001" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 23740416, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 32000, 128 ], "dtype": "float32", "format": "raw", "nbytes": 16384000, "byteOffset": 0 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 16384000 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float32", "format": "raw", "nbytes": 7340032, "byteOffset": 16400384 } ], "md5sum": "d8e471c8b822fac86c7c829eb9f6b759" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 30425088, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float32", "format": "raw", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.0.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 12582912, "byteOffset": 14696448 }, { "name": "model.layers.0.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float32", "format": "raw", "nbytes": 3145728, "byteOffset": 27279360 } ], "md5sum": "ee86aa786c350fdf376f8fcd1b7dd304" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "raw", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "7cec0a7772edc8daf93c5aecbb170739" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "6b8c389a2a26e5a115e514bee62c8dab" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 32538624, "records": [ { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 8388608 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 10485760 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float32", "format": "raw", "nbytes": 7340032, "byteOffset": 10502144 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float32", "format": "raw", "nbytes": 14680064, "byteOffset": 17842176 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 32522240 } ], "md5sum": "0f658ab047842b925de593e93c417e38" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "raw", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "ccd740702f8b906039a116a3840f9f7f" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 26230784, "records": [ { "name": "model.layers.1.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.1.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float32", "format": "raw", "nbytes": 3145728, "byteOffset": 12582912 }, { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 15728640 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 24117248 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 26214400 } ], "md5sum": "7f2d4d91c059257ec8d6e0aa505862c8" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "cff9f6aadd6d0fe28f0fce2063dc235f" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 22036480, "records": [ { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float32", "format": "raw", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float32", "format": "raw", "nbytes": 14680064, "byteOffset": 7340032 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 22020096 } ], "md5sum": "f652fdd4da913ee1a7f8511ffad68119" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "raw", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "f4e0a7a3c15aac30d0775135d7079e1b" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 26230784, "records": [ { "name": "model.layers.10.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.10.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float32", "format": "raw", "nbytes": 3145728, "byteOffset": 12582912 }, { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 15728640 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 24117248 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 26214400 } ], "md5sum": "41209ed402dbd14fdc67b42720674dbd" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "c4718b2d718c5d154fd5577293002bf9" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 22036480, "records": [ { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float32", "format": "raw", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float32", "format": "raw", "nbytes": 14680064, "byteOffset": 7340032 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 22020096 } ], "md5sum": "e14a8a97b3b3d74051a4f7c1df838508" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "raw", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "82b5f2bfa0064b8f32b8789f65f5cd5e" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 26230784, "records": [ { "name": "model.layers.11.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.11.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float32", "format": "raw", "nbytes": 3145728, "byteOffset": 12582912 }, { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 15728640 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 24117248 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 26214400 } ], "md5sum": "cfc8b7444e82f6a9e52f70a4083ddb12" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "5fc6402b60de33335c1558e4edaef570" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 22036480, "records": [ { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float32", "format": "raw", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float32", "format": "raw", "nbytes": 14680064, "byteOffset": 7340032 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 22020096 } ], "md5sum": "f5466345685ad425677d4b2b4f465369" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "raw", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "8140e84617ad16c0c7edc1d112f29245" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 26230784, "records": [ { "name": "model.layers.12.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.12.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float32", "format": "raw", "nbytes": 3145728, "byteOffset": 12582912 }, { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 15728640 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 24117248 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 26214400 } ], "md5sum": "6562c92b7fa4eabf2faabb61696fdfb2" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "f8c76952917cbcd82dbf5c99189a83eb" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 22036480, "records": [ { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float32", "format": "raw", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float32", "format": "raw", "nbytes": 14680064, "byteOffset": 7340032 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 22020096 } ], "md5sum": "e145eb0e0d19eab53731cb653f41cad9" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "raw", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "2b0704a4b9c766c902ff89e93bab2cb6" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 26230784, "records": [ { "name": "model.layers.13.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.13.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float32", "format": "raw", "nbytes": 3145728, "byteOffset": 12582912 }, { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 15728640 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 24117248 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 26214400 } ], "md5sum": "8bde50f386c9218b8cd0ddc8b40cd9c4" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "265bb8e6153a262085ce31dcd320e2e1" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 22036480, "records": [ { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float32", "format": "raw", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float32", "format": "raw", "nbytes": 14680064, "byteOffset": 7340032 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 22020096 } ], "md5sum": "fe3bcd1dccde680dd280681575f3f93a" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "raw", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "ff09219f2313ea01a85068b7db893c22" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 26230784, "records": [ { "name": "model.layers.14.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.14.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float32", "format": "raw", "nbytes": 3145728, "byteOffset": 12582912 }, { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 15728640 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 24117248 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 26214400 } ], "md5sum": "3d9494e6488b1ebebc6f435cd177f1c8" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "bc19f6c9bba60edaa9ec0a2b5f0ad421" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 22036480, "records": [ { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float32", "format": "raw", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float32", "format": "raw", "nbytes": 14680064, "byteOffset": 7340032 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 22020096 } ], "md5sum": "44621957dac6c0fc4fa0a8e67fa53dc9" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "raw", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "4298771a85f7a929fadb96db46a3a73e" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 26230784, "records": [ { "name": "model.layers.15.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.15.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float32", "format": "raw", "nbytes": 3145728, "byteOffset": 12582912 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 15728640 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 24117248 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 26214400 } ], "md5sum": "5086314b70060b545d50a1df10b680c9" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "f187efd27737bca1d72fedfa48dd11e6" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 22036480, "records": [ { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float32", "format": "raw", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float32", "format": "raw", "nbytes": 14680064, "byteOffset": 7340032 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 22020096 } ], "md5sum": "b8a6034a489d29231ea3bc377f3b2ea1" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "raw", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "ac977b87bc88d7fefc25f8bc467193f1" }, { "dataPath": "params_shard_77.bin", "format": "raw-shard", "nbytes": 26230784, "records": [ { "name": "model.layers.16.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.16.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float32", "format": "raw", "nbytes": 3145728, "byteOffset": 12582912 }, { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 15728640 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 24117248 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 26214400 } ], "md5sum": "cffa4b071ee7a52e2724681842d0ed11" }, { "dataPath": "params_shard_78.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "c44e2421e4ecdfd800bf6e04c72a2cd7" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 22036480, "records": [ { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float32", "format": "raw", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float32", "format": "raw", "nbytes": 14680064, "byteOffset": 7340032 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 22020096 } ], "md5sum": "08069abbefcaae0c23d54dbb63e644e8" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "raw", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "849cc431f1d22748794977f0efb0f691" }, { "dataPath": "params_shard_81.bin", "format": "raw-shard", "nbytes": 26230784, "records": [ { "name": "model.layers.17.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.17.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float32", "format": "raw", "nbytes": 3145728, "byteOffset": 12582912 }, { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 15728640 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 24117248 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 26214400 } ], "md5sum": "a7b45621b246a47239eb01a167d70676" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "372cee2283d66098e3e0539a6ab0ae48" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 22036480, "records": [ { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float32", "format": "raw", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float32", "format": "raw", "nbytes": 14680064, "byteOffset": 7340032 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 22020096 } ], "md5sum": "1cf5bd04fb3b2471dcbaaf6f5fe4a102" }, { "dataPath": "params_shard_84.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "raw", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "b75e2b42b7b02f2fd9e7232eb05da2b7" }, { "dataPath": "params_shard_85.bin", "format": "raw-shard", "nbytes": 26230784, "records": [ { "name": "model.layers.18.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.18.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float32", "format": "raw", "nbytes": 3145728, "byteOffset": 12582912 }, { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 15728640 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 24117248 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 26214400 } ], "md5sum": "855404c4ddf261e806178c6c34a1885f" }, { "dataPath": "params_shard_86.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "526de27417a4a51164b2f1fa6ee2c46a" }, { "dataPath": "params_shard_87.bin", "format": "raw-shard", "nbytes": 22036480, "records": [ { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float32", "format": "raw", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float32", "format": "raw", "nbytes": 14680064, "byteOffset": 7340032 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 22020096 } ], "md5sum": "ca47a97ca1754ab0fbf3d7d34e7f438e" }, { "dataPath": "params_shard_88.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "raw", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "d4b2efe97cf64553fa83de0325010595" }, { "dataPath": "params_shard_89.bin", "format": "raw-shard", "nbytes": 26230784, "records": [ { "name": "model.layers.19.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.19.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float32", "format": "raw", "nbytes": 3145728, "byteOffset": 12582912 }, { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 15728640 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 24117248 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 26214400 } ], "md5sum": "35afd96bc40f5a2fe7ec3eb89d4e70e3" }, { "dataPath": "params_shard_90.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "a9e603c45ca8fb982835476eeacb4edc" }, { "dataPath": "params_shard_91.bin", "format": "raw-shard", "nbytes": 22036480, "records": [ { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float32", "format": "raw", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float32", "format": "raw", "nbytes": 14680064, "byteOffset": 7340032 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 22020096 } ], "md5sum": "7c2981a85d0bfbe8b3b41b9898da562f" }, { "dataPath": "params_shard_92.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "raw", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "907929365d6a3da45082e49f6696ab43" }, { "dataPath": "params_shard_93.bin", "format": "raw-shard", "nbytes": 26230784, "records": [ { "name": "model.layers.2.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.2.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float32", "format": "raw", "nbytes": 3145728, "byteOffset": 12582912 }, { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 15728640 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 24117248 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 26214400 } ], "md5sum": "1736b3214009d76c9d4fa611df30687d" }, { "dataPath": "params_shard_94.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "55ed1ff5d7347c89789c6a58b5598f84" }, { "dataPath": "params_shard_95.bin", "format": "raw-shard", "nbytes": 22036480, "records": [ { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float32", "format": "raw", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float32", "format": "raw", "nbytes": 14680064, "byteOffset": 7340032 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 22020096 } ], "md5sum": "16300b1881083a74248ec71bf96a81ba" }, { "dataPath": "params_shard_96.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "raw", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "b67b7fbe06ac07a22d8681e6d1c16ac1" }, { "dataPath": "params_shard_97.bin", "format": "raw-shard", "nbytes": 26230784, "records": [ { "name": "model.layers.20.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.20.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float32", "format": "raw", "nbytes": 3145728, "byteOffset": 12582912 }, { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 15728640 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 24117248 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 26214400 } ], "md5sum": "c7dec0339ce7b3c3cfeb0a38fc6d98d3" }, { "dataPath": "params_shard_98.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "88753881c4ebbe9062096ca7e607d7a1" }, { "dataPath": "params_shard_99.bin", "format": "raw-shard", "nbytes": 22036480, "records": [ { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float32", "format": "raw", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float32", "format": "raw", "nbytes": 14680064, "byteOffset": 7340032 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 22020096 } ], "md5sum": "7fc0e64054935c90e5293cd40d8d12f6" }, { "dataPath": "params_shard_100.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.21.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.21.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float32", "format": "raw", "nbytes": 3145728, "byteOffset": 12582912 }, { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 15728640 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 24117248 } ], "md5sum": "dedd68822d3b0c1f113680c2e40d64bd" }, { "dataPath": "params_shard_101.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "raw", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "36144ad005b123074207afc8fff140ff" }, { "dataPath": "params_shard_102.bin", "format": "raw-shard", "nbytes": 26230784, "records": [ { "name": "model.layers.22.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.22.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float32", "format": "raw", "nbytes": 3145728, "byteOffset": 12582912 }, { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 15728640 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 24117248 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 26214400 } ], "md5sum": "d12d3899915b5bf83658f58410533995" }, { "dataPath": "params_shard_103.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "ae63cbc43b6eae5f025fa8836855fefb" }, { "dataPath": "params_shard_104.bin", "format": "raw-shard", "nbytes": 22036480, "records": [ { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float32", "format": "raw", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float32", "format": "raw", "nbytes": 14680064, "byteOffset": 7340032 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 22020096 } ], "md5sum": "a2d71dd088aa40f4ae8d858ff242728f" }, { "dataPath": "params_shard_105.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "raw", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "234cf222c778bbc61ef236bbf196982f" }, { "dataPath": "params_shard_106.bin", "format": "raw-shard", "nbytes": 26230784, "records": [ { "name": "model.layers.3.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.3.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float32", "format": "raw", "nbytes": 3145728, "byteOffset": 12582912 }, { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 15728640 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 24117248 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 26214400 } ], "md5sum": "589fa26257e4171093193266fd9df398" }, { "dataPath": "params_shard_107.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "73375be119532672cdab81f32bfb9c34" }, { "dataPath": "params_shard_108.bin", "format": "raw-shard", "nbytes": 22036480, "records": [ { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float32", "format": "raw", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float32", "format": "raw", "nbytes": 14680064, "byteOffset": 7340032 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 22020096 } ], "md5sum": "689947fd7b4159cff92fde75747021ad" }, { "dataPath": "params_shard_109.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "raw", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "2beffcf1e5aa6a06b8ba41d14ed32703" }, { "dataPath": "params_shard_110.bin", "format": "raw-shard", "nbytes": 26230784, "records": [ { "name": "model.layers.4.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.4.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float32", "format": "raw", "nbytes": 3145728, "byteOffset": 12582912 }, { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 15728640 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 24117248 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 26214400 } ], "md5sum": "6c278adf43b22ace2d7be0a566327f6b" }, { "dataPath": "params_shard_111.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "31b57e518befed5b5473c3d41cb8d521" }, { "dataPath": "params_shard_112.bin", "format": "raw-shard", "nbytes": 22036480, "records": [ { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float32", "format": "raw", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float32", "format": "raw", "nbytes": 14680064, "byteOffset": 7340032 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 22020096 } ], "md5sum": "8f145f66f16be25d580c6b0e78e17eda" }, { "dataPath": "params_shard_113.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "raw", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "f8ded7277bb4ca7caf9ca513b0f00a64" }, { "dataPath": "params_shard_114.bin", "format": "raw-shard", "nbytes": 26230784, "records": [ { "name": "model.layers.5.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.5.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float32", "format": "raw", "nbytes": 3145728, "byteOffset": 12582912 }, { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 15728640 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 24117248 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 26214400 } ], "md5sum": "17a96fd92cca2d2aaadf2d115c5b56fc" }, { "dataPath": "params_shard_115.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "8b28269943072c6401eea76582bad1e5" }, { "dataPath": "params_shard_116.bin", "format": "raw-shard", "nbytes": 22036480, "records": [ { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float32", "format": "raw", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float32", "format": "raw", "nbytes": 14680064, "byteOffset": 7340032 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 22020096 } ], "md5sum": "599fe821f4e97d4329feb88ddd806887" }, { "dataPath": "params_shard_117.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "raw", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "4e1c90f6c53d443b4990c82816a0a228" }, { "dataPath": "params_shard_118.bin", "format": "raw-shard", "nbytes": 26230784, "records": [ { "name": "model.layers.6.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.6.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float32", "format": "raw", "nbytes": 3145728, "byteOffset": 12582912 }, { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 15728640 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 24117248 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 26214400 } ], "md5sum": "ca90f980a21ca0d24776803eedde652a" }, { "dataPath": "params_shard_119.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "9ba8e2b03bfc6f14e856cbfc14d085a4" }, { "dataPath": "params_shard_120.bin", "format": "raw-shard", "nbytes": 22036480, "records": [ { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float32", "format": "raw", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float32", "format": "raw", "nbytes": 14680064, "byteOffset": 7340032 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 22020096 } ], "md5sum": "06998508e25d51e24cb89caf7e4281bf" }, { "dataPath": "params_shard_121.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "raw", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "8b852cd6adfc4a48224be4bfbb034de4" }, { "dataPath": "params_shard_122.bin", "format": "raw-shard", "nbytes": 26230784, "records": [ { "name": "model.layers.7.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.7.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float32", "format": "raw", "nbytes": 3145728, "byteOffset": 12582912 }, { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 15728640 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 24117248 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 26214400 } ], "md5sum": "aa6c051862fa80e5ed1ea920e34df999" }, { "dataPath": "params_shard_123.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "d57dade81beba2bc3e9807fc81bbece5" }, { "dataPath": "params_shard_124.bin", "format": "raw-shard", "nbytes": 22036480, "records": [ { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float32", "format": "raw", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float32", "format": "raw", "nbytes": 14680064, "byteOffset": 7340032 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 22020096 } ], "md5sum": "eabceccd9f9c71f14ceb8567f07e92e4" }, { "dataPath": "params_shard_125.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "raw", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "9db80661678c13e71baa3561104ec2f1" }, { "dataPath": "params_shard_126.bin", "format": "raw-shard", "nbytes": 26230784, "records": [ { "name": "model.layers.8.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.8.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float32", "format": "raw", "nbytes": 3145728, "byteOffset": 12582912 }, { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 15728640 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 24117248 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 26214400 } ], "md5sum": "32133141a3a2a1d3dd1878457071ba17" }, { "dataPath": "params_shard_127.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "95d43a392befebfd2255311895a01c79" }, { "dataPath": "params_shard_128.bin", "format": "raw-shard", "nbytes": 22036480, "records": [ { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float32", "format": "raw", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float32", "format": "raw", "nbytes": 14680064, "byteOffset": 7340032 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 22020096 } ], "md5sum": "37d7032743c222205af1b1177643a427" }, { "dataPath": "params_shard_129.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.9.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.9.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float32", "format": "raw", "nbytes": 3145728, "byteOffset": 12582912 }, { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 15728640 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 24117248 } ], "md5sum": "0074c4657b32e9ad0453b77bf8aac506" } ] }