| { | |
| "metadata": { | |
| "ParamSize": 311, | |
| "ParamBytes": 868547584.0, | |
| "BitsPerParam": 4.501079412165634 | |
| }, | |
| "records": [ | |
| { | |
| "dataPath": "params_shard_0.bin", | |
| "format": "raw-shard", | |
| "nbytes": 116686848, | |
| "records": [ | |
| { | |
| "name": "model.embed_tokens.q_weight", | |
| "shape": [ | |
| 151936, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 116686848, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "222b7275ffd8c1bc101d0869d74a4584" | |
| }, | |
| { | |
| "dataPath": "params_shard_1.bin", | |
| "format": "raw-shard", | |
| "nbytes": 22330368, | |
| "records": [ | |
| { | |
| "name": "model.embed_tokens.q_scale", | |
| "shape": [ | |
| 151936, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 14585856, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.0.input_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 14585856 | |
| }, | |
| { | |
| "name": "model.layers.0.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 1120 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6881280, | |
| "byteOffset": 14588928 | |
| }, | |
| { | |
| "name": "model.layers.0.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 280 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 860160, | |
| "byteOffset": 21470208 | |
| } | |
| ], | |
| "md5sum": "072f71ec0703b046b23cb5d37a3f3ddb" | |
| }, | |
| { | |
| "dataPath": "params_shard_2.bin", | |
| "format": "raw-shard", | |
| "nbytes": 26331136, | |
| "records": [ | |
| { | |
| "name": "model.layers.0.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 17920, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 13762560, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.0.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 17920, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1720320, | |
| "byteOffset": 13762560 | |
| }, | |
| { | |
| "name": "model.layers.0.post_attention_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 15482880 | |
| }, | |
| { | |
| "name": "model.layers.0.self_attn.c_attn.bias", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 15485952 | |
| }, | |
| { | |
| "name": "model.layers.0.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 2048, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1572864, | |
| "byteOffset": 15490048 | |
| }, | |
| { | |
| "name": "model.layers.0.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 2048, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 196608, | |
| "byteOffset": 17062912 | |
| }, | |
| { | |
| "name": "model.layers.0.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1179648, | |
| "byteOffset": 17259520 | |
| }, | |
| { | |
| "name": "model.layers.0.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 147456, | |
| "byteOffset": 18439168 | |
| }, | |
| { | |
| "name": "model.layers.1.input_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 18586624 | |
| }, | |
| { | |
| "name": "model.layers.1.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 1120 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6881280, | |
| "byteOffset": 18589696 | |
| }, | |
| { | |
| "name": "model.layers.1.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 280 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 860160, | |
| "byteOffset": 25470976 | |
| } | |
| ], | |
| "md5sum": "a9baa820efe9cf5058524291ed4d2e82" | |
| }, | |
| { | |
| "dataPath": "params_shard_3.bin", | |
| "format": "raw-shard", | |
| "nbytes": 26331136, | |
| "records": [ | |
| { | |
| "name": "model.layers.1.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 17920, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 13762560, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.1.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 17920, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1720320, | |
| "byteOffset": 13762560 | |
| }, | |
| { | |
| "name": "model.layers.1.post_attention_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 15482880 | |
| }, | |
| { | |
| "name": "model.layers.1.self_attn.c_attn.bias", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 15485952 | |
| }, | |
| { | |
| "name": "model.layers.1.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 2048, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1572864, | |
| "byteOffset": 15490048 | |
| }, | |
| { | |
| "name": "model.layers.1.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 2048, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 196608, | |
| "byteOffset": 17062912 | |
| }, | |
| { | |
| "name": "model.layers.1.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1179648, | |
| "byteOffset": 17259520 | |
| }, | |
| { | |
| "name": "model.layers.1.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 147456, | |
| "byteOffset": 18439168 | |
| }, | |
| { | |
| "name": "model.layers.10.input_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 18586624 | |
| }, | |
| { | |
| "name": "model.layers.10.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 1120 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6881280, | |
| "byteOffset": 18589696 | |
| }, | |
| { | |
| "name": "model.layers.10.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 280 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 860160, | |
| "byteOffset": 25470976 | |
| } | |
| ], | |
| "md5sum": "f73b0fd37d045e9dca85f6b7b5d23a38" | |
| }, | |
| { | |
| "dataPath": "params_shard_4.bin", | |
| "format": "raw-shard", | |
| "nbytes": 26331136, | |
| "records": [ | |
| { | |
| "name": "model.layers.10.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 17920, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 13762560, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.10.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 17920, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1720320, | |
| "byteOffset": 13762560 | |
| }, | |
| { | |
| "name": "model.layers.10.post_attention_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 15482880 | |
| }, | |
| { | |
| "name": "model.layers.10.self_attn.c_attn.bias", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 15485952 | |
| }, | |
| { | |
| "name": "model.layers.10.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 2048, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1572864, | |
| "byteOffset": 15490048 | |
| }, | |
| { | |
| "name": "model.layers.10.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 2048, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 196608, | |
| "byteOffset": 17062912 | |
| }, | |
| { | |
| "name": "model.layers.10.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1179648, | |
| "byteOffset": 17259520 | |
| }, | |
| { | |
| "name": "model.layers.10.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 147456, | |
| "byteOffset": 18439168 | |
| }, | |
| { | |
| "name": "model.layers.11.input_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 18586624 | |
| }, | |
| { | |
| "name": "model.layers.11.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 1120 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6881280, | |
| "byteOffset": 18589696 | |
| }, | |
| { | |
| "name": "model.layers.11.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 280 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 860160, | |
| "byteOffset": 25470976 | |
| } | |
| ], | |
| "md5sum": "e4e129a8eaeb6145195f93de4711785b" | |
| }, | |
| { | |
| "dataPath": "params_shard_5.bin", | |
| "format": "raw-shard", | |
| "nbytes": 26331136, | |
| "records": [ | |
| { | |
| "name": "model.layers.11.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 17920, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 13762560, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.11.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 17920, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1720320, | |
| "byteOffset": 13762560 | |
| }, | |
| { | |
| "name": "model.layers.11.post_attention_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 15482880 | |
| }, | |
| { | |
| "name": "model.layers.11.self_attn.c_attn.bias", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 15485952 | |
| }, | |
| { | |
| "name": "model.layers.11.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 2048, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1572864, | |
| "byteOffset": 15490048 | |
| }, | |
| { | |
| "name": "model.layers.11.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 2048, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 196608, | |
| "byteOffset": 17062912 | |
| }, | |
| { | |
| "name": "model.layers.11.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1179648, | |
| "byteOffset": 17259520 | |
| }, | |
| { | |
| "name": "model.layers.11.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 147456, | |
| "byteOffset": 18439168 | |
| }, | |
| { | |
| "name": "model.layers.12.input_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 18586624 | |
| }, | |
| { | |
| "name": "model.layers.12.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 1120 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6881280, | |
| "byteOffset": 18589696 | |
| }, | |
| { | |
| "name": "model.layers.12.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 280 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 860160, | |
| "byteOffset": 25470976 | |
| } | |
| ], | |
| "md5sum": "67791807e26cef5a5c05ce2517ee7835" | |
| }, | |
| { | |
| "dataPath": "params_shard_6.bin", | |
| "format": "raw-shard", | |
| "nbytes": 26331136, | |
| "records": [ | |
| { | |
| "name": "model.layers.12.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 17920, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 13762560, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.12.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 17920, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1720320, | |
| "byteOffset": 13762560 | |
| }, | |
| { | |
| "name": "model.layers.12.post_attention_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 15482880 | |
| }, | |
| { | |
| "name": "model.layers.12.self_attn.c_attn.bias", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 15485952 | |
| }, | |
| { | |
| "name": "model.layers.12.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 2048, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1572864, | |
| "byteOffset": 15490048 | |
| }, | |
| { | |
| "name": "model.layers.12.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 2048, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 196608, | |
| "byteOffset": 17062912 | |
| }, | |
| { | |
| "name": "model.layers.12.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1179648, | |
| "byteOffset": 17259520 | |
| }, | |
| { | |
| "name": "model.layers.12.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 147456, | |
| "byteOffset": 18439168 | |
| }, | |
| { | |
| "name": "model.layers.13.input_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 18586624 | |
| }, | |
| { | |
| "name": "model.layers.13.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 1120 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6881280, | |
| "byteOffset": 18589696 | |
| }, | |
| { | |
| "name": "model.layers.13.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 280 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 860160, | |
| "byteOffset": 25470976 | |
| } | |
| ], | |
| "md5sum": "4acec95395a8806a12ab45f4af3d8acb" | |
| }, | |
| { | |
| "dataPath": "params_shard_7.bin", | |
| "format": "raw-shard", | |
| "nbytes": 26331136, | |
| "records": [ | |
| { | |
| "name": "model.layers.13.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 17920, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 13762560, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.13.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 17920, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1720320, | |
| "byteOffset": 13762560 | |
| }, | |
| { | |
| "name": "model.layers.13.post_attention_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 15482880 | |
| }, | |
| { | |
| "name": "model.layers.13.self_attn.c_attn.bias", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 15485952 | |
| }, | |
| { | |
| "name": "model.layers.13.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 2048, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1572864, | |
| "byteOffset": 15490048 | |
| }, | |
| { | |
| "name": "model.layers.13.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 2048, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 196608, | |
| "byteOffset": 17062912 | |
| }, | |
| { | |
| "name": "model.layers.13.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1179648, | |
| "byteOffset": 17259520 | |
| }, | |
| { | |
| "name": "model.layers.13.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 147456, | |
| "byteOffset": 18439168 | |
| }, | |
| { | |
| "name": "model.layers.14.input_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 18586624 | |
| }, | |
| { | |
| "name": "model.layers.14.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 1120 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6881280, | |
| "byteOffset": 18589696 | |
| }, | |
| { | |
| "name": "model.layers.14.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 280 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 860160, | |
| "byteOffset": 25470976 | |
| } | |
| ], | |
| "md5sum": "5724a12932499c66eb6d533bca971b0d" | |
| }, | |
| { | |
| "dataPath": "params_shard_8.bin", | |
| "format": "raw-shard", | |
| "nbytes": 26331136, | |
| "records": [ | |
| { | |
| "name": "model.layers.14.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 17920, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 13762560, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.14.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 17920, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1720320, | |
| "byteOffset": 13762560 | |
| }, | |
| { | |
| "name": "model.layers.14.post_attention_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 15482880 | |
| }, | |
| { | |
| "name": "model.layers.14.self_attn.c_attn.bias", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 15485952 | |
| }, | |
| { | |
| "name": "model.layers.14.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 2048, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1572864, | |
| "byteOffset": 15490048 | |
| }, | |
| { | |
| "name": "model.layers.14.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 2048, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 196608, | |
| "byteOffset": 17062912 | |
| }, | |
| { | |
| "name": "model.layers.14.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1179648, | |
| "byteOffset": 17259520 | |
| }, | |
| { | |
| "name": "model.layers.14.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 147456, | |
| "byteOffset": 18439168 | |
| }, | |
| { | |
| "name": "model.layers.15.input_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 18586624 | |
| }, | |
| { | |
| "name": "model.layers.15.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 1120 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6881280, | |
| "byteOffset": 18589696 | |
| }, | |
| { | |
| "name": "model.layers.15.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 280 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 860160, | |
| "byteOffset": 25470976 | |
| } | |
| ], | |
| "md5sum": "d25739ece3a272000923447e0ecff7cb" | |
| }, | |
| { | |
| "dataPath": "params_shard_9.bin", | |
| "format": "raw-shard", | |
| "nbytes": 26331136, | |
| "records": [ | |
| { | |
| "name": "model.layers.15.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 17920, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 13762560, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.15.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 17920, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1720320, | |
| "byteOffset": 13762560 | |
| }, | |
| { | |
| "name": "model.layers.15.post_attention_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 15482880 | |
| }, | |
| { | |
| "name": "model.layers.15.self_attn.c_attn.bias", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 15485952 | |
| }, | |
| { | |
| "name": "model.layers.15.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 2048, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1572864, | |
| "byteOffset": 15490048 | |
| }, | |
| { | |
| "name": "model.layers.15.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 2048, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 196608, | |
| "byteOffset": 17062912 | |
| }, | |
| { | |
| "name": "model.layers.15.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1179648, | |
| "byteOffset": 17259520 | |
| }, | |
| { | |
| "name": "model.layers.15.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 147456, | |
| "byteOffset": 18439168 | |
| }, | |
| { | |
| "name": "model.layers.16.input_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 18586624 | |
| }, | |
| { | |
| "name": "model.layers.16.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 1120 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6881280, | |
| "byteOffset": 18589696 | |
| }, | |
| { | |
| "name": "model.layers.16.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 280 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 860160, | |
| "byteOffset": 25470976 | |
| } | |
| ], | |
| "md5sum": "468fe545ad657babc7c3ee3174a50faf" | |
| }, | |
| { | |
| "dataPath": "params_shard_10.bin", | |
| "format": "raw-shard", | |
| "nbytes": 26331136, | |
| "records": [ | |
| { | |
| "name": "model.layers.16.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 17920, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 13762560, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.16.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 17920, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1720320, | |
| "byteOffset": 13762560 | |
| }, | |
| { | |
| "name": "model.layers.16.post_attention_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 15482880 | |
| }, | |
| { | |
| "name": "model.layers.16.self_attn.c_attn.bias", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 15485952 | |
| }, | |
| { | |
| "name": "model.layers.16.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 2048, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1572864, | |
| "byteOffset": 15490048 | |
| }, | |
| { | |
| "name": "model.layers.16.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 2048, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 196608, | |
| "byteOffset": 17062912 | |
| }, | |
| { | |
| "name": "model.layers.16.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1179648, | |
| "byteOffset": 17259520 | |
| }, | |
| { | |
| "name": "model.layers.16.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 147456, | |
| "byteOffset": 18439168 | |
| }, | |
| { | |
| "name": "model.layers.17.input_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 18586624 | |
| }, | |
| { | |
| "name": "model.layers.17.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 1120 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6881280, | |
| "byteOffset": 18589696 | |
| }, | |
| { | |
| "name": "model.layers.17.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 280 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 860160, | |
| "byteOffset": 25470976 | |
| } | |
| ], | |
| "md5sum": "744d3f1b72b223ce76e5810179f3a568" | |
| }, | |
| { | |
| "dataPath": "params_shard_11.bin", | |
| "format": "raw-shard", | |
| "nbytes": 26331136, | |
| "records": [ | |
| { | |
| "name": "model.layers.17.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 17920, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 13762560, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.17.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 17920, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1720320, | |
| "byteOffset": 13762560 | |
| }, | |
| { | |
| "name": "model.layers.17.post_attention_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 15482880 | |
| }, | |
| { | |
| "name": "model.layers.17.self_attn.c_attn.bias", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 15485952 | |
| }, | |
| { | |
| "name": "model.layers.17.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 2048, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1572864, | |
| "byteOffset": 15490048 | |
| }, | |
| { | |
| "name": "model.layers.17.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 2048, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 196608, | |
| "byteOffset": 17062912 | |
| }, | |
| { | |
| "name": "model.layers.17.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1179648, | |
| "byteOffset": 17259520 | |
| }, | |
| { | |
| "name": "model.layers.17.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 147456, | |
| "byteOffset": 18439168 | |
| }, | |
| { | |
| "name": "model.layers.18.input_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 18586624 | |
| }, | |
| { | |
| "name": "model.layers.18.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 1120 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6881280, | |
| "byteOffset": 18589696 | |
| }, | |
| { | |
| "name": "model.layers.18.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 280 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 860160, | |
| "byteOffset": 25470976 | |
| } | |
| ], | |
| "md5sum": "b1065cb46de4bcf9496e3c4ed2e5393b" | |
| }, | |
| { | |
| "dataPath": "params_shard_12.bin", | |
| "format": "raw-shard", | |
| "nbytes": 26331136, | |
| "records": [ | |
| { | |
| "name": "model.layers.18.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 17920, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 13762560, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.18.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 17920, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1720320, | |
| "byteOffset": 13762560 | |
| }, | |
| { | |
| "name": "model.layers.18.post_attention_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 15482880 | |
| }, | |
| { | |
| "name": "model.layers.18.self_attn.c_attn.bias", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 15485952 | |
| }, | |
| { | |
| "name": "model.layers.18.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 2048, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1572864, | |
| "byteOffset": 15490048 | |
| }, | |
| { | |
| "name": "model.layers.18.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 2048, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 196608, | |
| "byteOffset": 17062912 | |
| }, | |
| { | |
| "name": "model.layers.18.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1179648, | |
| "byteOffset": 17259520 | |
| }, | |
| { | |
| "name": "model.layers.18.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 147456, | |
| "byteOffset": 18439168 | |
| }, | |
| { | |
| "name": "model.layers.19.input_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 18586624 | |
| }, | |
| { | |
| "name": "model.layers.19.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 1120 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6881280, | |
| "byteOffset": 18589696 | |
| }, | |
| { | |
| "name": "model.layers.19.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 280 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 860160, | |
| "byteOffset": 25470976 | |
| } | |
| ], | |
| "md5sum": "d51494c4bbac94e56bc49de01304be89" | |
| }, | |
| { | |
| "dataPath": "params_shard_13.bin", | |
| "format": "raw-shard", | |
| "nbytes": 26331136, | |
| "records": [ | |
| { | |
| "name": "model.layers.19.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 17920, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 13762560, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.19.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 17920, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1720320, | |
| "byteOffset": 13762560 | |
| }, | |
| { | |
| "name": "model.layers.19.post_attention_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 15482880 | |
| }, | |
| { | |
| "name": "model.layers.19.self_attn.c_attn.bias", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 15485952 | |
| }, | |
| { | |
| "name": "model.layers.19.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 2048, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1572864, | |
| "byteOffset": 15490048 | |
| }, | |
| { | |
| "name": "model.layers.19.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 2048, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 196608, | |
| "byteOffset": 17062912 | |
| }, | |
| { | |
| "name": "model.layers.19.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1179648, | |
| "byteOffset": 17259520 | |
| }, | |
| { | |
| "name": "model.layers.19.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 147456, | |
| "byteOffset": 18439168 | |
| }, | |
| { | |
| "name": "model.layers.2.input_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 18586624 | |
| }, | |
| { | |
| "name": "model.layers.2.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 1120 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6881280, | |
| "byteOffset": 18589696 | |
| }, | |
| { | |
| "name": "model.layers.2.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 280 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 860160, | |
| "byteOffset": 25470976 | |
| } | |
| ], | |
| "md5sum": "9bdd4c4172d7e17bb7a3b479dae58bdd" | |
| }, | |
| { | |
| "dataPath": "params_shard_14.bin", | |
| "format": "raw-shard", | |
| "nbytes": 26331136, | |
| "records": [ | |
| { | |
| "name": "model.layers.2.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 17920, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 13762560, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.2.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 17920, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1720320, | |
| "byteOffset": 13762560 | |
| }, | |
| { | |
| "name": "model.layers.2.post_attention_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 15482880 | |
| }, | |
| { | |
| "name": "model.layers.2.self_attn.c_attn.bias", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 15485952 | |
| }, | |
| { | |
| "name": "model.layers.2.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 2048, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1572864, | |
| "byteOffset": 15490048 | |
| }, | |
| { | |
| "name": "model.layers.2.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 2048, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 196608, | |
| "byteOffset": 17062912 | |
| }, | |
| { | |
| "name": "model.layers.2.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1179648, | |
| "byteOffset": 17259520 | |
| }, | |
| { | |
| "name": "model.layers.2.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 147456, | |
| "byteOffset": 18439168 | |
| }, | |
| { | |
| "name": "model.layers.20.input_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 18586624 | |
| }, | |
| { | |
| "name": "model.layers.20.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 1120 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6881280, | |
| "byteOffset": 18589696 | |
| }, | |
| { | |
| "name": "model.layers.20.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 280 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 860160, | |
| "byteOffset": 25470976 | |
| } | |
| ], | |
| "md5sum": "227a8bcd1bba0b2c9e7e0d6721eca69c" | |
| }, | |
| { | |
| "dataPath": "params_shard_15.bin", | |
| "format": "raw-shard", | |
| "nbytes": 26331136, | |
| "records": [ | |
| { | |
| "name": "model.layers.20.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 17920, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 13762560, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.20.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 17920, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1720320, | |
| "byteOffset": 13762560 | |
| }, | |
| { | |
| "name": "model.layers.20.post_attention_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 15482880 | |
| }, | |
| { | |
| "name": "model.layers.20.self_attn.c_attn.bias", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 15485952 | |
| }, | |
| { | |
| "name": "model.layers.20.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 2048, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1572864, | |
| "byteOffset": 15490048 | |
| }, | |
| { | |
| "name": "model.layers.20.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 2048, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 196608, | |
| "byteOffset": 17062912 | |
| }, | |
| { | |
| "name": "model.layers.20.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1179648, | |
| "byteOffset": 17259520 | |
| }, | |
| { | |
| "name": "model.layers.20.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 147456, | |
| "byteOffset": 18439168 | |
| }, | |
| { | |
| "name": "model.layers.21.input_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 18586624 | |
| }, | |
| { | |
| "name": "model.layers.21.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 1120 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6881280, | |
| "byteOffset": 18589696 | |
| }, | |
| { | |
| "name": "model.layers.21.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 280 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 860160, | |
| "byteOffset": 25470976 | |
| } | |
| ], | |
| "md5sum": "ee148f8c8aa4b2f38da304155ad6ae34" | |
| }, | |
| { | |
| "dataPath": "params_shard_16.bin", | |
| "format": "raw-shard", | |
| "nbytes": 26331136, | |
| "records": [ | |
| { | |
| "name": "model.layers.21.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 17920, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 13762560, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.21.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 17920, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1720320, | |
| "byteOffset": 13762560 | |
| }, | |
| { | |
| "name": "model.layers.21.post_attention_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 15482880 | |
| }, | |
| { | |
| "name": "model.layers.21.self_attn.c_attn.bias", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 15485952 | |
| }, | |
| { | |
| "name": "model.layers.21.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 2048, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1572864, | |
| "byteOffset": 15490048 | |
| }, | |
| { | |
| "name": "model.layers.21.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 2048, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 196608, | |
| "byteOffset": 17062912 | |
| }, | |
| { | |
| "name": "model.layers.21.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1179648, | |
| "byteOffset": 17259520 | |
| }, | |
| { | |
| "name": "model.layers.21.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 147456, | |
| "byteOffset": 18439168 | |
| }, | |
| { | |
| "name": "model.layers.22.input_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 18586624 | |
| }, | |
| { | |
| "name": "model.layers.22.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 1120 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6881280, | |
| "byteOffset": 18589696 | |
| }, | |
| { | |
| "name": "model.layers.22.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 280 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 860160, | |
| "byteOffset": 25470976 | |
| } | |
| ], | |
| "md5sum": "a745ac08ce0709bf7c3c301025cf98f0" | |
| }, | |
| { | |
| "dataPath": "params_shard_17.bin", | |
| "format": "raw-shard", | |
| "nbytes": 26331136, | |
| "records": [ | |
| { | |
| "name": "model.layers.22.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 17920, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 13762560, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.22.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 17920, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1720320, | |
| "byteOffset": 13762560 | |
| }, | |
| { | |
| "name": "model.layers.22.post_attention_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 15482880 | |
| }, | |
| { | |
| "name": "model.layers.22.self_attn.c_attn.bias", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 15485952 | |
| }, | |
| { | |
| "name": "model.layers.22.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 2048, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1572864, | |
| "byteOffset": 15490048 | |
| }, | |
| { | |
| "name": "model.layers.22.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 2048, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 196608, | |
| "byteOffset": 17062912 | |
| }, | |
| { | |
| "name": "model.layers.22.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1179648, | |
| "byteOffset": 17259520 | |
| }, | |
| { | |
| "name": "model.layers.22.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 147456, | |
| "byteOffset": 18439168 | |
| }, | |
| { | |
| "name": "model.layers.23.input_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 18586624 | |
| }, | |
| { | |
| "name": "model.layers.23.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 1120 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6881280, | |
| "byteOffset": 18589696 | |
| }, | |
| { | |
| "name": "model.layers.23.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 280 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 860160, | |
| "byteOffset": 25470976 | |
| } | |
| ], | |
| "md5sum": "6727c773941120f1e59f5e9e0bb9e7f4" | |
| }, | |
| { | |
| "dataPath": "params_shard_18.bin", | |
| "format": "raw-shard", | |
| "nbytes": 26331136, | |
| "records": [ | |
| { | |
| "name": "model.layers.23.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 17920, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 13762560, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.23.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 17920, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1720320, | |
| "byteOffset": 13762560 | |
| }, | |
| { | |
| "name": "model.layers.23.post_attention_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 15482880 | |
| }, | |
| { | |
| "name": "model.layers.23.self_attn.c_attn.bias", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 15485952 | |
| }, | |
| { | |
| "name": "model.layers.23.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 2048, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1572864, | |
| "byteOffset": 15490048 | |
| }, | |
| { | |
| "name": "model.layers.23.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 2048, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 196608, | |
| "byteOffset": 17062912 | |
| }, | |
| { | |
| "name": "model.layers.23.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1179648, | |
| "byteOffset": 17259520 | |
| }, | |
| { | |
| "name": "model.layers.23.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 147456, | |
| "byteOffset": 18439168 | |
| }, | |
| { | |
| "name": "model.layers.24.input_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 18586624 | |
| }, | |
| { | |
| "name": "model.layers.24.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 1120 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6881280, | |
| "byteOffset": 18589696 | |
| }, | |
| { | |
| "name": "model.layers.24.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 280 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 860160, | |
| "byteOffset": 25470976 | |
| } | |
| ], | |
| "md5sum": "4cde459316fe13ee7e024fce73eaa8da" | |
| }, | |
| { | |
| "dataPath": "params_shard_19.bin", | |
| "format": "raw-shard", | |
| "nbytes": 26331136, | |
| "records": [ | |
| { | |
| "name": "model.layers.24.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 17920, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 13762560, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.24.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 17920, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1720320, | |
| "byteOffset": 13762560 | |
| }, | |
| { | |
| "name": "model.layers.24.post_attention_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 15482880 | |
| }, | |
| { | |
| "name": "model.layers.24.self_attn.c_attn.bias", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 15485952 | |
| }, | |
| { | |
| "name": "model.layers.24.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 2048, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1572864, | |
| "byteOffset": 15490048 | |
| }, | |
| { | |
| "name": "model.layers.24.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 2048, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 196608, | |
| "byteOffset": 17062912 | |
| }, | |
| { | |
| "name": "model.layers.24.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1179648, | |
| "byteOffset": 17259520 | |
| }, | |
| { | |
| "name": "model.layers.24.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 147456, | |
| "byteOffset": 18439168 | |
| }, | |
| { | |
| "name": "model.layers.25.input_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 18586624 | |
| }, | |
| { | |
| "name": "model.layers.25.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 1120 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6881280, | |
| "byteOffset": 18589696 | |
| }, | |
| { | |
| "name": "model.layers.25.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 280 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 860160, | |
| "byteOffset": 25470976 | |
| } | |
| ], | |
| "md5sum": "3679d417950208882cf12e6f7c4b6e19" | |
| }, | |
| { | |
| "dataPath": "params_shard_20.bin", | |
| "format": "raw-shard", | |
| "nbytes": 26331136, | |
| "records": [ | |
| { | |
| "name": "model.layers.25.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 17920, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 13762560, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.25.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 17920, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1720320, | |
| "byteOffset": 13762560 | |
| }, | |
| { | |
| "name": "model.layers.25.post_attention_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 15482880 | |
| }, | |
| { | |
| "name": "model.layers.25.self_attn.c_attn.bias", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 15485952 | |
| }, | |
| { | |
| "name": "model.layers.25.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 2048, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1572864, | |
| "byteOffset": 15490048 | |
| }, | |
| { | |
| "name": "model.layers.25.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 2048, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 196608, | |
| "byteOffset": 17062912 | |
| }, | |
| { | |
| "name": "model.layers.25.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1179648, | |
| "byteOffset": 17259520 | |
| }, | |
| { | |
| "name": "model.layers.25.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 147456, | |
| "byteOffset": 18439168 | |
| }, | |
| { | |
| "name": "model.layers.26.input_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 18586624 | |
| }, | |
| { | |
| "name": "model.layers.26.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 1120 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6881280, | |
| "byteOffset": 18589696 | |
| }, | |
| { | |
| "name": "model.layers.26.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 280 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 860160, | |
| "byteOffset": 25470976 | |
| } | |
| ], | |
| "md5sum": "b14c23e7fa1477cbcddcb6c3c49318bc" | |
| }, | |
| { | |
| "dataPath": "params_shard_21.bin", | |
| "format": "raw-shard", | |
| "nbytes": 26331136, | |
| "records": [ | |
| { | |
| "name": "model.layers.26.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 17920, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 13762560, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.26.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 17920, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1720320, | |
| "byteOffset": 13762560 | |
| }, | |
| { | |
| "name": "model.layers.26.post_attention_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 15482880 | |
| }, | |
| { | |
| "name": "model.layers.26.self_attn.c_attn.bias", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 15485952 | |
| }, | |
| { | |
| "name": "model.layers.26.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 2048, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1572864, | |
| "byteOffset": 15490048 | |
| }, | |
| { | |
| "name": "model.layers.26.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 2048, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 196608, | |
| "byteOffset": 17062912 | |
| }, | |
| { | |
| "name": "model.layers.26.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1179648, | |
| "byteOffset": 17259520 | |
| }, | |
| { | |
| "name": "model.layers.26.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 147456, | |
| "byteOffset": 18439168 | |
| }, | |
| { | |
| "name": "model.layers.27.input_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 18586624 | |
| }, | |
| { | |
| "name": "model.layers.27.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 1120 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6881280, | |
| "byteOffset": 18589696 | |
| }, | |
| { | |
| "name": "model.layers.27.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 280 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 860160, | |
| "byteOffset": 25470976 | |
| } | |
| ], | |
| "md5sum": "af57725d3149f41f9fa16896962e52e0" | |
| }, | |
| { | |
| "dataPath": "params_shard_22.bin", | |
| "format": "raw-shard", | |
| "nbytes": 26331136, | |
| "records": [ | |
| { | |
| "name": "model.layers.27.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 17920, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 13762560, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.27.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 17920, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1720320, | |
| "byteOffset": 13762560 | |
| }, | |
| { | |
| "name": "model.layers.27.post_attention_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 15482880 | |
| }, | |
| { | |
| "name": "model.layers.27.self_attn.c_attn.bias", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 15485952 | |
| }, | |
| { | |
| "name": "model.layers.27.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 2048, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1572864, | |
| "byteOffset": 15490048 | |
| }, | |
| { | |
| "name": "model.layers.27.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 2048, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 196608, | |
| "byteOffset": 17062912 | |
| }, | |
| { | |
| "name": "model.layers.27.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1179648, | |
| "byteOffset": 17259520 | |
| }, | |
| { | |
| "name": "model.layers.27.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 147456, | |
| "byteOffset": 18439168 | |
| }, | |
| { | |
| "name": "model.layers.3.input_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 18586624 | |
| }, | |
| { | |
| "name": "model.layers.3.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 1120 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6881280, | |
| "byteOffset": 18589696 | |
| }, | |
| { | |
| "name": "model.layers.3.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 280 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 860160, | |
| "byteOffset": 25470976 | |
| } | |
| ], | |
| "md5sum": "ba0a573cc09af859ca1f979af8119419" | |
| }, | |
| { | |
| "dataPath": "params_shard_23.bin", | |
| "format": "raw-shard", | |
| "nbytes": 26331136, | |
| "records": [ | |
| { | |
| "name": "model.layers.3.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 17920, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 13762560, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.3.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 17920, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1720320, | |
| "byteOffset": 13762560 | |
| }, | |
| { | |
| "name": "model.layers.3.post_attention_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 15482880 | |
| }, | |
| { | |
| "name": "model.layers.3.self_attn.c_attn.bias", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 15485952 | |
| }, | |
| { | |
| "name": "model.layers.3.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 2048, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1572864, | |
| "byteOffset": 15490048 | |
| }, | |
| { | |
| "name": "model.layers.3.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 2048, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 196608, | |
| "byteOffset": 17062912 | |
| }, | |
| { | |
| "name": "model.layers.3.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1179648, | |
| "byteOffset": 17259520 | |
| }, | |
| { | |
| "name": "model.layers.3.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 147456, | |
| "byteOffset": 18439168 | |
| }, | |
| { | |
| "name": "model.layers.4.input_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 18586624 | |
| }, | |
| { | |
| "name": "model.layers.4.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 1120 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6881280, | |
| "byteOffset": 18589696 | |
| }, | |
| { | |
| "name": "model.layers.4.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 280 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 860160, | |
| "byteOffset": 25470976 | |
| } | |
| ], | |
| "md5sum": "ffe0ab479f5069499f56431434c15eb3" | |
| }, | |
| { | |
| "dataPath": "params_shard_24.bin", | |
| "format": "raw-shard", | |
| "nbytes": 26331136, | |
| "records": [ | |
| { | |
| "name": "model.layers.4.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 17920, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 13762560, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.4.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 17920, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1720320, | |
| "byteOffset": 13762560 | |
| }, | |
| { | |
| "name": "model.layers.4.post_attention_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 15482880 | |
| }, | |
| { | |
| "name": "model.layers.4.self_attn.c_attn.bias", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 15485952 | |
| }, | |
| { | |
| "name": "model.layers.4.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 2048, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1572864, | |
| "byteOffset": 15490048 | |
| }, | |
| { | |
| "name": "model.layers.4.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 2048, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 196608, | |
| "byteOffset": 17062912 | |
| }, | |
| { | |
| "name": "model.layers.4.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1179648, | |
| "byteOffset": 17259520 | |
| }, | |
| { | |
| "name": "model.layers.4.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 147456, | |
| "byteOffset": 18439168 | |
| }, | |
| { | |
| "name": "model.layers.5.input_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 18586624 | |
| }, | |
| { | |
| "name": "model.layers.5.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 1120 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6881280, | |
| "byteOffset": 18589696 | |
| }, | |
| { | |
| "name": "model.layers.5.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 280 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 860160, | |
| "byteOffset": 25470976 | |
| } | |
| ], | |
| "md5sum": "4e8f1097041041b974507cad792ed6e2" | |
| }, | |
| { | |
| "dataPath": "params_shard_25.bin", | |
| "format": "raw-shard", | |
| "nbytes": 26331136, | |
| "records": [ | |
| { | |
| "name": "model.layers.5.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 17920, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 13762560, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.5.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 17920, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1720320, | |
| "byteOffset": 13762560 | |
| }, | |
| { | |
| "name": "model.layers.5.post_attention_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 15482880 | |
| }, | |
| { | |
| "name": "model.layers.5.self_attn.c_attn.bias", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 15485952 | |
| }, | |
| { | |
| "name": "model.layers.5.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 2048, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1572864, | |
| "byteOffset": 15490048 | |
| }, | |
| { | |
| "name": "model.layers.5.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 2048, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 196608, | |
| "byteOffset": 17062912 | |
| }, | |
| { | |
| "name": "model.layers.5.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1179648, | |
| "byteOffset": 17259520 | |
| }, | |
| { | |
| "name": "model.layers.5.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 147456, | |
| "byteOffset": 18439168 | |
| }, | |
| { | |
| "name": "model.layers.6.input_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 18586624 | |
| }, | |
| { | |
| "name": "model.layers.6.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 1120 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6881280, | |
| "byteOffset": 18589696 | |
| }, | |
| { | |
| "name": "model.layers.6.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 280 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 860160, | |
| "byteOffset": 25470976 | |
| } | |
| ], | |
| "md5sum": "7a965a229b4e3cccd7c683ae69a39828" | |
| }, | |
| { | |
| "dataPath": "params_shard_26.bin", | |
| "format": "raw-shard", | |
| "nbytes": 26331136, | |
| "records": [ | |
| { | |
| "name": "model.layers.6.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 17920, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 13762560, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.6.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 17920, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1720320, | |
| "byteOffset": 13762560 | |
| }, | |
| { | |
| "name": "model.layers.6.post_attention_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 15482880 | |
| }, | |
| { | |
| "name": "model.layers.6.self_attn.c_attn.bias", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 15485952 | |
| }, | |
| { | |
| "name": "model.layers.6.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 2048, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1572864, | |
| "byteOffset": 15490048 | |
| }, | |
| { | |
| "name": "model.layers.6.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 2048, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 196608, | |
| "byteOffset": 17062912 | |
| }, | |
| { | |
| "name": "model.layers.6.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1179648, | |
| "byteOffset": 17259520 | |
| }, | |
| { | |
| "name": "model.layers.6.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 147456, | |
| "byteOffset": 18439168 | |
| }, | |
| { | |
| "name": "model.layers.7.input_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 18586624 | |
| }, | |
| { | |
| "name": "model.layers.7.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 1120 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6881280, | |
| "byteOffset": 18589696 | |
| }, | |
| { | |
| "name": "model.layers.7.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 280 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 860160, | |
| "byteOffset": 25470976 | |
| } | |
| ], | |
| "md5sum": "758ca3a92d8a671e6000b1500e592fd5" | |
| }, | |
| { | |
| "dataPath": "params_shard_27.bin", | |
| "format": "raw-shard", | |
| "nbytes": 26331136, | |
| "records": [ | |
| { | |
| "name": "model.layers.7.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 17920, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 13762560, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.7.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 17920, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1720320, | |
| "byteOffset": 13762560 | |
| }, | |
| { | |
| "name": "model.layers.7.post_attention_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 15482880 | |
| }, | |
| { | |
| "name": "model.layers.7.self_attn.c_attn.bias", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 15485952 | |
| }, | |
| { | |
| "name": "model.layers.7.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 2048, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1572864, | |
| "byteOffset": 15490048 | |
| }, | |
| { | |
| "name": "model.layers.7.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 2048, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 196608, | |
| "byteOffset": 17062912 | |
| }, | |
| { | |
| "name": "model.layers.7.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1179648, | |
| "byteOffset": 17259520 | |
| }, | |
| { | |
| "name": "model.layers.7.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 147456, | |
| "byteOffset": 18439168 | |
| }, | |
| { | |
| "name": "model.layers.8.input_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 18586624 | |
| }, | |
| { | |
| "name": "model.layers.8.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 1120 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6881280, | |
| "byteOffset": 18589696 | |
| }, | |
| { | |
| "name": "model.layers.8.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 280 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 860160, | |
| "byteOffset": 25470976 | |
| } | |
| ], | |
| "md5sum": "75e27eeb1f1b6054dd9185b77c98166a" | |
| }, | |
| { | |
| "dataPath": "params_shard_28.bin", | |
| "format": "raw-shard", | |
| "nbytes": 26331136, | |
| "records": [ | |
| { | |
| "name": "model.layers.8.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 17920, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 13762560, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.8.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 17920, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1720320, | |
| "byteOffset": 13762560 | |
| }, | |
| { | |
| "name": "model.layers.8.post_attention_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 15482880 | |
| }, | |
| { | |
| "name": "model.layers.8.self_attn.c_attn.bias", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 15485952 | |
| }, | |
| { | |
| "name": "model.layers.8.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 2048, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1572864, | |
| "byteOffset": 15490048 | |
| }, | |
| { | |
| "name": "model.layers.8.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 2048, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 196608, | |
| "byteOffset": 17062912 | |
| }, | |
| { | |
| "name": "model.layers.8.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1179648, | |
| "byteOffset": 17259520 | |
| }, | |
| { | |
| "name": "model.layers.8.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 147456, | |
| "byteOffset": 18439168 | |
| }, | |
| { | |
| "name": "model.layers.9.input_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 18586624 | |
| }, | |
| { | |
| "name": "model.layers.9.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 1120 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6881280, | |
| "byteOffset": 18589696 | |
| }, | |
| { | |
| "name": "model.layers.9.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 280 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 860160, | |
| "byteOffset": 25470976 | |
| } | |
| ], | |
| "md5sum": "b74e153c85a3895902e045872c7ce5e5" | |
| }, | |
| { | |
| "dataPath": "params_shard_29.bin", | |
| "format": "raw-shard", | |
| "nbytes": 18589696, | |
| "records": [ | |
| { | |
| "name": "model.layers.9.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 17920, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 13762560, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.9.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 17920, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1720320, | |
| "byteOffset": 13762560 | |
| }, | |
| { | |
| "name": "model.layers.9.post_attention_layernorm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 15482880 | |
| }, | |
| { | |
| "name": "model.layers.9.self_attn.c_attn.bias", | |
| "shape": [ | |
| 2048 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4096, | |
| "byteOffset": 15485952 | |
| }, | |
| { | |
| "name": "model.layers.9.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 2048, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1572864, | |
| "byteOffset": 15490048 | |
| }, | |
| { | |
| "name": "model.layers.9.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 2048, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 196608, | |
| "byteOffset": 17062912 | |
| }, | |
| { | |
| "name": "model.layers.9.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 1536, | |
| 192 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1179648, | |
| "byteOffset": 17259520 | |
| }, | |
| { | |
| "name": "model.layers.9.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 1536, | |
| 48 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 147456, | |
| "byteOffset": 18439168 | |
| }, | |
| { | |
| "name": "model.norm.weight", | |
| "shape": [ | |
| 1536 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 3072, | |
| "byteOffset": 18586624 | |
| } | |
| ], | |
| "md5sum": "62ae19ad61c991aecaf9ce68f7170a53" | |
| } | |
| ] | |
| } |