| { |
| "metadata": { |
| "ParamSize": 245, |
| "ParamBytes": 675649536.0, |
| "BitsPerParam": 5.001880498111684 |
| }, |
| "records": [ |
| { |
| "dataPath": "params_shard_0.bin", |
| "format": "raw-shard", |
| "nbytes": 100270080, |
| "records": [ |
| { |
| "name": "model.embed_tokens.q_weight", |
| "shape": [ |
| 130560, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 100270080, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "2598e084429f0f43b8948aedacb150f9" |
| }, |
| { |
| "dataPath": "params_shard_1.bin", |
| "format": "raw-shard", |
| "nbytes": 100270080, |
| "records": [ |
| { |
| "name": "lm_head.q_weight", |
| "shape": [ |
| 130560, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 100270080, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "556205fc2e6903255cdbfc51bbd2dbcb" |
| }, |
| { |
| "dataPath": "params_shard_2.bin", |
| "format": "raw-shard", |
| "nbytes": 32145408, |
| "records": [ |
| { |
| "name": "model.embed_tokens.q_scale", |
| "shape": [ |
| 130560, |
| 48 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 12533760, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "lm_head.q_scale", |
| "shape": [ |
| 130560, |
| 48 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 12533760, |
| "byteOffset": 12533760 |
| }, |
| { |
| "name": "model.layers.0.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 25067520 |
| }, |
| { |
| "name": "model.layers.0.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 64 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 26640384 |
| }, |
| { |
| "name": "model.layers.1.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 26836992 |
| }, |
| { |
| "name": "model.layers.1.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 64 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 28409856 |
| }, |
| { |
| "name": "model.layers.2.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 28606464 |
| }, |
| { |
| "name": "model.layers.2.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 64 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 30179328 |
| }, |
| { |
| "name": "model.layers.3.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 30375936 |
| }, |
| { |
| "name": "model.layers.3.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 64 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 31948800 |
| } |
| ], |
| "md5sum": "61c1913e8fdcae3c2c3fdd77960c63d4" |
| }, |
| { |
| "dataPath": "params_shard_3.bin", |
| "format": "raw-shard", |
| "nbytes": 33423360, |
| "records": [ |
| { |
| "name": "model.layers.4.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.4.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 64 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 1572864 |
| }, |
| { |
| "name": "model.layers.5.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 1769472 |
| }, |
| { |
| "name": "model.layers.5.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 64 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 3342336 |
| }, |
| { |
| "name": "model.layers.6.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 3538944 |
| }, |
| { |
| "name": "model.layers.6.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 64 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 5111808 |
| }, |
| { |
| "name": "model.layers.7.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 5308416 |
| }, |
| { |
| "name": "model.layers.7.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 64 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 6881280 |
| }, |
| { |
| "name": "model.layers.8.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 7077888 |
| }, |
| { |
| "name": "model.layers.8.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 64 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 8650752 |
| }, |
| { |
| "name": "model.layers.9.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 8847360 |
| }, |
| { |
| "name": "model.layers.9.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 64 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 10420224 |
| }, |
| { |
| "name": "model.layers.10.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 10616832 |
| }, |
| { |
| "name": "model.layers.10.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 64 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 12189696 |
| }, |
| { |
| "name": "model.layers.11.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 12386304 |
| }, |
| { |
| "name": "model.layers.11.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 64 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 13959168 |
| }, |
| { |
| "name": "model.layers.12.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 14155776 |
| }, |
| { |
| "name": "model.layers.12.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 64 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 15728640 |
| }, |
| { |
| "name": "model.layers.13.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 15925248 |
| }, |
| { |
| "name": "model.layers.13.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 64 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 17498112 |
| }, |
| { |
| "name": "model.layers.14.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 17694720 |
| }, |
| { |
| "name": "model.layers.14.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 64 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 19267584 |
| }, |
| { |
| "name": "model.layers.15.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 19464192 |
| }, |
| { |
| "name": "model.layers.15.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 64 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 21037056 |
| }, |
| { |
| "name": "model.layers.16.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 21233664 |
| }, |
| { |
| "name": "model.layers.16.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 64 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 22806528 |
| }, |
| { |
| "name": "model.layers.17.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 23003136 |
| }, |
| { |
| "name": "model.layers.17.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 64 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 24576000 |
| }, |
| { |
| "name": "model.layers.18.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 24772608 |
| }, |
| { |
| "name": "model.layers.18.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 64 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 26345472 |
| }, |
| { |
| "name": "model.layers.19.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 26542080 |
| }, |
| { |
| "name": "model.layers.19.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 64 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 28114944 |
| }, |
| { |
| "name": "model.layers.20.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 28311552 |
| }, |
| { |
| "name": "model.layers.20.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 64 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 29884416 |
| }, |
| { |
| "name": "model.layers.21.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 30081024 |
| }, |
| { |
| "name": "model.layers.21.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 64 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 31653888 |
| }, |
| { |
| "name": "model.layers.22.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 31850496 |
| } |
| ], |
| "md5sum": "fc6df0fc8b62de0dda75a475f65689d3" |
| }, |
| { |
| "dataPath": "params_shard_4.bin", |
| "format": "raw-shard", |
| "nbytes": 32931840, |
| "records": [ |
| { |
| "name": "model.layers.22.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 64 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.23.self_attn.o_proj.q_weight", |
| "shape": [ |
| 1536, |
| 256 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 196608 |
| }, |
| { |
| "name": "model.layers.23.self_attn.o_proj.q_scale", |
| "shape": [ |
| 1536, |
| 64 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 196608, |
| "byteOffset": 1769472 |
| }, |
| { |
| "name": "model.layers.0.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 2560, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1966080, |
| "byteOffset": 1966080 |
| }, |
| { |
| "name": "model.layers.0.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 2560, |
| 48 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 245760, |
| "byteOffset": 3932160 |
| }, |
| { |
| "name": "model.layers.1.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 2560, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1966080, |
| "byteOffset": 4177920 |
| }, |
| { |
| "name": "model.layers.1.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 2560, |
| 48 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 245760, |
| "byteOffset": 6144000 |
| }, |
| { |
| "name": "model.layers.2.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 2560, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1966080, |
| "byteOffset": 6389760 |
| }, |
| { |
| "name": "model.layers.2.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 2560, |
| 48 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 245760, |
| "byteOffset": 8355840 |
| }, |
| { |
| "name": "model.layers.3.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 2560, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1966080, |
| "byteOffset": 8601600 |
| }, |
| { |
| "name": "model.layers.3.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 2560, |
| 48 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 245760, |
| "byteOffset": 10567680 |
| }, |
| { |
| "name": "model.layers.4.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 2560, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1966080, |
| "byteOffset": 10813440 |
| }, |
| { |
| "name": "model.layers.4.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 2560, |
| 48 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 245760, |
| "byteOffset": 12779520 |
| }, |
| { |
| "name": "model.layers.5.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 2560, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1966080, |
| "byteOffset": 13025280 |
| }, |
| { |
| "name": "model.layers.5.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 2560, |
| 48 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 245760, |
| "byteOffset": 14991360 |
| }, |
| { |
| "name": "model.layers.6.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 2560, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1966080, |
| "byteOffset": 15237120 |
| }, |
| { |
| "name": "model.layers.6.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 2560, |
| 48 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 245760, |
| "byteOffset": 17203200 |
| }, |
| { |
| "name": "model.layers.7.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 2560, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1966080, |
| "byteOffset": 17448960 |
| }, |
| { |
| "name": "model.layers.7.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 2560, |
| 48 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 245760, |
| "byteOffset": 19415040 |
| }, |
| { |
| "name": "model.layers.8.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 2560, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1966080, |
| "byteOffset": 19660800 |
| }, |
| { |
| "name": "model.layers.8.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 2560, |
| 48 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 245760, |
| "byteOffset": 21626880 |
| }, |
| { |
| "name": "model.layers.9.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 2560, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1966080, |
| "byteOffset": 21872640 |
| }, |
| { |
| "name": "model.layers.9.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 2560, |
| 48 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 245760, |
| "byteOffset": 23838720 |
| }, |
| { |
| "name": "model.layers.10.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 2560, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1966080, |
| "byteOffset": 24084480 |
| }, |
| { |
| "name": "model.layers.10.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 2560, |
| 48 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 245760, |
| "byteOffset": 26050560 |
| }, |
| { |
| "name": "model.layers.11.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 2560, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1966080, |
| "byteOffset": 26296320 |
| }, |
| { |
| "name": "model.layers.11.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 2560, |
| 48 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 245760, |
| "byteOffset": 28262400 |
| }, |
| { |
| "name": "model.layers.12.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 2560, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1966080, |
| "byteOffset": 28508160 |
| }, |
| { |
| "name": "model.layers.12.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 2560, |
| 48 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 245760, |
| "byteOffset": 30474240 |
| }, |
| { |
| "name": "model.layers.13.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 2560, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1966080, |
| "byteOffset": 30720000 |
| }, |
| { |
| "name": "model.layers.13.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 2560, |
| 48 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 245760, |
| "byteOffset": 32686080 |
| } |
| ], |
| "md5sum": "bd876216cb29d81ffdaadd9336ffa2b1" |
| }, |
| { |
| "dataPath": "params_shard_5.bin", |
| "format": "raw-shard", |
| "nbytes": 30081024, |
| "records": [ |
| { |
| "name": "model.layers.14.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 2560, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1966080, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.14.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 2560, |
| 48 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 245760, |
| "byteOffset": 1966080 |
| }, |
| { |
| "name": "model.layers.15.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 2560, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1966080, |
| "byteOffset": 2211840 |
| }, |
| { |
| "name": "model.layers.15.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 2560, |
| 48 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 245760, |
| "byteOffset": 4177920 |
| }, |
| { |
| "name": "model.layers.16.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 2560, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1966080, |
| "byteOffset": 4423680 |
| }, |
| { |
| "name": "model.layers.16.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 2560, |
| 48 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 245760, |
| "byteOffset": 6389760 |
| }, |
| { |
| "name": "model.layers.17.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 2560, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1966080, |
| "byteOffset": 6635520 |
| }, |
| { |
| "name": "model.layers.17.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 2560, |
| 48 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 245760, |
| "byteOffset": 8601600 |
| }, |
| { |
| "name": "model.layers.18.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 2560, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1966080, |
| "byteOffset": 8847360 |
| }, |
| { |
| "name": "model.layers.18.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 2560, |
| 48 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 245760, |
| "byteOffset": 10813440 |
| }, |
| { |
| "name": "model.layers.19.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 2560, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1966080, |
| "byteOffset": 11059200 |
| }, |
| { |
| "name": "model.layers.19.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 2560, |
| 48 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 245760, |
| "byteOffset": 13025280 |
| }, |
| { |
| "name": "model.layers.20.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 2560, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1966080, |
| "byteOffset": 13271040 |
| }, |
| { |
| "name": "model.layers.20.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 2560, |
| 48 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 245760, |
| "byteOffset": 15237120 |
| }, |
| { |
| "name": "model.layers.21.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 2560, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1966080, |
| "byteOffset": 15482880 |
| }, |
| { |
| "name": "model.layers.21.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 2560, |
| 48 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 245760, |
| "byteOffset": 17448960 |
| }, |
| { |
| "name": "model.layers.22.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 2560, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1966080, |
| "byteOffset": 17694720 |
| }, |
| { |
| "name": "model.layers.22.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 2560, |
| 48 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 245760, |
| "byteOffset": 19660800 |
| }, |
| { |
| "name": "model.layers.23.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 2560, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 1966080, |
| "byteOffset": 19906560 |
| }, |
| { |
| "name": "model.layers.23.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 2560, |
| 48 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 245760, |
| "byteOffset": 21872640 |
| }, |
| { |
| "name": "model.layers.0.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 9216, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 7077888, |
| "byteOffset": 22118400 |
| }, |
| { |
| "name": "model.layers.0.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 9216, |
| 48 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 884736, |
| "byteOffset": 29196288 |
| } |
| ], |
| "md5sum": "4163b30e140b958c0afb1c0d13a973d7" |
| }, |
| { |
| "dataPath": "params_shard_6.bin", |
| "format": "raw-shard", |
| "nbytes": 31850496, |
| "records": [ |
| { |
| "name": "model.layers.1.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 9216, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 7077888, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.1.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 9216, |
| 48 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 884736, |
| "byteOffset": 7077888 |
| }, |
| { |
| "name": "model.layers.2.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 9216, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 7077888, |
| "byteOffset": 7962624 |
| }, |
| { |
| "name": "model.layers.2.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 9216, |
| 48 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 884736, |
| "byteOffset": 15040512 |
| }, |
| { |
| "name": "model.layers.3.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 9216, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 7077888, |
| "byteOffset": 15925248 |
| }, |
| { |
| "name": "model.layers.3.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 9216, |
| 48 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 884736, |
| "byteOffset": 23003136 |
| }, |
| { |
| "name": "model.layers.4.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 9216, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 7077888, |
| "byteOffset": 23887872 |
| }, |
| { |
| "name": "model.layers.4.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 9216, |
| 48 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 884736, |
| "byteOffset": 30965760 |
| } |
| ], |
| "md5sum": "270bcd27df3a3eb1d3825ea5f27a76ae" |
| }, |
| { |
| "dataPath": "params_shard_7.bin", |
| "format": "raw-shard", |
| "nbytes": 31850496, |
| "records": [ |
| { |
| "name": "model.layers.5.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 9216, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 7077888, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.5.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 9216, |
| 48 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 884736, |
| "byteOffset": 7077888 |
| }, |
| { |
| "name": "model.layers.6.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 9216, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 7077888, |
| "byteOffset": 7962624 |
| }, |
| { |
| "name": "model.layers.6.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 9216, |
| 48 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 884736, |
| "byteOffset": 15040512 |
| }, |
| { |
| "name": "model.layers.7.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 9216, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 7077888, |
| "byteOffset": 15925248 |
| }, |
| { |
| "name": "model.layers.7.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 9216, |
| 48 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 884736, |
| "byteOffset": 23003136 |
| }, |
| { |
| "name": "model.layers.8.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 9216, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 7077888, |
| "byteOffset": 23887872 |
| }, |
| { |
| "name": "model.layers.8.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 9216, |
| 48 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 884736, |
| "byteOffset": 30965760 |
| } |
| ], |
| "md5sum": "72b988018ae64d4effba400daa2578e3" |
| }, |
| { |
| "dataPath": "params_shard_8.bin", |
| "format": "raw-shard", |
| "nbytes": 31850496, |
| "records": [ |
| { |
| "name": "model.layers.9.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 9216, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 7077888, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.9.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 9216, |
| 48 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 884736, |
| "byteOffset": 7077888 |
| }, |
| { |
| "name": "model.layers.10.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 9216, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 7077888, |
| "byteOffset": 7962624 |
| }, |
| { |
| "name": "model.layers.10.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 9216, |
| 48 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 884736, |
| "byteOffset": 15040512 |
| }, |
| { |
| "name": "model.layers.11.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 9216, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 7077888, |
| "byteOffset": 15925248 |
| }, |
| { |
| "name": "model.layers.11.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 9216, |
| 48 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 884736, |
| "byteOffset": 23003136 |
| }, |
| { |
| "name": "model.layers.12.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 9216, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 7077888, |
| "byteOffset": 23887872 |
| }, |
| { |
| "name": "model.layers.12.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 9216, |
| 48 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 884736, |
| "byteOffset": 30965760 |
| } |
| ], |
| "md5sum": "1f9319150954f810b5a5d6c9e4b9ef58" |
| }, |
| { |
| "dataPath": "params_shard_9.bin", |
| "format": "raw-shard", |
| "nbytes": 31850496, |
| "records": [ |
| { |
| "name": "model.layers.13.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 9216, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 7077888, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.13.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 9216, |
| 48 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 884736, |
| "byteOffset": 7077888 |
| }, |
| { |
| "name": "model.layers.14.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 9216, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 7077888, |
| "byteOffset": 7962624 |
| }, |
| { |
| "name": "model.layers.14.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 9216, |
| 48 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 884736, |
| "byteOffset": 15040512 |
| }, |
| { |
| "name": "model.layers.15.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 9216, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 7077888, |
| "byteOffset": 15925248 |
| }, |
| { |
| "name": "model.layers.15.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 9216, |
| 48 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 884736, |
| "byteOffset": 23003136 |
| }, |
| { |
| "name": "model.layers.16.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 9216, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 7077888, |
| "byteOffset": 23887872 |
| }, |
| { |
| "name": "model.layers.16.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 9216, |
| 48 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 884736, |
| "byteOffset": 30965760 |
| } |
| ], |
| "md5sum": "ae6b83b3b118dff2ad9c083d7f29b2a5" |
| }, |
| { |
| "dataPath": "params_shard_10.bin", |
| "format": "raw-shard", |
| "nbytes": 31850496, |
| "records": [ |
| { |
| "name": "model.layers.17.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 9216, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 7077888, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.17.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 9216, |
| 48 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 884736, |
| "byteOffset": 7077888 |
| }, |
| { |
| "name": "model.layers.18.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 9216, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 7077888, |
| "byteOffset": 7962624 |
| }, |
| { |
| "name": "model.layers.18.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 9216, |
| 48 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 884736, |
| "byteOffset": 15040512 |
| }, |
| { |
| "name": "model.layers.19.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 9216, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 7077888, |
| "byteOffset": 15925248 |
| }, |
| { |
| "name": "model.layers.19.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 9216, |
| 48 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 884736, |
| "byteOffset": 23003136 |
| }, |
| { |
| "name": "model.layers.20.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 9216, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 7077888, |
| "byteOffset": 23887872 |
| }, |
| { |
| "name": "model.layers.20.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 9216, |
| 48 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 884736, |
| "byteOffset": 30965760 |
| } |
| ], |
| "md5sum": "42b2f8880efe411c27d685137462dd21" |
| }, |
| { |
| "dataPath": "params_shard_11.bin", |
| "format": "raw-shard", |
| "nbytes": 31850496, |
| "records": [ |
| { |
| "name": "model.layers.21.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 9216, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 7077888, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.21.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 9216, |
| 48 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 884736, |
| "byteOffset": 7077888 |
| }, |
| { |
| "name": "model.layers.22.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 9216, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 7077888, |
| "byteOffset": 7962624 |
| }, |
| { |
| "name": "model.layers.22.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 9216, |
| 48 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 884736, |
| "byteOffset": 15040512 |
| }, |
| { |
| "name": "model.layers.23.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 9216, |
| 192 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 7077888, |
| "byteOffset": 15925248 |
| }, |
| { |
| "name": "model.layers.23.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 9216, |
| 48 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 884736, |
| "byteOffset": 23003136 |
| }, |
| { |
| "name": "model.layers.0.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 576 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 3538944, |
| "byteOffset": 23887872 |
| }, |
| { |
| "name": "model.layers.0.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 144 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 442368, |
| "byteOffset": 27426816 |
| }, |
| { |
| "name": "model.layers.1.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 576 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 3538944, |
| "byteOffset": 27869184 |
| }, |
| { |
| "name": "model.layers.1.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 144 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 442368, |
| "byteOffset": 31408128 |
| } |
| ], |
| "md5sum": "a59089f22f52ee5c843e1ee11a3b9e89" |
| }, |
| { |
| "dataPath": "params_shard_12.bin", |
| "format": "raw-shard", |
| "nbytes": 31850496, |
| "records": [ |
| { |
| "name": "model.layers.2.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 576 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 3538944, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.2.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 144 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 442368, |
| "byteOffset": 3538944 |
| }, |
| { |
| "name": "model.layers.3.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 576 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 3538944, |
| "byteOffset": 3981312 |
| }, |
| { |
| "name": "model.layers.3.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 144 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 442368, |
| "byteOffset": 7520256 |
| }, |
| { |
| "name": "model.layers.4.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 576 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 3538944, |
| "byteOffset": 7962624 |
| }, |
| { |
| "name": "model.layers.4.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 144 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 442368, |
| "byteOffset": 11501568 |
| }, |
| { |
| "name": "model.layers.5.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 576 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 3538944, |
| "byteOffset": 11943936 |
| }, |
| { |
| "name": "model.layers.5.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 144 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 442368, |
| "byteOffset": 15482880 |
| }, |
| { |
| "name": "model.layers.6.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 576 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 3538944, |
| "byteOffset": 15925248 |
| }, |
| { |
| "name": "model.layers.6.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 144 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 442368, |
| "byteOffset": 19464192 |
| }, |
| { |
| "name": "model.layers.7.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 576 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 3538944, |
| "byteOffset": 19906560 |
| }, |
| { |
| "name": "model.layers.7.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 144 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 442368, |
| "byteOffset": 23445504 |
| }, |
| { |
| "name": "model.layers.8.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 576 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 3538944, |
| "byteOffset": 23887872 |
| }, |
| { |
| "name": "model.layers.8.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 144 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 442368, |
| "byteOffset": 27426816 |
| }, |
| { |
| "name": "model.layers.9.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 576 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 3538944, |
| "byteOffset": 27869184 |
| }, |
| { |
| "name": "model.layers.9.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 144 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 442368, |
| "byteOffset": 31408128 |
| } |
| ], |
| "md5sum": "4e38702dfad82f78018d4020d1baced6" |
| }, |
| { |
| "dataPath": "params_shard_13.bin", |
| "format": "raw-shard", |
| "nbytes": 31850496, |
| "records": [ |
| { |
| "name": "model.layers.10.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 576 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 3538944, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.10.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 144 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 442368, |
| "byteOffset": 3538944 |
| }, |
| { |
| "name": "model.layers.11.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 576 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 3538944, |
| "byteOffset": 3981312 |
| }, |
| { |
| "name": "model.layers.11.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 144 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 442368, |
| "byteOffset": 7520256 |
| }, |
| { |
| "name": "model.layers.12.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 576 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 3538944, |
| "byteOffset": 7962624 |
| }, |
| { |
| "name": "model.layers.12.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 144 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 442368, |
| "byteOffset": 11501568 |
| }, |
| { |
| "name": "model.layers.13.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 576 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 3538944, |
| "byteOffset": 11943936 |
| }, |
| { |
| "name": "model.layers.13.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 144 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 442368, |
| "byteOffset": 15482880 |
| }, |
| { |
| "name": "model.layers.14.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 576 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 3538944, |
| "byteOffset": 15925248 |
| }, |
| { |
| "name": "model.layers.14.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 144 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 442368, |
| "byteOffset": 19464192 |
| }, |
| { |
| "name": "model.layers.15.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 576 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 3538944, |
| "byteOffset": 19906560 |
| }, |
| { |
| "name": "model.layers.15.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 144 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 442368, |
| "byteOffset": 23445504 |
| }, |
| { |
| "name": "model.layers.16.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 576 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 3538944, |
| "byteOffset": 23887872 |
| }, |
| { |
| "name": "model.layers.16.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 144 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 442368, |
| "byteOffset": 27426816 |
| }, |
| { |
| "name": "model.layers.17.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 576 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 3538944, |
| "byteOffset": 27869184 |
| }, |
| { |
| "name": "model.layers.17.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 144 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 442368, |
| "byteOffset": 31408128 |
| } |
| ], |
| "md5sum": "3d3f711fcf061b40f63be0ac2431837f" |
| }, |
| { |
| "dataPath": "params_shard_14.bin", |
| "format": "raw-shard", |
| "nbytes": 24038400, |
| "records": [ |
| { |
| "name": "model.layers.18.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 576 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 3538944, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.18.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 144 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 442368, |
| "byteOffset": 3538944 |
| }, |
| { |
| "name": "model.layers.19.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 576 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 3538944, |
| "byteOffset": 3981312 |
| }, |
| { |
| "name": "model.layers.19.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 144 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 442368, |
| "byteOffset": 7520256 |
| }, |
| { |
| "name": "model.layers.20.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 576 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 3538944, |
| "byteOffset": 7962624 |
| }, |
| { |
| "name": "model.layers.20.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 144 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 442368, |
| "byteOffset": 11501568 |
| }, |
| { |
| "name": "model.layers.21.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 576 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 3538944, |
| "byteOffset": 11943936 |
| }, |
| { |
| "name": "model.layers.21.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 144 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 442368, |
| "byteOffset": 15482880 |
| }, |
| { |
| "name": "model.layers.22.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 576 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 3538944, |
| "byteOffset": 15925248 |
| }, |
| { |
| "name": "model.layers.22.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 144 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 442368, |
| "byteOffset": 19464192 |
| }, |
| { |
| "name": "model.layers.23.mlp.down_proj.q_weight", |
| "shape": [ |
| 1536, |
| 576 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 3538944, |
| "byteOffset": 19906560 |
| }, |
| { |
| "name": "model.layers.23.mlp.down_proj.q_scale", |
| "shape": [ |
| 1536, |
| 144 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 442368, |
| "byteOffset": 23445504 |
| }, |
| { |
| "name": "model.layers.0.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 23887872 |
| }, |
| { |
| "name": "model.layers.1.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 23890944 |
| }, |
| { |
| "name": "model.layers.2.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 23894016 |
| }, |
| { |
| "name": "model.layers.3.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 23897088 |
| }, |
| { |
| "name": "model.layers.4.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 23900160 |
| }, |
| { |
| "name": "model.layers.5.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 23903232 |
| }, |
| { |
| "name": "model.layers.6.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 23906304 |
| }, |
| { |
| "name": "model.layers.7.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 23909376 |
| }, |
| { |
| "name": "model.layers.8.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 23912448 |
| }, |
| { |
| "name": "model.layers.9.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 23915520 |
| }, |
| { |
| "name": "model.layers.10.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 23918592 |
| }, |
| { |
| "name": "model.layers.11.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 23921664 |
| }, |
| { |
| "name": "model.layers.12.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 23924736 |
| }, |
| { |
| "name": "model.layers.13.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 23927808 |
| }, |
| { |
| "name": "model.layers.14.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 23930880 |
| }, |
| { |
| "name": "model.layers.15.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 23933952 |
| }, |
| { |
| "name": "model.layers.16.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 23937024 |
| }, |
| { |
| "name": "model.layers.17.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 23940096 |
| }, |
| { |
| "name": "model.layers.18.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 23943168 |
| }, |
| { |
| "name": "model.layers.19.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 23946240 |
| }, |
| { |
| "name": "model.layers.20.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 23949312 |
| }, |
| { |
| "name": "model.layers.21.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 23952384 |
| }, |
| { |
| "name": "model.layers.22.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 23955456 |
| }, |
| { |
| "name": "model.layers.23.input_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 23958528 |
| }, |
| { |
| "name": "model.layers.0.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 23961600 |
| }, |
| { |
| "name": "model.layers.1.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 23964672 |
| }, |
| { |
| "name": "model.layers.2.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 23967744 |
| }, |
| { |
| "name": "model.layers.3.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 23970816 |
| }, |
| { |
| "name": "model.layers.4.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 23973888 |
| }, |
| { |
| "name": "model.layers.5.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 23976960 |
| }, |
| { |
| "name": "model.layers.6.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 23980032 |
| }, |
| { |
| "name": "model.layers.7.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 23983104 |
| }, |
| { |
| "name": "model.layers.8.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 23986176 |
| }, |
| { |
| "name": "model.layers.9.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 23989248 |
| }, |
| { |
| "name": "model.layers.10.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 23992320 |
| }, |
| { |
| "name": "model.layers.11.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 23995392 |
| }, |
| { |
| "name": "model.layers.12.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 23998464 |
| }, |
| { |
| "name": "model.layers.13.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 24001536 |
| }, |
| { |
| "name": "model.layers.14.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 24004608 |
| }, |
| { |
| "name": "model.layers.15.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 24007680 |
| }, |
| { |
| "name": "model.layers.16.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 24010752 |
| }, |
| { |
| "name": "model.layers.17.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 24013824 |
| }, |
| { |
| "name": "model.layers.18.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 24016896 |
| }, |
| { |
| "name": "model.layers.19.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 24019968 |
| }, |
| { |
| "name": "model.layers.20.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 24023040 |
| }, |
| { |
| "name": "model.layers.21.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 24026112 |
| }, |
| { |
| "name": "model.layers.22.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 24029184 |
| }, |
| { |
| "name": "model.layers.23.post_attention_layernorm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 24032256 |
| }, |
| { |
| "name": "model.norm.weight", |
| "shape": [ |
| 1536 |
| ], |
| "dtype": "float32", |
| "format": "f32-to-bf16", |
| "nbytes": 3072, |
| "byteOffset": 24035328 |
| } |
| ], |
| "md5sum": "3a7a9a3c1b9726ccb266acbda72cf447" |
| } |
| ] |
| } |