diff --git a/_init_1.5B_seed42/0/lr_scheduler/lr_scheduler_pp-0-of-1_tp-0-of-1_exp-0-of-1.pt b/_init_1.5B_seed42/0/lr_scheduler/lr_scheduler_pp-0-of-1_tp-0-of-1_exp-0-of-1.pt new file mode 100644 index 0000000000000000000000000000000000000000..33926ee0265a77925ebf30b794e7b5c9797b9f26 --- /dev/null +++ b/_init_1.5B_seed42/0/lr_scheduler/lr_scheduler_pp-0-of-1_tp-0-of-1_exp-0-of-1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:889382f98afd01f8c75222d962276f2b645262a034076af2441244995c489774 +size 4784 diff --git a/_init_1.5B_seed42/0/model/model/decoder/0/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/0/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ff78d64f24601636230bd9fdb83e9f26c0d2519c --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/0/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f768d3b996eb7ddebba0fe1aecce3e2bc7252a6d977d37f78a4c411e5255146 +size 8388848 diff --git a/_init_1.5B_seed42/0/model/model/decoder/0/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/0/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fff8497aba0b699308bab587e3bce5ccaab07c8d --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/0/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e1ba2bd2eaaea32431f4b856f195f70d748ffcffcf3c44312fa382efdbc51a6 +size 25166192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/0/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/model/model/decoder/0/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/0/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/0/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/0/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..422b8af30217c752f58047d3e2e6aad9121d635c --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/0/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4098c46f45c64bb553655c05ccc73ed78331c2698073f07ed3cdd2fdc1d2071a +size 23068912 diff --git a/_init_1.5B_seed42/0/model/model/decoder/0/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/0/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ad14c0bce5bf73ad45d388391adea4cf5b6d792f --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/0/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54634f9f196db93bcd2fc6a8edccfe94e59903a93ab6a0ab6cbb714ac4a7d8e1 +size 46137656 diff --git a/_init_1.5B_seed42/0/model/model/decoder/0/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/model/model/decoder/0/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/0/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/1/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/1/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a55554c813d30b9c3e07d0ed333105bbb4eafaf8 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/1/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:154dcf85698bd6f14f5376b3bf8cf014fb44d30d02047a9cf366752184d74160 +size 8388848 diff --git a/_init_1.5B_seed42/0/model/model/decoder/1/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/1/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4914439fb292cbbb15bcc4b9cfc78d88c5c1e4bb --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/1/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19c931b349d32914020857372b00fef2f13aad165ec0708f75dc5eb9b1ac82cb +size 25166192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/1/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/model/model/decoder/1/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/1/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/1/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/1/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..28c75b0c02cc8b17e98f54b802dee3afe94f2ef5 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/1/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dca0d452571543955688476d4eb416b41725e42a33093569f9a3b97132d5127a +size 23068912 diff --git a/_init_1.5B_seed42/0/model/model/decoder/1/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/1/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..90332440b1fc1258f40bf9d2c657efcdcbc05b67 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/1/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad2d27efa8c916f67157cf1a61ffdfd1846e4f28b9b13758673dd354b2e5886e +size 46137656 diff --git a/_init_1.5B_seed42/0/model/model/decoder/1/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/model/model/decoder/1/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/1/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/13/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/13/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6f0cdf6a04ccffea4d1d5219168680c71cf4ab0a --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/13/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d213db67c570cc736f5e49aad8b9936bccf9daf4579c5a820b2f5a46e242ce9e +size 8388848 diff --git a/_init_1.5B_seed42/0/model/model/decoder/13/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/13/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..934587485fa5bb7d2f2e26b3d9c384d7bc49a1a4 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/13/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2976108409c09c0fe05825b7aa0a6b75705b35f0b0eeec904f9d2804122cf83d +size 25166192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/13/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/model/model/decoder/13/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/13/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/13/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/13/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a1dc444a6f21aa9b799f21e4effa78955c0eb0d4 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/13/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8602593d959e08389b582bb9714665492aae6eeb8ba69dc2f3aa6fea7e926074 +size 23068912 diff --git a/_init_1.5B_seed42/0/model/model/decoder/13/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/13/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d0e47590c6a3d7b42982b678603261584278f592 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/13/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a1d67bb981f8bf15ecbed112f0f475746513b6187e76b6c1807749b8329c2c1 +size 46137656 diff --git a/_init_1.5B_seed42/0/model/model/decoder/13/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/model/model/decoder/13/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/13/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/14/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/14/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..92ecb8b6a94433b2c53c5021786cca01a88df16a --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/14/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79ff45d7524180b4fc3c49f27ba55a5a404937aa8f6fe834f67b24412d932348 +size 8388848 diff --git a/_init_1.5B_seed42/0/model/model/decoder/14/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/14/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0c82c1057f5e4d70dde38a36dc49e08346bd34ba --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/14/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7434f3a21ddc3bbbb30c07c9c68ea9cc5809f29244ef027fec24be04dac85617 +size 25166192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/14/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/model/model/decoder/14/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/14/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/14/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/14/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d94889d7cfd69d4c35dd2d958a6ebcce61f60035 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/14/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27824e8526cb049929170ef2c4493fad38d00534b663fc2de354766eb93b3025 +size 23068912 diff --git a/_init_1.5B_seed42/0/model/model/decoder/14/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/14/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3db9ccbbd2ae73d0ff3d256756d328867d3c448e --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/14/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7627f53629209ed3837e8097528d407d4dc5beca6e534a474b89678d97d490b6 +size 46137656 diff --git a/_init_1.5B_seed42/0/model/model/decoder/14/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/model/model/decoder/14/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/14/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/17/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/17/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9abf734e2f40639ed2074cbb0ce4c15efdbbd896 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/17/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e5a324889883c678c1d04c1b9f9ea1d5e24d974f6bb93dad9ab0f6c6c9780ea +size 8388848 diff --git a/_init_1.5B_seed42/0/model/model/decoder/17/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/17/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2f0f733f51204a368e29733f2c5db31483e26a31 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/17/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88d59ae6c21fef66b16b128319a09533f069cdfa77fcc311d6ffc07ec833f89d +size 25166192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/17/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/model/model/decoder/17/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/17/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/17/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/17/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..041e21337b664c754c32ba5ce5d1702414d39eb8 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/17/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7110dde346c01a0f36a1719eed689e9b55ac001ce125f7f34650f73b4fce9bab +size 23068912 diff --git a/_init_1.5B_seed42/0/model/model/decoder/17/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/17/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..662c5d140d06074d040a5120e96f45f43ee14a8b --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/17/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04ddcea4d0dc13eb84118d857cb5d313bea7a8068cde26de9983c18dc57d48a1 +size 46137656 diff --git a/_init_1.5B_seed42/0/model/model/decoder/17/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/model/model/decoder/17/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/17/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/19/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/19/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4ee5d4a138cb5205699315d3a86411712f8e638 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/19/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59ee1f1d1f80d1ae65f551247b22e8a1ca1ec3e5ea41ea189a9619350b6af2d0 +size 8388848 diff --git a/_init_1.5B_seed42/0/model/model/decoder/19/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/19/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..208407091db564d60aad1d7e1b1a82a2a223e89c --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/19/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c15d54e9aa194eebda12644496c49f253fc96aec8fac97bf547a6618a38b75ad +size 25166192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/19/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/19/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..60b67889917033b759d896407c673e5597b4069a --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/19/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83f7a0e2d6bd58e847eafd0482d26b89340259771679c31a9f556cbf98d28a69 +size 23068912 diff --git a/_init_1.5B_seed42/0/model/model/decoder/19/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/19/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..026acf63cdb8a2da18ee9de0621c1a9bea9582c8 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/19/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4121b0331ab05b277361988bc4d90dea393c5d41319b96ed5519a65743344719 +size 46137656 diff --git a/_init_1.5B_seed42/0/model/model/decoder/21/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/21/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f32ee52391a8600aaed5a88bd6ec4c06c657406d --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/21/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24236509d97bf79c8bd919bc11d30eaddf132af64787439c5ef6139d79ad7164 +size 8388848 diff --git a/_init_1.5B_seed42/0/model/model/decoder/21/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/21/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bef7a3cd80af285644e181b21dc9412958486623 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/21/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2cfe62faf8b21d9cf2fbcbe444431c1ebda00944a32404373d4222a00fd2083 +size 25166192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/21/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/model/model/decoder/21/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/21/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/21/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/21/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a91dad5de18f18c70389961ab4a4a1ef4f2e56d5 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/21/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:476194dec1c613939e3a4f55a93fa89a1d03b96e269ef5e1663d259df41a7968 +size 23068912 diff --git a/_init_1.5B_seed42/0/model/model/decoder/21/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/21/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..48aba65e2dbb8b15197946983f73367d74b3e778 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/21/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a44e5c3ea81236caf228d8a1bebbc3dfdedc6e8843259db81be4405ca975a0c2 +size 46137656 diff --git a/_init_1.5B_seed42/0/model/model/decoder/21/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/model/model/decoder/21/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/21/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/22/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/22/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5e0ef9ea73d48d49f2eef612130d07ec3da87965 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/22/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd4187d1beed7321efd9fbc57b4c4a5a214c8359ded0273f7fab534076ca8138 +size 46137656 diff --git a/_init_1.5B_seed42/0/model/model/decoder/24/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/24/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f2d40d9f92bc87791a590b9fe74ce0fc2bb3d3ad --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/24/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fb201b6dde9c3b569d5a686d6680b8bdc6599af381deb644fc0aaeb18000e97 +size 8388848 diff --git a/_init_1.5B_seed42/0/model/model/decoder/24/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/24/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bac8c80f5ad3d593ea90a6c1d29b24247858405d --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/24/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1444895cdca068e290bdd56938665475579fc23df52dce9fbbb94c24d005a1a +size 25166192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/24/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/model/model/decoder/24/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/24/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/24/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/24/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e1a9b56c59577249b96626f7be2a62f69049e011 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/24/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:093f989c50f3caa8266d5b1f495d977d404243469650d44cd254bd0b8eb39f30 +size 23068912 diff --git a/_init_1.5B_seed42/0/model/model/decoder/24/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/24/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..87121f55df31efe2709124175824ae4f23f0f684 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/24/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:631b09b4bffa4ffa613a00ddbcf72e5fd9bc48098691a6ed0301d32a863e4b48 +size 46137656 diff --git a/_init_1.5B_seed42/0/model/model/decoder/24/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/model/model/decoder/24/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/24/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/26/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/26/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..528576d46313bf471a065c7622d7c28a5f7ddad6 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/26/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2630064bddc9b312a8d23744df2b6df592afcf7a760fe2887c67383c3183c12 +size 8388848 diff --git a/_init_1.5B_seed42/0/model/model/decoder/26/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/26/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c7d1268a6e51898b59a2b362922a26ffff4468d0 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/26/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5c3cc416a08a347e70a2031c63955dc6fc3f896c61f613f758e9680b7ec7be7 +size 25166192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/26/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/model/model/decoder/26/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/26/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/26/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/26/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..190c38ae90a0f5ac611debaf87eb99fc1620fee9 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/26/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34c9ab27458607a4c063652abb5019d224033cf130f3fe310f9f052898832dab +size 23068912 diff --git a/_init_1.5B_seed42/0/model/model/decoder/26/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/26/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..27018ed5c4df6d9e9b4c1e5b556974d01b5677a5 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/26/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bee63c56b22034b3ca613be2af39d4b65e4004be3488347fd3265ab223c14195 +size 46137656 diff --git a/_init_1.5B_seed42/0/model/model/decoder/26/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/model/model/decoder/26/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/26/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/27/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/27/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8b47bf578c20682166ad063ec843d862d18d3fac --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/27/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83f46c01f721ef3b12243e621f5e6e027baacfa71b90fe6a0010c197f53ed14a +size 8388848 diff --git a/_init_1.5B_seed42/0/model/model/decoder/27/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/27/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1da10a9e33b35639c3372b4c399c921b66e75a05 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/27/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc8620e82411dde585ccb0a784811367a9d090499920b0a7a00a4a7fe8501b88 +size 25166192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/27/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/model/model/decoder/27/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/27/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/27/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/27/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8ee65ff5f358ae6ab522115e1d969a3bb80e48fa --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/27/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:adc720eb887cd2229e65be73afae83abcc22647b643ed30068f2a1a38206a5b1 +size 23068912 diff --git a/_init_1.5B_seed42/0/model/model/decoder/27/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/27/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..65485859903962a36b02ebf63dadf782fde98f4b --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/27/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:459c6dfab6c2bfa18e4d9c541c363ea1d6edb46db7ae8b3e248616f7891bc5e2 +size 46137656 diff --git a/_init_1.5B_seed42/0/model/model/decoder/27/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/model/model/decoder/27/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/27/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/3/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/3/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..de43f6ed431b7b7a9f1b38d67bf599530b5c3a41 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/3/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11070f7fce4e9b917aa812a8eca5cf1fa3c4f9f705fd48e74b5785510d84b257 +size 8388848 diff --git a/_init_1.5B_seed42/0/model/model/decoder/3/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/3/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b6997c88bf62f6aa7ee4ff585b8c81da24240435 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/3/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60dd3b0de4d20640d3c131dfe7b1262b88af9182a2e3041e78cb07ff25552cbf +size 25166192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/3/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/model/model/decoder/3/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/3/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/3/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/3/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..32ca5d1d11dd49e6c6ecacf93a6d8217c4aa5bc4 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/3/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:860f7bc215f07c46c72bda1419984a81a9c35444cc3fd362a34c3b77fcb3c594 +size 23068912 diff --git a/_init_1.5B_seed42/0/model/model/decoder/3/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/3/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ff580e40ff2851b3f997487ee7d14a0e24dc181c --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/3/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0983d8db9ff38bfea9e26c59d89d30ed0e8b477275f0a7fd6475de46f64ebc20 +size 46137656 diff --git a/_init_1.5B_seed42/0/model/model/decoder/3/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/model/model/decoder/3/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/3/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/4/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/4/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..db4eefec7542fe53685045af122538c947ed0b0c --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/4/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95a8fdbc1d787007d9774188be273cbbee202bbdaa5be72bc464c1626409d7cd +size 8388848 diff --git a/_init_1.5B_seed42/0/model/model/decoder/4/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/4/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..23cd43f40dcd9d8b2600223f89caec857f0e6669 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/4/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80fd5762185b788b1ffb555fa301284e1fe1de7fea4fda2d36ff347da2bfdf0e +size 25166192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/4/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/model/model/decoder/4/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/4/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/4/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/4/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..59a4fcb717aef3d79cd0f33eb52aa82892862f69 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/4/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d38e821a8666a3c55742a75f365bd8a6c871249d27c1e4827517dea1b2322ba +size 23068912 diff --git a/_init_1.5B_seed42/0/model/model/decoder/4/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/4/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..144891f8c15cde0c61bc85c1f0ab6c90987b984a --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/4/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e28316b8d6ab3d3d896b7afdef54dbe9fb6e4646b4dc865c699ee702e6abb1a +size 46137656 diff --git a/_init_1.5B_seed42/0/model/model/decoder/4/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/model/model/decoder/4/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/4/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/8/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/8/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c84c8bec944a557219843637c27871fbb389b0fa --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/8/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a1d16d2560889e66ec4218a4e2fe7f8439a43a77be64446023db636584d2156 +size 8388848 diff --git a/_init_1.5B_seed42/0/model/model/decoder/8/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/8/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7d56fefde4a9f0b1a2a794c805f215454eb16ef0 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/8/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7e7d216451c08c8c5f35be55e880d8a06d53c68bf90fd77b490af4e638211f6 +size 25166192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/8/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/model/model/decoder/8/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/8/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/8/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/8/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..06b45ea513d8dc92c70da15a9e13ba40dd6e3f50 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/8/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89cafae467defb6cdbcdf946ed3aa4f339c13fc05c03141eef2cf02a9d901d81 +size 23068912 diff --git a/_init_1.5B_seed42/0/model/model/decoder/8/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/8/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f888c49643098a53e573fca6511d77c41547bb19 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/8/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fb00dfd9b5e52d43ce56a5423162bd1db10e93b381aef426828369a78d519a6 +size 46137656 diff --git a/_init_1.5B_seed42/0/model/model/decoder/8/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/model/model/decoder/8/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/8/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/9/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/9/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0f90c7754ace503be1f609eeab4c7273230537c8 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/9/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0df20b2e453b1e581ada7d0034632743a6faf3d18c694cff197677b31ebadac7 +size 8388848 diff --git a/_init_1.5B_seed42/0/model/model/decoder/9/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/9/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..03d09bf28cc076cdd345872ba23734e047dc0336 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/9/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54dc68fad1dbfc58ee172950407ae36c868f1fd25e551a1dbef314868ffb0b02 +size 25166192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/9/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/model/model/decoder/9/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/9/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/9/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/9/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4774fb3dde2cd26a88f4b92397e4eb0d74b1e118 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/9/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd99cbcd6d0fcfdab2ef73add7ecc6f3745d573363a89eafddf05e0ddede9c91 +size 23068912 diff --git a/_init_1.5B_seed42/0/model/model/decoder/9/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/decoder/9/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2bf3a65b264b1b5ba534ca1353c0188f759047e3 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/9/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfd0359f5a1e8c819f5c53aa1b59002277cd3492ac401f70172046e5fc1abc27 +size 46137656 diff --git a/_init_1.5B_seed42/0/model/model/decoder/9/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/model/model/decoder/9/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/9/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/lr_scheduler/lr_scheduler_pp-0-of-1_tp-0-of-1_exp-0-of-1.pt b/_init_1.5B_seed44/0/lr_scheduler/lr_scheduler_pp-0-of-1_tp-0-of-1_exp-0-of-1.pt new file mode 100644 index 0000000000000000000000000000000000000000..c1248d7daa36f48aa2659cf759508ba33bc30df3 --- /dev/null +++ b/_init_1.5B_seed44/0/lr_scheduler/lr_scheduler_pp-0-of-1_tp-0-of-1_exp-0-of-1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61cd9db5cd452564f4c66b062fabb1add7a2d292d19a5155edb8af8ee3c61bb9 +size 4784 diff --git a/_init_1.5B_seed44/0/model/model/decoder/12/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/12/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f9fd8ee3cb438b6033f41a2b6690a5f174c7fa03 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/12/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ca53e24d375c64c716938f9190298de8aaa556c7033d546542f59858c3c1b32 +size 8388848 diff --git a/_init_1.5B_seed44/0/model/model/decoder/12/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/12/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/12/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/12/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/12/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6d6695b1731d4ac39ba3711d39d17ca3894b7536 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/12/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbda4ae3e51be0215af97ba9ccbdb343f0f6d142cb3ad980a0d0ee9c334945af +size 23068912 diff --git a/_init_1.5B_seed44/0/model/model/decoder/12/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/12/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/12/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/19/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/19/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0246b92000050bf43afbd5fe3fd314749098f0dc --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/19/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07fcc5e7e4e0f4829604ef9268bf2f6b3d276e9aa52abd0754770027131acf02 +size 8388848 diff --git a/_init_1.5B_seed44/0/model/model/decoder/19/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/19/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8bbd8f923a4deade68a09cf77cb3fc71427ee0ca --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/19/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d3d88bd084fca94eb791bb6c986ce33283f39d826cc4e10b58eb0dfa2297bf7 +size 25166192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/19/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/19/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/19/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/19/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/19/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..17061b59b7807c99f6bdfe2aa181bf25011f1b81 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/19/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f6bd25510cdc4f0b65c567d09df42d17a103d16386e093b2ee0b0a8d8ef0f69 +size 23068912 diff --git a/_init_1.5B_seed44/0/model/model/decoder/19/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/19/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..605452565f3356bce6e0200ee8454be7aaf44927 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/19/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da88c5bdca766948dbcd50b79d5bf759d6d4a821011d1b4fa150a32e6852e2d9 +size 46137656 diff --git a/_init_1.5B_seed44/0/model/model/decoder/19/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/19/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/19/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/3/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/3/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/3/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/random/tp-0-of-1_dp-0-of-4_pp-0-of-1.pt b/_init_1.5B_seed44/0/random/tp-0-of-1_dp-0-of-4_pp-0-of-1.pt new file mode 100644 index 0000000000000000000000000000000000000000..8e2ff92a97577808d7898ec9acf98564605dce21 --- /dev/null +++ b/_init_1.5B_seed44/0/random/tp-0-of-1_dp-0-of-4_pp-0-of-1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cafa33c7f898af8cfdd14070a86ceb6e82a7e4667f7742eb260461bfa472220c +size 1080 diff --git a/_init_1.5B_seed44/0/random/tp-0-of-1_dp-1-of-4_pp-0-of-1.pt b/_init_1.5B_seed44/0/random/tp-0-of-1_dp-1-of-4_pp-0-of-1.pt new file mode 100644 index 0000000000000000000000000000000000000000..2dba7a6d95fd2669b13d67e2a5f1d2bc70239654 --- /dev/null +++ b/_init_1.5B_seed44/0/random/tp-0-of-1_dp-1-of-4_pp-0-of-1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c767793d2f8cbbe122ed6d6d45d61859b9e7c78f012f40becea9d84a766f26d +size 1080 diff --git a/_init_1.5B_seed44/0/random/tp-0-of-1_dp-2-of-4_pp-0-of-1.pt b/_init_1.5B_seed44/0/random/tp-0-of-1_dp-2-of-4_pp-0-of-1.pt new file mode 100644 index 0000000000000000000000000000000000000000..13ee4024b14178b9d269e0d7012104fc9a6cc689 --- /dev/null +++ b/_init_1.5B_seed44/0/random/tp-0-of-1_dp-2-of-4_pp-0-of-1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe7792d5682fe9b9672a0f9dff4fd43975f3cb836180000e3eb5a809190a859e +size 1080 diff --git a/_init_1.5B_seed44/0/random/tp-0-of-1_dp-3-of-4_pp-0-of-1.pt b/_init_1.5B_seed44/0/random/tp-0-of-1_dp-3-of-4_pp-0-of-1.pt new file mode 100644 index 0000000000000000000000000000000000000000..80a292d765754d0db86f2349e36aeda4565867cf --- /dev/null +++ b/_init_1.5B_seed44/0/random/tp-0-of-1_dp-3-of-4_pp-0-of-1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:456788c887b847f5cba3eb98c3649fe84190ceba1f1ce60dbe40c39ea668703f +size 1080