{ "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": "7e4576c07fce908093414ffff240dcdd" }, { "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": "00c1643c6db0043775eea25c0347c048" }, { "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": "c4a986b266763532c6973a1b30e0390b" }, { "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": "2bd8404ba9e600a2323889463dc347f8" }, { "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": "02d66213af174e3427edfd56e6e13c63" }, { "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": "6367d168e51818dcf6a872bdb0935542" }, { "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": "6da239745d2445631c4407af4b286d59" }, { "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": "ebc9fc8b55fdaa32f912f606549ff4f3" }, { "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": "8d0c6860ea429cd6a4f8f53477419cb0" }, { "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": "bd1b8619ee9a94aebfe5e21ad6e2a557" }, { "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": "ae3a7d695526c23fa87a36bfdaea405b" }, { "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": "c7d47c3f13924dec79b970c34fb056fa" }, { "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": "13ca9dbcbd4aea876b7227c110162bbc" }, { "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": "6c45ef1a9c3008514d3fbc2c2c9659a8" }, { "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": "d9ac9ce00694e02489f4bf4fb901a4cd" }, { "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": "b9b1284175837385f7ea29e345c97aef" }, { "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": "7e4a86a15bf53fb9b03e25214ca8c4a4" }, { "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": "96f3b0461f73301f7d2cc3c134a87a77" }, { "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": "dbc0cc340a7d84c41a09768f6de16a2d" }, { "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": "492cfe2c4e80517d4f77bb32dfe0a62e" }, { "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": "60878d4166f00677d136dd14ffd6eddd" }, { "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": "c96acb6aca828e8edfeb5adf01119691" }, { "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": "ccbf78f9d6c44cce084c25561dfe5ece" }, { "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": "366ddb796a4cd07d2d25d340247f14b5" }, { "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": "fd706cd3b59906f736599d83f4ea26c2" }, { "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": "cbea6e8f98bb99a057b22b754de50b02" }, { "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": "85a1b8047643b2c4f59b3ccd25f6e4ed" }, { "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": "5b609119a2aa433fe5d35d46ef55e79d" }, { "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": "2d2808c288c7a12674c8fd810020f224" }, { "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": "3c6d707e5a8381d0ab2f975855444e1a" }, { "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": "666beb5c0d2a184224870c1844e2b15c" }, { "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": "ffb974f535a08dbb1b09db3588ac331f" }, { "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": "8702fc30864ba1e5b2cc96b19f78e80c" }, { "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": "e7df01a804cd3ee366a3e324b76ae9db" }, { "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": "ba0ebc718f171323f4147ee48a587b31" }, { "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": "db61f9b2534c6e658ca16c28b0dde4e5" }, { "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": "0446e579abdf145b7734819cacfbf479" }, { "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": "5d6c682f3e589bd9165f379ed2eb1ab0" }, { "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": "16881e1e112e8ef0399aa4d44631eac9" }, { "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": "1c4fc0de06233f8781943972b80c759c" }, { "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": "6249596b05935b943f4d0426bf046766" }, { "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": "f98e8ccf2ae94a9e04b82d8e2d915fbf" }, { "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": "c86fbb8b626f17aac02f242c009b4256" }, { "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": "65204a656db2ad0825135b9aab30ddf5" }, { "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": "cf1d0e9078181963f9dea74316aa3b15" }, { "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": "9a4abd28c719d76c32d097904580f986" }, { "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": "b9a3874ba8a1e240665a0677d9a82ebe" }, { "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": "693658356398dc3505759c57cd4fe67a" }, { "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": "495e28b5d612e26afbba91cecb8a8aed" }, { "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": "0278e7f95743e2c812b02ccf40fadd28" }, { "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": "e760b01a3f06d3de82e1ceebaa21caa6" }, { "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": "abfc8789869eca5df3f30bca85cde824" }, { "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": "ebe7edce9304edb202feac9383bf9dec" }, { "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": "2c8140b356b912b6c8f84866d1c5c6ca" }, { "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": "ebb669c2d5e41f33f08fc561f1c2419e" }, { "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": "66c4be80268bed22c9fd0b70b43a8225" }, { "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": "e1e2849da778fdbe10f2ce58fe9ce40e" }, { "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": "e57768461b597fd4bfd6389da6697ccc" }, { "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": "03229f67029d25726791b10ff8262bcc" }, { "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": "9458c126f9aa59dba20e947c54cd2aa4" }, { "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": "5fd55f563827e23dd765bbb937f31d66" }, { "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": "4376b48c8e6284334b256028286509e2" }, { "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": "1e4987168561c0a5db9ebf44ee8a9424" }, { "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": "e773d9aa7ba372a225e21019a3fa38ec" }, { "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": "48276e528e22bc50cf279b6170bec8d6" }, { "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": "e3ed5287728d1004dd0461c0c4aef853" }, { "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": "41a8eba58b99ba0f148490b058ed7ec9" }, { "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": "172de04a197f3f18056abeff78854a7d" }, { "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": "f82fdd62509f3f9544ef3295a4b99fd6" }, { "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": "19ffc01115f69283e5b7a4509d4cc998" }, { "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": "9b0bde9a722959f698a5c772ea40c68a" }, { "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": "7c993228d7171070ff8dcc39547015e9" }, { "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": "9e15e8b3c52a28c2b2993ecb53e9049c" }, { "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": "ab716d4630d0588fb4bcc2018981d92a" }, { "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": "07fa4e32e4f3d75cf7b2326532b8a26f" }, { "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": "1057500304a6b3532bb3880307eea3e3" }, { "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": "6be78685a6e30368062ec1f73903402b" }, { "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": "a8037b2b6e28f0ddb288b94c1cc77c49" }, { "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": "25b20e44689a6b4ebb428f8cf3867538" }, { "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": "66b5f951d840b7a1cd29a0c936bf4aed" }, { "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": "43237e9e6a6b53f4797b074ef0a147da" }, { "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": "611c8761cef2d83624e3dd03bc08afe9" }, { "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": "afb85125e0d7190b4f7ae3d887399e66" }, { "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": "04be1e3a4a301e4e0cebbf8bec2f523f" }, { "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": "6c07c00c4c2270f790ab0218a5e037e7" }, { "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": "544d1ca7b904f5fc795e99359c9f3c62" }, { "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": "caa93e9336cc6379c466bac6eaaf66ab" }, { "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": "af505a1ee54e172a5896b06e9294936c" }, { "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": "d4eb2bbc3ce6eb01506061d4e0237532" }, { "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": "29b2b07fcbe7f192f81bca781959ab81" }, { "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": "9e8571de7c9cfbb388659073e3d025ed" }, { "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": "bd16c78b53b4f0a9c99f13b2544b11b0" }, { "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": "01353ad084cde0fefc9bc0e1f16d3dbb" }, { "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": "f8942297e2fa661a2f9d113dcea19f65" }, { "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": "e3c28134926f26f2d5186ed9efe334e0" }, { "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": "dab747801ab17eba5028560544162b92" }, { "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": "cba06d0b33815bd3c3f6c6de46112a0b" }, { "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": "a3ecc7eab584e9f268f2efc8a1ea286d" }, { "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": "c1f6ec0f7153295cc44cab84c075768d" }, { "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": "005171076f3dcb99b326dbea207fbd1c" }, { "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": "221f10e6dedb81a4308c60f8da2d34f0" }, { "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": "f9246a2c637e236530d8fafbcceccd49" }, { "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": "93f319f38eaaf077138819f24c37bc5c" }, { "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": "730dd51beece20e879b51d35c8852883" }, { "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": "9528a320655b41582c8c8a7f7143680b" }, { "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": "da2e2a9bf3b992a73934b17c74b88a8f" }, { "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": "453984ba9f09566e6f3c700d40de89e3" }, { "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": "5dc2f7f16fff5468b783d8eadbca6f6c" }, { "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": "262abad8708041b7a599322c4fe5d6fa" }, { "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": "6e519f081f7d31f914e9f1d40c57b4d6" }, { "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": "8bdb0b7a39b4f5d3b32963ee613e10bf" }, { "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": "1777d2c63e22eb17fb7e8085f11dd8a0" }, { "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": "6e042047505aba0ac55667379d36113c" }, { "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": "7ada24e4cb10cc2a5f443c9a26020c60" }, { "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": "57919085e78e3de309dd1cc79d569b63" }, { "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": "fb55db9c254adfc20d61fc13397c6de5" }, { "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": "95a73544dc84a886e36a33ffb9dda738" }, { "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": "bc074055cad926ae6f5361279335f9f9" }, { "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": "40c464d52a88511ce67efc54b4e5b806" }, { "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": "8008c7f263828a8138d0dc848780c502" }, { "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": "10074895a3b73b5aef4e57e7619e558a" }, { "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": "b14104498f64a730882381c68305ebc3" }, { "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": "7e89c9fbddd11221dc274adcfcde1a4c" }, { "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": "bad36775edec6f1510c34eb1e5f9bb76" }, { "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": "f4aceffe977520d8bfc1a4f6bf90b1f2" }, { "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": "62a5ae31004ad4bd648c8e6f643c0676" } ] }