Add checkpoint shards (1204/1285 dirs)

.gitattributes

@@ -18715,3 +18715,11 @@ model/model/layers/6/mlp/experts/gate_proj/weight/4.0.0 filter=lfs diff=lfs merg
 model/model/layers/6/mlp/experts/gate_proj/weight/5.0.0 filter=lfs diff=lfs merge=lfs -text
 model/model/layers/6/mlp/experts/gate_proj/weight/6.0.0 filter=lfs diff=lfs merge=lfs -text
 model/model/layers/6/mlp/experts/gate_proj/weight/7.0.0 filter=lfs diff=lfs merge=lfs -text
+model/model/layers/6/mlp/experts/up_proj/weight/0.0.0 filter=lfs diff=lfs merge=lfs -text
+model/model/layers/6/mlp/experts/up_proj/weight/1.0.0 filter=lfs diff=lfs merge=lfs -text
+model/model/layers/6/mlp/experts/up_proj/weight/2.0.0 filter=lfs diff=lfs merge=lfs -text
+model/model/layers/6/mlp/experts/up_proj/weight/3.0.0 filter=lfs diff=lfs merge=lfs -text
+model/model/layers/6/mlp/experts/up_proj/weight/4.0.0 filter=lfs diff=lfs merge=lfs -text
+model/model/layers/6/mlp/experts/up_proj/weight/5.0.0 filter=lfs diff=lfs merge=lfs -text
+model/model/layers/6/mlp/experts/up_proj/weight/6.0.0 filter=lfs diff=lfs merge=lfs -text
+model/model/layers/6/mlp/experts/up_proj/weight/7.0.0 filter=lfs diff=lfs merge=lfs -text

model/model/layers/6/mlp/experts/up_proj/weight/.zarray

@@ -0,0 +1 @@
+{"chunks":[32,4096,2048],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[256,4096,2048],"zarr_format":2}

model/model/layers/6/mlp/experts/up_proj/weight/0.0.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e79f3fc08a8bd8078f907a44e4fed19a31f22d85f64619c5bd6976dafb0dda5f
+size 173665988

model/model/layers/6/mlp/experts/up_proj/weight/1.0.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:771afd50e9d17787bb50f0419b880c2e48430d5590192ae08959f174f1ab4cbf
+size 173675493

model/model/layers/6/mlp/experts/up_proj/weight/2.0.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62555a553e42c21bb3bad8baf26edd884c7a38aa7bb43ea2912a427e5042e6a2
+size 173648180

model/model/layers/6/mlp/experts/up_proj/weight/3.0.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afee660871bc04cac09a4d1f9ab3d7ce1be04818f3741b28873278f53ce93cb2
+size 173601598

model/model/layers/6/mlp/experts/up_proj/weight/4.0.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f113e40d37a92b8623422cd0e5fc7fb7c5c94dcde8b6d46feb5bdae2c91738dd
+size 173663664

model/model/layers/6/mlp/experts/up_proj/weight/5.0.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5c24ec0e693122753e827d76e97d3b9493627654980cf722b3d0ab598f92436
+size 173621991

model/model/layers/6/mlp/experts/up_proj/weight/6.0.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c23b8cb5942dba9a56831fd5e26347781987d12b98ccc368042efbbacffb5ae8
+size 173589492

model/model/layers/6/mlp/experts/up_proj/weight/7.0.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:140c6bd83ec9a2c0b7a25259c5121f1ea2cd9e5bf5171402b95a1a104ea1ad07
+size 173626841

model/model/layers/6/mlp/gate/e_score_correction_bias/.zarray

@@ -0,0 +1 @@
+{"chunks":[256],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[256],"zarr_format":2}

model/model/layers/6/mlp/gate/weight/.zarray

@@ -0,0 +1 @@
+{"chunks":[4096,256],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,256],"zarr_format":2}

model/model/layers/6/mlp/gate/weight/0.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:327bfb935e1b670154d483af3d86f984e365319532670c1f0333e30cbc9c450e
+size 1636633

model/model/layers/6/mlp/shared_experts/down_proj/weight/.zarray

@@ -0,0 +1 @@
+{"chunks":[2048,4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2048,4096],"zarr_format":2}

model/model/layers/6/mlp/shared_experts/down_proj/weight/0.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53edcfd883c4a8d93914ab4b897a31030e2e027c2f0e99809781fca973ba7f2e
+size 9128269

model/model/layers/6/mlp/shared_experts/gate_up_proj/weight/.zarray

@@ -0,0 +1 @@
+{"chunks":[4096,4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}

model/model/layers/6/mlp/shared_experts/gate_up_proj/weight/0.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e381f7481178fc91185980d7f37f0572decdf98395f96fb331222b349bf4bf52
+size 18263722

model/model/layers/6/post_attention_layernorm/weight/.zarray

@@ -0,0 +1 @@
+{"chunks":[4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096],"zarr_format":2}

model/model/layers/6/self_attn/compressor/gate_proj/weight/.zarray

@@ -0,0 +1 @@
+{"chunks":[4096,1024],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,1024],"zarr_format":2}

model/model/layers/6/self_attn/compressor/gate_proj/weight/0.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c03375b3304c4e434f99d21afbbc02c555032bec952290e7a78a7498b1a22f6
+size 6585521

model/model/layers/6/self_attn/compressor/indexer/gate_proj/weight/.zarray

@@ -0,0 +1 @@
+{"chunks":[4096,256],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,256],"zarr_format":2}

model/model/layers/6/self_attn/compressor/indexer/gate_proj/weight/0.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d50dbfe746188741df0104e98754f61f9fdc0548cd6ca1efe902a7238919866
+size 1652612

model/model/layers/6/self_attn/compressor/indexer/kv_norm/weight/.zarray

@@ -0,0 +1 @@
+{"chunks":[128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[128],"zarr_format":2}

model/model/layers/6/self_attn/compressor/indexer/kv_proj/weight/.zarray

@@ -0,0 +1 @@
+{"chunks":[4096,256],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,256],"zarr_format":2}

model/model/layers/6/self_attn/compressor/indexer/kv_proj/weight/0.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80e8f3a5cf013588ba487dcfef1c4a3a526d13dd0b446a5a75d6249b13e67edc
+size 1644920

model/model/layers/6/self_attn/compressor/indexer/position_bias/.zarray

@@ -0,0 +1 @@
+{"chunks":[4,256],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4,256],"zarr_format":2}

model/model/layers/6/self_attn/compressor/indexer/position_bias/0.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c8f9e9e5b5f81096b7b189eb6370e0ffb345a6ab8f8f8fab793bf02ab974b1b
+size 1672

model/model/layers/6/self_attn/compressor/indexer/q_b_proj/weight/.zarray

@@ -0,0 +1 @@
+{"chunks":[1024,8192],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[1024,8192],"zarr_format":2}

model/model/layers/6/self_attn/compressor/indexer/q_b_proj/weight/0.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebb7dec128d6495cd679fb448b395e562dd762cac8513f3af1506935e021d74f
+size 9349553

model/model/layers/6/self_attn/compressor/indexer/scorer/weights_proj/weight/.zarray

@@ -0,0 +1 @@
+{"chunks":[4096,64],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,64],"zarr_format":2}

model/model/layers/6/self_attn/compressor/indexer/scorer/weights_proj/weight/0.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63df42eefac12ea8a32f2616cfd46e03888dd2187b98f23f8a2276b8a462349b
+size 411523

model/model/layers/6/self_attn/compressor/kv_norm/weight/.zarray

@@ -0,0 +1 @@
+{"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2}

model/model/layers/6/self_attn/compressor/kv_proj/weight/.zarray

@@ -0,0 +1 @@
+{"chunks":[4096,1024],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,1024],"zarr_format":2}

model/model/layers/6/self_attn/compressor/kv_proj/weight/0.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d902f0ca5bb6b600ef8657ace2f873de250f2266ae915e92f12d73b5724e750a
+size 6573121

model/model/layers/6/self_attn/compressor/position_bias/.zarray

@@ -0,0 +1 @@
+{"chunks":[4,1024],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4,1024],"zarr_format":2}

model/model/layers/6/self_attn/compressor/position_bias/0.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ed2fddffbc469448d05c70df6b1bd8755f495cab469fad3b82925155c52069d
+size 6277

model/model/layers/6/self_attn/kv_norm/weight/.zarray

@@ -0,0 +1 @@
+{"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2}

model/model/layers/6/self_attn/kv_proj/weight/.zarray

@@ -0,0 +1 @@
+{"chunks":[4096,512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,512],"zarr_format":2}

model/model/layers/6/self_attn/kv_proj/weight/0.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cdda6530e6372d510d21143c3292cc109d070c80b858b3aaf19d21a7067a8b1
+size 2297174

model/model/layers/6/self_attn/o_a_proj/weight/.zarray

@@ -0,0 +1 @@
+{"chunks":[4096,8192],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,8192],"zarr_format":2}

model/model/layers/6/self_attn/o_a_proj/weight/0.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffc5202b9f33896b44c88c69e806b2ee5389d87a8dd2a728a874fb1c44e7869d
+size 36824588

model/model/layers/6/self_attn/o_b_proj/weight/.zarray

@@ -0,0 +1 @@
+{"chunks":[8192,4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[8192,4096],"zarr_format":2}

model/model/layers/6/self_attn/o_b_proj/weight/0.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da41b595fda4de5d9a9e3b9586254eed1e58b819ea0fce5b6fc35cb14aefcf54
+size 36705228

model/model/layers/6/self_attn/q_a_norm/weight/.zarray

@@ -0,0 +1 @@
+{"chunks":[1024],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[1024],"zarr_format":2}