{ "metadata": { "ParamSize": 507, "ParamBytes": 4766153728.0, "BitsPerParam": 4.068522985105678 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 458752000, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 256000, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 458752000, "byteOffset": 0 } ], "md5sum": "85ddc730c8a7f5f548d3e5857de426bc" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 25690112, "records": [ { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 3584, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25690112, "byteOffset": 0 } ], "md5sum": "bb4419cbf0f312715b0bf55db6050812" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 51380224, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 28672, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 51380224, "byteOffset": 0 } ], "md5sum": "d2f5065a1bb35028c3f5509fe5a14de2" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 31911936, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 256000, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336000, "byteOffset": 0 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 14336000 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 802816, "byteOffset": 14343168 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 28672, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 15145984 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 16751616 }, { "name": "model.layers.0.post_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 16758784 }, { "name": "model.layers.0.pre_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 16765952 }, { "name": "model.layers.0.self_attn.qkv_proj.q_weight", "shape": [ 8192, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 16773120 }, { "name": "model.layers.0.self_attn.qkv_proj.q_scale", "shape": [ 8192, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 458752, "byteOffset": 31453184 } ], "md5sum": "3cc01913407a88853011fc6f96227365" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 33266688, "records": [ { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 3584, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 3584, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 229376, "byteOffset": 7340032 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 7569408 }, { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 3584, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25690112, "byteOffset": 7576576 } ], "md5sum": "6e40c7aa7002d4df8fac4928a22c2389" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 51380224, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 28672, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 51380224, "byteOffset": 0 } ], "md5sum": "1db1cbb0f7db5d3fd5fcc500a555f897" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 25690112, "records": [ { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 3584, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25690112, "byteOffset": 0 } ], "md5sum": "ffce79b9a2c040e7c11175a068a0ab40" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 51380224, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 28672, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 51380224, "byteOffset": 0 } ], "md5sum": "3e3868fcae15a3f76ff68f4148fa136f" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 27575296, "records": [ { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 802816, "byteOffset": 0 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 28672, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 802816 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 2408448 }, { "name": "model.layers.1.post_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 2415616 }, { "name": "model.layers.1.pre_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 2422784 }, { "name": "model.layers.1.self_attn.qkv_proj.q_weight", "shape": [ 8192, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 2429952 }, { "name": "model.layers.1.self_attn.qkv_proj.q_scale", "shape": [ 8192, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 458752, "byteOffset": 17110016 }, { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 3584, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 17568768 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 3584, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 229376, "byteOffset": 24908800 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25138176 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 802816, "byteOffset": 25145344 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 28672, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 25948160 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 27553792 }, { "name": "model.layers.2.post_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 27560960 }, { "name": "model.layers.2.pre_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 27568128 } ], "md5sum": "08ac49803fa7e49ebea6652328f57d4c" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 25690112, "records": [ { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 3584, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25690112, "byteOffset": 0 } ], "md5sum": "922434ed6cc67979e1eb8cd82fb1ae3a" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 51380224, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 28672, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 51380224, "byteOffset": 0 } ], "md5sum": "31d9bf14effaf9f3b337a23e3cceb02a" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 25145344, "records": [ { "name": "model.layers.2.self_attn.qkv_proj.q_weight", "shape": [ 8192, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.2.self_attn.qkv_proj.q_scale", "shape": [ 8192, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 458752, "byteOffset": 14680064 }, { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 3584, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 15138816 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 3584, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 229376, "byteOffset": 22478848 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 22708224 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 802816, "byteOffset": 22715392 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 28672, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 23518208 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25123840 }, { "name": "model.layers.3.post_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25131008 }, { "name": "model.layers.3.pre_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25138176 } ], "md5sum": "fd6df6ab2a2e27039e54933780cfb191" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 25690112, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 3584, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25690112, "byteOffset": 0 } ], "md5sum": "cffab491b837e1a19693ac200d5606ca" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 51380224, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 28672, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 51380224, "byteOffset": 0 } ], "md5sum": "24cf500acae04c8598887d47e0f69046" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 25145344, "records": [ { "name": "model.layers.3.self_attn.qkv_proj.q_weight", "shape": [ 8192, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.3.self_attn.qkv_proj.q_scale", "shape": [ 8192, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 458752, "byteOffset": 14680064 }, { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 3584, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 15138816 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 3584, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 229376, "byteOffset": 22478848 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 22708224 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 802816, "byteOffset": 22715392 }, { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 28672, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 23518208 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25123840 }, { "name": "model.layers.4.post_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25131008 }, { "name": "model.layers.4.pre_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25138176 } ], "md5sum": "5c7ee5c18891558e552dc0574ec198d1" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 25690112, "records": [ { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 3584, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25690112, "byteOffset": 0 } ], "md5sum": "50cecbbc6f08392e5db829f861f49840" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 51380224, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 28672, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 51380224, "byteOffset": 0 } ], "md5sum": "ebeb4c56f39b4ba1b5250295b3a1b50a" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 25145344, "records": [ { "name": "model.layers.4.self_attn.qkv_proj.q_weight", "shape": [ 8192, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.4.self_attn.qkv_proj.q_scale", "shape": [ 8192, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 458752, "byteOffset": 14680064 }, { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 3584, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 15138816 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 3584, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 229376, "byteOffset": 22478848 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 22708224 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 802816, "byteOffset": 22715392 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 28672, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 23518208 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25123840 }, { "name": "model.layers.5.post_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25131008 }, { "name": "model.layers.5.pre_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25138176 } ], "md5sum": "5f8f5e97e4a25e4ca2177f6692f1a60b" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 25690112, "records": [ { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 3584, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25690112, "byteOffset": 0 } ], "md5sum": "57cfe0b420f797b6752c52253fbc25eb" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 51380224, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 28672, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 51380224, "byteOffset": 0 } ], "md5sum": "22b415beba87a7e75c425d9eba25af1f" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 25145344, "records": [ { "name": "model.layers.5.self_attn.qkv_proj.q_weight", "shape": [ 8192, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.5.self_attn.qkv_proj.q_scale", "shape": [ 8192, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 458752, "byteOffset": 14680064 }, { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 3584, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 15138816 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 3584, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 229376, "byteOffset": 22478848 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 22708224 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 802816, "byteOffset": 22715392 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 28672, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 23518208 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25123840 }, { "name": "model.layers.6.post_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25131008 }, { "name": "model.layers.6.pre_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25138176 } ], "md5sum": "38c529c6ee776b58b6ed52e193ed87cc" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 51380224, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 28672, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 51380224, "byteOffset": 0 } ], "md5sum": "af8fca295f34376838aa691c1b9de6be" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 24313856, "records": [ { "name": "model.layers.6.self_attn.qkv_proj.q_weight", "shape": [ 8192, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.6.self_attn.qkv_proj.q_scale", "shape": [ 8192, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 458752, "byteOffset": 14680064 }, { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 3584, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 15138816 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 3584, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 229376, "byteOffset": 22478848 }, { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 28672, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 22708224 } ], "md5sum": "dce382f294302e6febdb315b9f97cbd3" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 25690112, "records": [ { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 3584, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25690112, "byteOffset": 0 } ], "md5sum": "ae1b007e79d081f7a19cabd25872d486" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 51380224, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 28672, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 51380224, "byteOffset": 0 } ], "md5sum": "bfc54c2dc75f36ee0e67ef49f868436f" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 25145344, "records": [ { "name": "model.layers.7.self_attn.qkv_proj.q_weight", "shape": [ 8192, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.7.self_attn.qkv_proj.q_scale", "shape": [ 8192, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 458752, "byteOffset": 14680064 }, { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 3584, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 15138816 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 3584, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 229376, "byteOffset": 22478848 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 22708224 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 802816, "byteOffset": 22715392 }, { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 28672, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 23518208 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25123840 }, { "name": "model.layers.10.post_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25131008 }, { "name": "model.layers.10.pre_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25138176 } ], "md5sum": "2f20545ce596d493553a48d3ef0dcf81" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 25690112, "records": [ { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 3584, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25690112, "byteOffset": 0 } ], "md5sum": "a7b8e948253e9ec7635c71ad02e641b1" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 51380224, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 28672, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 51380224, "byteOffset": 0 } ], "md5sum": "1fccaf477885b60fe43b3274e4ca924e" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 25145344, "records": [ { "name": "model.layers.10.self_attn.qkv_proj.q_weight", "shape": [ 8192, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.10.self_attn.qkv_proj.q_scale", "shape": [ 8192, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 458752, "byteOffset": 14680064 }, { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 3584, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 15138816 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 3584, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 229376, "byteOffset": 22478848 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 22708224 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 802816, "byteOffset": 22715392 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 28672, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 23518208 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25123840 }, { "name": "model.layers.11.post_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25131008 }, { "name": "model.layers.11.pre_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25138176 } ], "md5sum": "e977dfd85e448ff95580b21f0c933ab1" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 25690112, "records": [ { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 3584, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25690112, "byteOffset": 0 } ], "md5sum": "8554c975d80380f0384525297790811b" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 51380224, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 28672, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 51380224, "byteOffset": 0 } ], "md5sum": "c7599906a82cfd7d5eb54bcbbc90a6b4" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 25145344, "records": [ { "name": "model.layers.11.self_attn.qkv_proj.q_weight", "shape": [ 8192, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.11.self_attn.qkv_proj.q_scale", "shape": [ 8192, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 458752, "byteOffset": 14680064 }, { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 3584, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 15138816 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 3584, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 229376, "byteOffset": 22478848 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 22708224 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 802816, "byteOffset": 22715392 }, { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 28672, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 23518208 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25123840 }, { "name": "model.layers.12.post_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25131008 }, { "name": "model.layers.12.pre_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25138176 } ], "md5sum": "840c896329a840af9d90682e5b89c56d" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 25690112, "records": [ { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 3584, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25690112, "byteOffset": 0 } ], "md5sum": "9fa9e75ecb040d1a30fc062160a13f3d" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 51380224, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 28672, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 51380224, "byteOffset": 0 } ], "md5sum": "36629a41a546845f9629929e3ae196c2" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 25145344, "records": [ { "name": "model.layers.12.self_attn.qkv_proj.q_weight", "shape": [ 8192, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.12.self_attn.qkv_proj.q_scale", "shape": [ 8192, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 458752, "byteOffset": 14680064 }, { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 3584, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 15138816 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 3584, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 229376, "byteOffset": 22478848 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 22708224 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 802816, "byteOffset": 22715392 }, { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 28672, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 23518208 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25123840 }, { "name": "model.layers.13.post_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25131008 }, { "name": "model.layers.13.pre_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25138176 } ], "md5sum": "72737948f1f2eac8fc3336d06a54b4b6" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 25690112, "records": [ { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 3584, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25690112, "byteOffset": 0 } ], "md5sum": "88958f7e9c1ce8690487cf67cde5e7df" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 51380224, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 28672, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 51380224, "byteOffset": 0 } ], "md5sum": "1425e040645d283ccfdee52e1f459962" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 25145344, "records": [ { "name": "model.layers.13.self_attn.qkv_proj.q_weight", "shape": [ 8192, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.13.self_attn.qkv_proj.q_scale", "shape": [ 8192, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 458752, "byteOffset": 14680064 }, { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 3584, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 15138816 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 3584, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 229376, "byteOffset": 22478848 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 22708224 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 802816, "byteOffset": 22715392 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 28672, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 23518208 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25123840 }, { "name": "model.layers.14.post_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25131008 }, { "name": "model.layers.14.pre_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25138176 } ], "md5sum": "8ed3378afd99d9cd65fe4338cca6c916" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 25690112, "records": [ { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 3584, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25690112, "byteOffset": 0 } ], "md5sum": "294dd395aaa6c7b4f57f754222f81773" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 51380224, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 28672, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 51380224, "byteOffset": 0 } ], "md5sum": "5d946028f63ed25c8153827f7526f4d9" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 25145344, "records": [ { "name": "model.layers.14.self_attn.qkv_proj.q_weight", "shape": [ 8192, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.14.self_attn.qkv_proj.q_scale", "shape": [ 8192, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 458752, "byteOffset": 14680064 }, { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 3584, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 15138816 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 3584, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 229376, "byteOffset": 22478848 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 22708224 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 802816, "byteOffset": 22715392 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 28672, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 23518208 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25123840 }, { "name": "model.layers.15.post_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25131008 }, { "name": "model.layers.15.pre_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25138176 } ], "md5sum": "544302a2e814d15c5febe53333079a37" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 25690112, "records": [ { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 3584, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25690112, "byteOffset": 0 } ], "md5sum": "8d72421b5536fe560240b3a1d994bfcc" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 51380224, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 28672, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 51380224, "byteOffset": 0 } ], "md5sum": "2700a5f59496bfede4e77b767f941d0e" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 25145344, "records": [ { "name": "model.layers.15.self_attn.qkv_proj.q_weight", "shape": [ 8192, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.15.self_attn.qkv_proj.q_scale", "shape": [ 8192, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 458752, "byteOffset": 14680064 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 3584, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 15138816 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 3584, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 229376, "byteOffset": 22478848 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 22708224 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 802816, "byteOffset": 22715392 }, { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 28672, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 23518208 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25123840 }, { "name": "model.layers.16.post_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25131008 }, { "name": "model.layers.16.pre_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25138176 } ], "md5sum": "08649a5a3aa1ec701d7efc6eb6e97c3f" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 25690112, "records": [ { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 3584, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25690112, "byteOffset": 0 } ], "md5sum": "b1955034fc36473f5dca818c6d1e4bdb" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 51380224, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 28672, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 51380224, "byteOffset": 0 } ], "md5sum": "62927f2a1b7ede683b6a5c94edf95424" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 25145344, "records": [ { "name": "model.layers.16.self_attn.qkv_proj.q_weight", "shape": [ 8192, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.16.self_attn.qkv_proj.q_scale", "shape": [ 8192, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 458752, "byteOffset": 14680064 }, { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 3584, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 15138816 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 3584, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 229376, "byteOffset": 22478848 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 22708224 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 802816, "byteOffset": 22715392 }, { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 28672, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 23518208 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25123840 }, { "name": "model.layers.17.post_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25131008 }, { "name": "model.layers.17.pre_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25138176 } ], "md5sum": "84753f17e779d420be9189a1a502654e" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 25690112, "records": [ { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 3584, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25690112, "byteOffset": 0 } ], "md5sum": "09c24c06dc5df81ebd1e653f415c260c" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 51380224, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 28672, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 51380224, "byteOffset": 0 } ], "md5sum": "8b183956e925d49373c5c2d736690bb4" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 25145344, "records": [ { "name": "model.layers.17.self_attn.qkv_proj.q_weight", "shape": [ 8192, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.17.self_attn.qkv_proj.q_scale", "shape": [ 8192, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 458752, "byteOffset": 14680064 }, { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 3584, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 15138816 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 3584, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 229376, "byteOffset": 22478848 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 22708224 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 802816, "byteOffset": 22715392 }, { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 28672, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 23518208 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25123840 }, { "name": "model.layers.18.post_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25131008 }, { "name": "model.layers.18.pre_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25138176 } ], "md5sum": "812ac727830b1303bdfac5ad2a2d391d" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 25690112, "records": [ { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 3584, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25690112, "byteOffset": 0 } ], "md5sum": "6b457f58cc68fb314e8249cef4c7e859" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 51380224, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 28672, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 51380224, "byteOffset": 0 } ], "md5sum": "c7ad18401ac2001e51d67fcfa6e4af8a" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 25145344, "records": [ { "name": "model.layers.18.self_attn.qkv_proj.q_weight", "shape": [ 8192, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.18.self_attn.qkv_proj.q_scale", "shape": [ 8192, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 458752, "byteOffset": 14680064 }, { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 3584, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 15138816 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 3584, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 229376, "byteOffset": 22478848 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 22708224 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 802816, "byteOffset": 22715392 }, { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 28672, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 23518208 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25123840 }, { "name": "model.layers.19.post_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25131008 }, { "name": "model.layers.19.pre_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25138176 } ], "md5sum": "ac1878c40c00b28ed70d70ea62d66006" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 22708224, "records": [ { "name": "model.layers.19.self_attn.qkv_proj.q_weight", "shape": [ 8192, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.19.self_attn.qkv_proj.q_scale", "shape": [ 8192, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 458752, "byteOffset": 14680064 }, { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 3584, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 15138816 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 3584, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 229376, "byteOffset": 22478848 } ], "md5sum": "11384b37c90f6c7121de9fed6970d272" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 25690112, "records": [ { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 3584, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25690112, "byteOffset": 0 } ], "md5sum": "399ee820a05957758c03ad1242271031" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 25690112, "records": [ { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 3584, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25690112, "byteOffset": 0 } ], "md5sum": "876fe3824d46c07818f6cc1678d43175" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 51380224, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 28672, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 51380224, "byteOffset": 0 } ], "md5sum": "6cb30c009d925dbdd95f39241376c7ef" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 33546240, "records": [ { "name": "model.layers.20.self_attn.qkv_proj.q_weight", "shape": [ 8192, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.20.self_attn.qkv_proj.q_scale", "shape": [ 8192, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 458752, "byteOffset": 14680064 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 15138816 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 802816, "byteOffset": 15145984 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 15948800 }, { "name": "model.layers.7.post_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 15955968 }, { "name": "model.layers.7.pre_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 15963136 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 15970304 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 802816, "byteOffset": 15977472 }, { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 28672, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 16780288 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 18385920 }, { "name": "model.layers.8.post_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 18393088 }, { "name": "model.layers.8.pre_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 18400256 }, { "name": "model.layers.8.self_attn.qkv_proj.q_weight", "shape": [ 8192, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 18407424 }, { "name": "model.layers.8.self_attn.qkv_proj.q_scale", "shape": [ 8192, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 458752, "byteOffset": 33087488 } ], "md5sum": "18965c2e694a87b04d8c1279f0cebc86" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 33266688, "records": [ { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 3584, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 3584, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 229376, "byteOffset": 7340032 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 7569408 }, { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 3584, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25690112, "byteOffset": 7576576 } ], "md5sum": "d8ee00c384625f10188b277ccc161493" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 51380224, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 28672, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 51380224, "byteOffset": 0 } ], "md5sum": "d09e2b0a5ff30691e216f78f9adfc081" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 25690112, "records": [ { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 3584, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25690112, "byteOffset": 0 } ], "md5sum": "4b30cb9e3a18a664e3a64582183a357c" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 51380224, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 28672, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 51380224, "byteOffset": 0 } ], "md5sum": "f56ceaaaaeece312aa884db2817b1fd7" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 27575296, "records": [ { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 802816, "byteOffset": 0 }, { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 28672, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 802816 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 2408448 }, { "name": "model.layers.9.post_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 2415616 }, { "name": "model.layers.9.pre_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 2422784 }, { "name": "model.layers.9.self_attn.qkv_proj.q_weight", "shape": [ 8192, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 2429952 }, { "name": "model.layers.9.self_attn.qkv_proj.q_scale", "shape": [ 8192, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 458752, "byteOffset": 17110016 }, { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 3584, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 17568768 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 3584, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 229376, "byteOffset": 24908800 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25138176 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 802816, "byteOffset": 25145344 }, { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 28672, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 25948160 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 27553792 }, { "name": "model.layers.20.post_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 27560960 }, { "name": "model.layers.20.pre_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 27568128 } ], "md5sum": "537a4bb1f6c0c0ea9fad8df175a333f1" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 33266688, "records": [ { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 3584, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 3584, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 229376, "byteOffset": 7340032 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 7569408 }, { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 3584, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25690112, "byteOffset": 7576576 } ], "md5sum": "31b28b086a3437fa66206d883e4df9ec" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 51380224, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 28672, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 51380224, "byteOffset": 0 } ], "md5sum": "f51ce4047eba661948f123eb144a46c7" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 25690112, "records": [ { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 3584, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25690112, "byteOffset": 0 } ], "md5sum": "18bdf269225a58e580cfb212f902ac42" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 51380224, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 28672, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 51380224, "byteOffset": 0 } ], "md5sum": "67391fdc73068de537a45c00c80b8a8e" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 27575296, "records": [ { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 802816, "byteOffset": 0 }, { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 28672, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 802816 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 2408448 }, { "name": "model.layers.21.post_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 2415616 }, { "name": "model.layers.21.pre_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 2422784 }, { "name": "model.layers.21.self_attn.qkv_proj.q_weight", "shape": [ 8192, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 2429952 }, { "name": "model.layers.21.self_attn.qkv_proj.q_scale", "shape": [ 8192, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 458752, "byteOffset": 17110016 }, { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 3584, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 17568768 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 3584, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 229376, "byteOffset": 24908800 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25138176 }, { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 802816, "byteOffset": 25145344 }, { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 28672, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 25948160 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 27553792 }, { "name": "model.layers.22.post_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 27560960 }, { "name": "model.layers.22.pre_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 27568128 } ], "md5sum": "3cc7fd932c3283eface0e575f862b2fc" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 25690112, "records": [ { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 3584, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25690112, "byteOffset": 0 } ], "md5sum": "b7d626f514afb4442442b6431ac84bfa" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 51380224, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 28672, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 51380224, "byteOffset": 0 } ], "md5sum": "ba086b5f1e57e30880f776d9fd85e9d2" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 25145344, "records": [ { "name": "model.layers.22.self_attn.qkv_proj.q_weight", "shape": [ 8192, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.22.self_attn.qkv_proj.q_scale", "shape": [ 8192, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 458752, "byteOffset": 14680064 }, { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 3584, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 15138816 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 3584, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 229376, "byteOffset": 22478848 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 22708224 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 802816, "byteOffset": 22715392 }, { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 28672, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 23518208 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25123840 }, { "name": "model.layers.23.post_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25131008 }, { "name": "model.layers.23.pre_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25138176 } ], "md5sum": "fa14a92c1d2d519407df75e96e6c4ccb" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 25690112, "records": [ { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 3584, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25690112, "byteOffset": 0 } ], "md5sum": "5c3ca3feb5e107c5ef0dc65fbbd19129" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 51380224, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 28672, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 51380224, "byteOffset": 0 } ], "md5sum": "63227636e853d7b8ec21ecf5694b1f42" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 25145344, "records": [ { "name": "model.layers.23.self_attn.qkv_proj.q_weight", "shape": [ 8192, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.23.self_attn.qkv_proj.q_scale", "shape": [ 8192, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 458752, "byteOffset": 14680064 }, { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 3584, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 15138816 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 3584, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 229376, "byteOffset": 22478848 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 22708224 }, { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 802816, "byteOffset": 22715392 }, { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 28672, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 23518208 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25123840 }, { "name": "model.layers.24.post_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25131008 }, { "name": "model.layers.24.pre_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25138176 } ], "md5sum": "bafebf42746495997140f00794650949" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 25690112, "records": [ { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 3584, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25690112, "byteOffset": 0 } ], "md5sum": "0f9944644bf445a96037ea19fd0457cc" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 51380224, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 28672, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 51380224, "byteOffset": 0 } ], "md5sum": "4fa854033ab8df4ca7a30d901d763056" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 25145344, "records": [ { "name": "model.layers.24.self_attn.qkv_proj.q_weight", "shape": [ 8192, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.24.self_attn.qkv_proj.q_scale", "shape": [ 8192, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 458752, "byteOffset": 14680064 }, { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 3584, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 15138816 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 3584, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 229376, "byteOffset": 22478848 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 22708224 }, { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 802816, "byteOffset": 22715392 }, { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 28672, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 23518208 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25123840 }, { "name": "model.layers.25.post_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25131008 }, { "name": "model.layers.25.pre_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25138176 } ], "md5sum": "12c42b0dc7f2b0f54ee6c01c7c5fdf80" }, { "dataPath": "params_shard_77.bin", "format": "raw-shard", "nbytes": 25690112, "records": [ { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 3584, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25690112, "byteOffset": 0 } ], "md5sum": "1b87d35c5f2c38ac36bf4112196353d2" }, { "dataPath": "params_shard_78.bin", "format": "raw-shard", "nbytes": 51380224, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 28672, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 51380224, "byteOffset": 0 } ], "md5sum": "e32831dc18e0c8908aa57bb23a75afaf" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 25145344, "records": [ { "name": "model.layers.25.self_attn.qkv_proj.q_weight", "shape": [ 8192, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.25.self_attn.qkv_proj.q_scale", "shape": [ 8192, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 458752, "byteOffset": 14680064 }, { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 3584, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 15138816 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 3584, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 229376, "byteOffset": 22478848 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 22708224 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 802816, "byteOffset": 22715392 }, { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 28672, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 23518208 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25123840 }, { "name": "model.layers.26.post_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25131008 }, { "name": "model.layers.26.pre_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25138176 } ], "md5sum": "e550107b4d8ebb9841fabd8a5ee8f60e" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 25690112, "records": [ { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 3584, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25690112, "byteOffset": 0 } ], "md5sum": "0e6d73cdd73aa70843b7ed06b8842d8a" }, { "dataPath": "params_shard_81.bin", "format": "raw-shard", "nbytes": 51380224, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 28672, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 51380224, "byteOffset": 0 } ], "md5sum": "02bcd499500e3bfadced68202ef3a2d1" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 25145344, "records": [ { "name": "model.layers.26.self_attn.qkv_proj.q_weight", "shape": [ 8192, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.26.self_attn.qkv_proj.q_scale", "shape": [ 8192, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 458752, "byteOffset": 14680064 }, { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 3584, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 15138816 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 3584, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 229376, "byteOffset": 22478848 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 22708224 }, { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 802816, "byteOffset": 22715392 }, { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 28672, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 23518208 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25123840 }, { "name": "model.layers.27.post_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25131008 }, { "name": "model.layers.27.pre_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25138176 } ], "md5sum": "a73ed16135208950d003c3f73a86f4b7" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 25690112, "records": [ { "name": "model.layers.28.mlp.down_proj.q_weight", "shape": [ 3584, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25690112, "byteOffset": 0 } ], "md5sum": "a9b7ebe1e4dcea43827a071b891d363a" }, { "dataPath": "params_shard_84.bin", "format": "raw-shard", "nbytes": 51380224, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_weight", "shape": [ 28672, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 51380224, "byteOffset": 0 } ], "md5sum": "08ff8a191d0ac75e2ec24be5390806d5" }, { "dataPath": "params_shard_85.bin", "format": "raw-shard", "nbytes": 25145344, "records": [ { "name": "model.layers.27.self_attn.qkv_proj.q_weight", "shape": [ 8192, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.27.self_attn.qkv_proj.q_scale", "shape": [ 8192, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 458752, "byteOffset": 14680064 }, { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 3584, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 15138816 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 3584, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 229376, "byteOffset": 22478848 }, { "name": "model.layers.28.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 22708224 }, { "name": "model.layers.28.mlp.down_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 802816, "byteOffset": 22715392 }, { "name": "model.layers.28.mlp.gate_up_proj.q_scale", "shape": [ 28672, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 23518208 }, { "name": "model.layers.28.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25123840 }, { "name": "model.layers.28.post_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25131008 }, { "name": "model.layers.28.pre_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25138176 } ], "md5sum": "a3140a2bd1cc113053142f785d597ffc" }, { "dataPath": "params_shard_86.bin", "format": "raw-shard", "nbytes": 25690112, "records": [ { "name": "model.layers.29.mlp.down_proj.q_weight", "shape": [ 3584, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25690112, "byteOffset": 0 } ], "md5sum": "077b9c89dffd7b5785316c7cb5a19679" }, { "dataPath": "params_shard_87.bin", "format": "raw-shard", "nbytes": 51380224, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_weight", "shape": [ 28672, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 51380224, "byteOffset": 0 } ], "md5sum": "c216ff00d1b9d6cde57662fc7f216238" }, { "dataPath": "params_shard_88.bin", "format": "raw-shard", "nbytes": 25145344, "records": [ { "name": "model.layers.28.self_attn.qkv_proj.q_weight", "shape": [ 8192, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.28.self_attn.qkv_proj.q_scale", "shape": [ 8192, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 458752, "byteOffset": 14680064 }, { "name": "model.layers.28.self_attn.o_proj.q_weight", "shape": [ 3584, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 15138816 }, { "name": "model.layers.28.self_attn.o_proj.q_scale", "shape": [ 3584, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 229376, "byteOffset": 22478848 }, { "name": "model.layers.29.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 22708224 }, { "name": "model.layers.29.mlp.down_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 802816, "byteOffset": 22715392 }, { "name": "model.layers.29.mlp.gate_up_proj.q_scale", "shape": [ 28672, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 23518208 }, { "name": "model.layers.29.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25123840 }, { "name": "model.layers.29.post_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25131008 }, { "name": "model.layers.29.pre_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25138176 } ], "md5sum": "da05c54714d018fb66d8c7831c60d4f0" }, { "dataPath": "params_shard_89.bin", "format": "raw-shard", "nbytes": 25690112, "records": [ { "name": "model.layers.30.mlp.down_proj.q_weight", "shape": [ 3584, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25690112, "byteOffset": 0 } ], "md5sum": "9e86e66bb92b1048d455fe76118403f5" }, { "dataPath": "params_shard_90.bin", "format": "raw-shard", "nbytes": 51380224, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_weight", "shape": [ 28672, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 51380224, "byteOffset": 0 } ], "md5sum": "91760b3ed369fa76415bf311bb6f7869" }, { "dataPath": "params_shard_91.bin", "format": "raw-shard", "nbytes": 25145344, "records": [ { "name": "model.layers.29.self_attn.qkv_proj.q_weight", "shape": [ 8192, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.29.self_attn.qkv_proj.q_scale", "shape": [ 8192, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 458752, "byteOffset": 14680064 }, { "name": "model.layers.29.self_attn.o_proj.q_weight", "shape": [ 3584, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 15138816 }, { "name": "model.layers.29.self_attn.o_proj.q_scale", "shape": [ 3584, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 229376, "byteOffset": 22478848 }, { "name": "model.layers.30.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 22708224 }, { "name": "model.layers.30.mlp.down_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 802816, "byteOffset": 22715392 }, { "name": "model.layers.30.mlp.gate_up_proj.q_scale", "shape": [ 28672, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 23518208 }, { "name": "model.layers.30.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25123840 }, { "name": "model.layers.30.post_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25131008 }, { "name": "model.layers.30.pre_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25138176 } ], "md5sum": "492e9e225327d06fff126c5108f31019" }, { "dataPath": "params_shard_92.bin", "format": "raw-shard", "nbytes": 25690112, "records": [ { "name": "model.layers.31.mlp.down_proj.q_weight", "shape": [ 3584, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25690112, "byteOffset": 0 } ], "md5sum": "09e74aee05187d5105a2e1d57a55cebc" }, { "dataPath": "params_shard_93.bin", "format": "raw-shard", "nbytes": 51380224, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_weight", "shape": [ 28672, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 51380224, "byteOffset": 0 } ], "md5sum": "8931c9e8901685b3e36fc1a4eaa0b936" }, { "dataPath": "params_shard_94.bin", "format": "raw-shard", "nbytes": 25145344, "records": [ { "name": "model.layers.30.self_attn.qkv_proj.q_weight", "shape": [ 8192, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.30.self_attn.qkv_proj.q_scale", "shape": [ 8192, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 458752, "byteOffset": 14680064 }, { "name": "model.layers.30.self_attn.o_proj.q_weight", "shape": [ 3584, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 15138816 }, { "name": "model.layers.30.self_attn.o_proj.q_scale", "shape": [ 3584, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 229376, "byteOffset": 22478848 }, { "name": "model.layers.31.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 22708224 }, { "name": "model.layers.31.mlp.down_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 802816, "byteOffset": 22715392 }, { "name": "model.layers.31.mlp.gate_up_proj.q_scale", "shape": [ 28672, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 23518208 }, { "name": "model.layers.31.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25123840 }, { "name": "model.layers.31.post_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25131008 }, { "name": "model.layers.31.pre_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25138176 } ], "md5sum": "a11414a9be6c54c9136ce59c2891f8f7" }, { "dataPath": "params_shard_95.bin", "format": "raw-shard", "nbytes": 51380224, "records": [ { "name": "model.layers.32.mlp.gate_up_proj.q_weight", "shape": [ 28672, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 51380224, "byteOffset": 0 } ], "md5sum": "15b1c22ad27d858d786d383074871639" }, { "dataPath": "params_shard_96.bin", "format": "raw-shard", "nbytes": 24313856, "records": [ { "name": "model.layers.31.self_attn.qkv_proj.q_weight", "shape": [ 8192, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.31.self_attn.qkv_proj.q_scale", "shape": [ 8192, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 458752, "byteOffset": 14680064 }, { "name": "model.layers.31.self_attn.o_proj.q_weight", "shape": [ 3584, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 15138816 }, { "name": "model.layers.31.self_attn.o_proj.q_scale", "shape": [ 3584, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 229376, "byteOffset": 22478848 }, { "name": "model.layers.32.mlp.gate_up_proj.q_scale", "shape": [ 28672, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 22708224 } ], "md5sum": "2637b4df95fb098e1ad6872fc2c797ca" }, { "dataPath": "params_shard_97.bin", "format": "raw-shard", "nbytes": 25690112, "records": [ { "name": "model.layers.32.mlp.down_proj.q_weight", "shape": [ 3584, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25690112, "byteOffset": 0 } ], "md5sum": "eab15a198072942de039f18942aa2d0f" }, { "dataPath": "params_shard_98.bin", "format": "raw-shard", "nbytes": 25690112, "records": [ { "name": "model.layers.33.mlp.down_proj.q_weight", "shape": [ 3584, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25690112, "byteOffset": 0 } ], "md5sum": "9de6da121fac1a1df51ae9850010e84f" }, { "dataPath": "params_shard_99.bin", "format": "raw-shard", "nbytes": 51380224, "records": [ { "name": "model.layers.33.mlp.gate_up_proj.q_weight", "shape": [ 28672, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 51380224, "byteOffset": 0 } ], "md5sum": "19eae08142e327e4ee646520ad8ba401" }, { "dataPath": "params_shard_100.bin", "format": "raw-shard", "nbytes": 25976832, "records": [ { "name": "model.layers.32.self_attn.qkv_proj.q_weight", "shape": [ 8192, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.32.self_attn.qkv_proj.q_scale", "shape": [ 8192, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 458752, "byteOffset": 14680064 }, { "name": "model.layers.32.self_attn.o_proj.q_weight", "shape": [ 3584, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 15138816 }, { "name": "model.layers.32.self_attn.o_proj.q_scale", "shape": [ 3584, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 229376, "byteOffset": 22478848 }, { "name": "model.layers.32.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 22708224 }, { "name": "model.layers.32.mlp.down_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 802816, "byteOffset": 22715392 }, { "name": "model.layers.32.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 23518208 }, { "name": "model.layers.32.post_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 23525376 }, { "name": "model.layers.32.pre_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 23532544 }, { "name": "model.layers.33.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 23539712 }, { "name": "model.layers.33.mlp.down_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 802816, "byteOffset": 23546880 }, { "name": "model.layers.33.mlp.gate_up_proj.q_scale", "shape": [ 28672, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 24349696 }, { "name": "model.layers.33.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25955328 }, { "name": "model.layers.33.post_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25962496 }, { "name": "model.layers.33.pre_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25969664 } ], "md5sum": "d715141ebe3f1b3069de920f2dfb5b5a" }, { "dataPath": "params_shard_101.bin", "format": "raw-shard", "nbytes": 25690112, "records": [ { "name": "model.layers.34.mlp.down_proj.q_weight", "shape": [ 3584, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25690112, "byteOffset": 0 } ], "md5sum": "9e405006447e3841c4697bd133e6e047" }, { "dataPath": "params_shard_102.bin", "format": "raw-shard", "nbytes": 51380224, "records": [ { "name": "model.layers.34.mlp.gate_up_proj.q_weight", "shape": [ 28672, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 51380224, "byteOffset": 0 } ], "md5sum": "54847ef1f05e1dc9eca982fa2388c630" }, { "dataPath": "params_shard_103.bin", "format": "raw-shard", "nbytes": 25145344, "records": [ { "name": "model.layers.33.self_attn.qkv_proj.q_weight", "shape": [ 8192, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.33.self_attn.qkv_proj.q_scale", "shape": [ 8192, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 458752, "byteOffset": 14680064 }, { "name": "model.layers.33.self_attn.o_proj.q_weight", "shape": [ 3584, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 15138816 }, { "name": "model.layers.33.self_attn.o_proj.q_scale", "shape": [ 3584, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 229376, "byteOffset": 22478848 }, { "name": "model.layers.34.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 22708224 }, { "name": "model.layers.34.mlp.down_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 802816, "byteOffset": 22715392 }, { "name": "model.layers.34.mlp.gate_up_proj.q_scale", "shape": [ 28672, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 23518208 }, { "name": "model.layers.34.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25123840 }, { "name": "model.layers.34.post_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25131008 }, { "name": "model.layers.34.pre_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25138176 } ], "md5sum": "ba38307adf9b43b7a1eca41722fdea96" }, { "dataPath": "params_shard_104.bin", "format": "raw-shard", "nbytes": 25690112, "records": [ { "name": "model.layers.35.mlp.down_proj.q_weight", "shape": [ 3584, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25690112, "byteOffset": 0 } ], "md5sum": "4d84dfb00e3f8248fe2c1155b6ab1017" }, { "dataPath": "params_shard_105.bin", "format": "raw-shard", "nbytes": 51380224, "records": [ { "name": "model.layers.35.mlp.gate_up_proj.q_weight", "shape": [ 28672, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 51380224, "byteOffset": 0 } ], "md5sum": "10b609a98894fb994d56bf4d0f082d41" }, { "dataPath": "params_shard_106.bin", "format": "raw-shard", "nbytes": 25145344, "records": [ { "name": "model.layers.34.self_attn.qkv_proj.q_weight", "shape": [ 8192, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.34.self_attn.qkv_proj.q_scale", "shape": [ 8192, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 458752, "byteOffset": 14680064 }, { "name": "model.layers.34.self_attn.o_proj.q_weight", "shape": [ 3584, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 15138816 }, { "name": "model.layers.34.self_attn.o_proj.q_scale", "shape": [ 3584, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 229376, "byteOffset": 22478848 }, { "name": "model.layers.35.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 22708224 }, { "name": "model.layers.35.mlp.down_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 802816, "byteOffset": 22715392 }, { "name": "model.layers.35.mlp.gate_up_proj.q_scale", "shape": [ 28672, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 23518208 }, { "name": "model.layers.35.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25123840 }, { "name": "model.layers.35.post_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25131008 }, { "name": "model.layers.35.pre_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25138176 } ], "md5sum": "138e011d21d31ed0106526306753e572" }, { "dataPath": "params_shard_107.bin", "format": "raw-shard", "nbytes": 25690112, "records": [ { "name": "model.layers.36.mlp.down_proj.q_weight", "shape": [ 3584, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25690112, "byteOffset": 0 } ], "md5sum": "4600e8de4dfd41d87559a2a53177b0b4" }, { "dataPath": "params_shard_108.bin", "format": "raw-shard", "nbytes": 51380224, "records": [ { "name": "model.layers.36.mlp.gate_up_proj.q_weight", "shape": [ 28672, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 51380224, "byteOffset": 0 } ], "md5sum": "9107024a94b2c85666158e3d54b84443" }, { "dataPath": "params_shard_109.bin", "format": "raw-shard", "nbytes": 25145344, "records": [ { "name": "model.layers.35.self_attn.qkv_proj.q_weight", "shape": [ 8192, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.35.self_attn.qkv_proj.q_scale", "shape": [ 8192, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 458752, "byteOffset": 14680064 }, { "name": "model.layers.35.self_attn.o_proj.q_weight", "shape": [ 3584, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 15138816 }, { "name": "model.layers.35.self_attn.o_proj.q_scale", "shape": [ 3584, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 229376, "byteOffset": 22478848 }, { "name": "model.layers.36.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 22708224 }, { "name": "model.layers.36.mlp.down_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 802816, "byteOffset": 22715392 }, { "name": "model.layers.36.mlp.gate_up_proj.q_scale", "shape": [ 28672, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 23518208 }, { "name": "model.layers.36.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25123840 }, { "name": "model.layers.36.post_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25131008 }, { "name": "model.layers.36.pre_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25138176 } ], "md5sum": "cfb294d0984a26effe0e1dbee22f708d" }, { "dataPath": "params_shard_110.bin", "format": "raw-shard", "nbytes": 25690112, "records": [ { "name": "model.layers.37.mlp.down_proj.q_weight", "shape": [ 3584, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25690112, "byteOffset": 0 } ], "md5sum": "2f49517cd11d503e5c03c50bfc60a517" }, { "dataPath": "params_shard_111.bin", "format": "raw-shard", "nbytes": 51380224, "records": [ { "name": "model.layers.37.mlp.gate_up_proj.q_weight", "shape": [ 28672, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 51380224, "byteOffset": 0 } ], "md5sum": "cdb42dcd5b2de120850ba8e64add011d" }, { "dataPath": "params_shard_112.bin", "format": "raw-shard", "nbytes": 25145344, "records": [ { "name": "model.layers.36.self_attn.qkv_proj.q_weight", "shape": [ 8192, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.36.self_attn.qkv_proj.q_scale", "shape": [ 8192, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 458752, "byteOffset": 14680064 }, { "name": "model.layers.36.self_attn.o_proj.q_weight", "shape": [ 3584, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 15138816 }, { "name": "model.layers.36.self_attn.o_proj.q_scale", "shape": [ 3584, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 229376, "byteOffset": 22478848 }, { "name": "model.layers.37.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 22708224 }, { "name": "model.layers.37.mlp.down_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 802816, "byteOffset": 22715392 }, { "name": "model.layers.37.mlp.gate_up_proj.q_scale", "shape": [ 28672, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 23518208 }, { "name": "model.layers.37.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25123840 }, { "name": "model.layers.37.post_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25131008 }, { "name": "model.layers.37.pre_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25138176 } ], "md5sum": "045ecdbbdebecae594dfb694abb5829f" }, { "dataPath": "params_shard_113.bin", "format": "raw-shard", "nbytes": 25690112, "records": [ { "name": "model.layers.38.mlp.down_proj.q_weight", "shape": [ 3584, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25690112, "byteOffset": 0 } ], "md5sum": "c1c54cefcd78a7d72e66e88a6d173b16" }, { "dataPath": "params_shard_114.bin", "format": "raw-shard", "nbytes": 51380224, "records": [ { "name": "model.layers.38.mlp.gate_up_proj.q_weight", "shape": [ 28672, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 51380224, "byteOffset": 0 } ], "md5sum": "2ca335c5f12896897bfab7229626f59a" }, { "dataPath": "params_shard_115.bin", "format": "raw-shard", "nbytes": 25145344, "records": [ { "name": "model.layers.37.self_attn.qkv_proj.q_weight", "shape": [ 8192, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.37.self_attn.qkv_proj.q_scale", "shape": [ 8192, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 458752, "byteOffset": 14680064 }, { "name": "model.layers.37.self_attn.o_proj.q_weight", "shape": [ 3584, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 15138816 }, { "name": "model.layers.37.self_attn.o_proj.q_scale", "shape": [ 3584, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 229376, "byteOffset": 22478848 }, { "name": "model.layers.38.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 22708224 }, { "name": "model.layers.38.mlp.down_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 802816, "byteOffset": 22715392 }, { "name": "model.layers.38.mlp.gate_up_proj.q_scale", "shape": [ 28672, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 23518208 }, { "name": "model.layers.38.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25123840 }, { "name": "model.layers.38.post_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25131008 }, { "name": "model.layers.38.pre_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25138176 } ], "md5sum": "4ca49ccdea1ac3d4cb79658e3752f724" }, { "dataPath": "params_shard_116.bin", "format": "raw-shard", "nbytes": 25690112, "records": [ { "name": "model.layers.39.mlp.down_proj.q_weight", "shape": [ 3584, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25690112, "byteOffset": 0 } ], "md5sum": "9810baf10126daa966665ddf645ee0f6" }, { "dataPath": "params_shard_117.bin", "format": "raw-shard", "nbytes": 51380224, "records": [ { "name": "model.layers.39.mlp.gate_up_proj.q_weight", "shape": [ 28672, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 51380224, "byteOffset": 0 } ], "md5sum": "ff624e7a06ab98bf0729170634d92321" }, { "dataPath": "params_shard_118.bin", "format": "raw-shard", "nbytes": 25145344, "records": [ { "name": "model.layers.38.self_attn.qkv_proj.q_weight", "shape": [ 8192, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.38.self_attn.qkv_proj.q_scale", "shape": [ 8192, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 458752, "byteOffset": 14680064 }, { "name": "model.layers.38.self_attn.o_proj.q_weight", "shape": [ 3584, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 15138816 }, { "name": "model.layers.38.self_attn.o_proj.q_scale", "shape": [ 3584, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 229376, "byteOffset": 22478848 }, { "name": "model.layers.39.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 22708224 }, { "name": "model.layers.39.mlp.down_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 802816, "byteOffset": 22715392 }, { "name": "model.layers.39.mlp.gate_up_proj.q_scale", "shape": [ 28672, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 23518208 }, { "name": "model.layers.39.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25123840 }, { "name": "model.layers.39.post_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25131008 }, { "name": "model.layers.39.pre_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25138176 } ], "md5sum": "e5f9eba44f9daaa3d9ebd23f3d370b06" }, { "dataPath": "params_shard_119.bin", "format": "raw-shard", "nbytes": 25690112, "records": [ { "name": "model.layers.40.mlp.down_proj.q_weight", "shape": [ 3584, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25690112, "byteOffset": 0 } ], "md5sum": "14413da31698c9c05755aae67b81d7c6" }, { "dataPath": "params_shard_120.bin", "format": "raw-shard", "nbytes": 51380224, "records": [ { "name": "model.layers.40.mlp.gate_up_proj.q_weight", "shape": [ 28672, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 51380224, "byteOffset": 0 } ], "md5sum": "3366e3e78f7779b2683594bf90f6d289" }, { "dataPath": "params_shard_121.bin", "format": "raw-shard", "nbytes": 25145344, "records": [ { "name": "model.layers.39.self_attn.qkv_proj.q_weight", "shape": [ 8192, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.39.self_attn.qkv_proj.q_scale", "shape": [ 8192, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 458752, "byteOffset": 14680064 }, { "name": "model.layers.39.self_attn.o_proj.q_weight", "shape": [ 3584, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 15138816 }, { "name": "model.layers.39.self_attn.o_proj.q_scale", "shape": [ 3584, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 229376, "byteOffset": 22478848 }, { "name": "model.layers.40.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 22708224 }, { "name": "model.layers.40.mlp.down_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 802816, "byteOffset": 22715392 }, { "name": "model.layers.40.mlp.gate_up_proj.q_scale", "shape": [ 28672, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 23518208 }, { "name": "model.layers.40.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25123840 }, { "name": "model.layers.40.post_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25131008 }, { "name": "model.layers.40.pre_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25138176 } ], "md5sum": "09d7a955c20847e33676d31db98e5363" }, { "dataPath": "params_shard_122.bin", "format": "raw-shard", "nbytes": 25690112, "records": [ { "name": "model.layers.41.mlp.down_proj.q_weight", "shape": [ 3584, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25690112, "byteOffset": 0 } ], "md5sum": "e5b62022e9b397779e786af1b00c113a" }, { "dataPath": "params_shard_123.bin", "format": "raw-shard", "nbytes": 51380224, "records": [ { "name": "model.layers.41.mlp.gate_up_proj.q_weight", "shape": [ 28672, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 51380224, "byteOffset": 0 } ], "md5sum": "85ec4ea85b1e541a4c8cb07cc8c6d8aa" }, { "dataPath": "params_shard_124.bin", "format": "raw-shard", "nbytes": 25145344, "records": [ { "name": "model.layers.40.self_attn.qkv_proj.q_weight", "shape": [ 8192, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.40.self_attn.qkv_proj.q_scale", "shape": [ 8192, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 458752, "byteOffset": 14680064 }, { "name": "model.layers.40.self_attn.o_proj.q_weight", "shape": [ 3584, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 15138816 }, { "name": "model.layers.40.self_attn.o_proj.q_scale", "shape": [ 3584, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 229376, "byteOffset": 22478848 }, { "name": "model.layers.41.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 22708224 }, { "name": "model.layers.41.mlp.down_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 802816, "byteOffset": 22715392 }, { "name": "model.layers.41.mlp.gate_up_proj.q_scale", "shape": [ 28672, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1605632, "byteOffset": 23518208 }, { "name": "model.layers.41.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25123840 }, { "name": "model.layers.41.post_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25131008 }, { "name": "model.layers.41.pre_feedforward_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 25138176 } ], "md5sum": "f772e027238c881c4cabba76bf10b911" }, { "dataPath": "params_shard_125.bin", "format": "raw-shard", "nbytes": 22715392, "records": [ { "name": "model.layers.41.self_attn.qkv_proj.q_weight", "shape": [ 8192, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.41.self_attn.qkv_proj.q_scale", "shape": [ 8192, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 458752, "byteOffset": 14680064 }, { "name": "model.layers.41.self_attn.o_proj.q_weight", "shape": [ 3584, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 15138816 }, { "name": "model.layers.41.self_attn.o_proj.q_scale", "shape": [ 3584, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 229376, "byteOffset": 22478848 }, { "name": "model.norm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 22708224 } ], "md5sum": "27bc965959cf441b5d38e13634bc59e0" } ] }