diff --git a/_init_1.5B_seed42/0/model/model/decoder/10/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/10/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7e314840a3185b5f2aee77be5a6966a2b4fbbdbd --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/10/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 sha256:38097e231d931f6b775467c790b18477dad683e7647dc1b1fe986d3f31beb086 +size 8388848 diff --git a/_init_1.5B_seed42/0/model/model/decoder/10/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/10/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..24b665d3fd09be0f23f02ccaf78159c13a3867e1 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/10/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:c292126832d7c1d2f7d7c41982a8d3d2283ec528f1ac77d79ec357e7d159aac7 +size 25166192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/10/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/model/model/decoder/10/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/10/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/10/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/10/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ca793d3ce89e0f4e671d2461f9dac1928fe83eae --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/10/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:ffa34296816be39fdd19504596259d3092445a81f2ea9f31f52e85a27bbfb97f +size 23068912 diff --git a/_init_1.5B_seed42/0/model/model/decoder/10/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/10/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..ab4a331338a10de3e8d2472e38c200865766f27e --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/10/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:dd25890d2287f52b8f20ac17ea520b0d310cce8d6539f2099fe14b898030bc2b +size 46137656 diff --git a/_init_1.5B_seed42/0/model/model/decoder/10/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/model/model/decoder/10/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/10/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/11/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/11/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..45fc904c48d551c691034e4a2480ea72ae65b763 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/11/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 sha256:6a2c5aeca3c87d5b8c47e50dce101a9f0ae7a7dce015838479ad8194d38d3eb6 +size 8388848 diff --git a/_init_1.5B_seed42/0/model/model/decoder/11/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/11/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dc1322da3aa6ce4c4bf0f5b55027199b21765d9d --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/11/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:cfc7029453dc75b62da4e5b563eb36bcca79b50ca513e769fc6490bec789129e +size 25166192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/11/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/model/model/decoder/11/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/11/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/11/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/11/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..12c91537c26b9d1504b55d5c232aa6d7a13a4eb8 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/11/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:a4c0e09cb9061ff95e71ec25dd96f023f9ba2cf3e955be42699b31754891a420 +size 23068912 diff --git a/_init_1.5B_seed42/0/model/model/decoder/11/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/11/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..a9061cde7204192b70fe20f6b309637d4ee2879a --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/11/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 sha256:1d6cff4b75a8141407c9f2f2abb0d9e2610fe19db78686e9774539fb2b2fa1c1 +size 46137656 diff --git a/_init_1.5B_seed42/0/model/model/decoder/11/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/model/model/decoder/11/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/11/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/12/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/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..d093093e4b59b0bc801f3c2d681c617b22f9b130 --- /dev/null +++ b/_init_1.5B_seed42/0/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:e20817559a1f5bfb87fce76f0a5c0cf3d36684684d63ad9b760574339da608d2 +size 8388848 diff --git a/_init_1.5B_seed42/0/model/model/decoder/12/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/12/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e8ff7a76238cb0e3f538c6a7f1001b29d4ae9313 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/12/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 sha256:667bb63d2649408c05e6e229e7f1dede63cbf9f6d1e54378131771fac09547c3 +size 25166192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/12/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/model/model/decoder/12/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed42/0/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_seed42/0/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_seed42/0/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..3c2e101eeb23f0236af776e3eaebe0456d0f4cb4 --- /dev/null +++ b/_init_1.5B_seed42/0/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 sha256:1db5d6c5d60e767b877cd7837cf0918d8c33ff0478b79d1a67705506f2fc86db +size 23068912 diff --git a/_init_1.5B_seed42/0/model/model/decoder/12/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/12/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..c96bb3553c22f8d91cacab61911418b2958b677d --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/12/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 sha256:30dc50e89ddffc5e3d3491ecf92769861e0354439b7cc77cbb1529f7c1b2c48e +size 46137656 diff --git a/_init_1.5B_seed42/0/model/model/decoder/12/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/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_seed42/0/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_seed42/0/model/model/decoder/15/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/15/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e1e9f6c96458e395b9d5441846be92583d57c559 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/15/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:d829461af28eecf5fe76020211df51c07b79876dbe75b2d0ca0b0496516a4e9c +size 8388848 diff --git a/_init_1.5B_seed42/0/model/model/decoder/15/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/15/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..29a70098c6e59f6debcdf7f0a3702463cbcc94c2 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/15/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:cf33974551d05b8ceb9cd1a50600a67929d6942440651dff69521c961e15a156 +size 25166192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/15/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/model/model/decoder/15/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/15/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/15/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/15/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2ac9190373d983fa6015341ab32369870a0152cb --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/15/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:acb91e30ea7960fa457398026bc32924e86ca34a1f0b7232abdb6d75614c1bde +size 23068912 diff --git a/_init_1.5B_seed42/0/model/model/decoder/15/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/15/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..352f353edaa184e39866f4c38b48b41ee94247b1 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/15/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:fd9396ea99866b4fae63f4072bfc2d0f4240129bdeba3e9ef696b4db7a1ecf20 +size 46137656 diff --git a/_init_1.5B_seed42/0/model/model/decoder/15/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/model/model/decoder/15/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/15/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/16/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/16/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..00848ff8d7294394a06eddc5f3e9184f475b92de --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/16/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 sha256:173eaf6a9146967dd281c82fa877e49683123ae4848d392d475a6d54e869f2d7 +size 46137656 diff --git a/_init_1.5B_seed42/0/model/model/decoder/18/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/18/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9628eadca5af4aa5e3b1be64844fbf58b7c0f04b --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/18/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:b654c42c0e6488e13cd5419d94ca1a03742fdb46cb651ff4cd414dd06eea1900 +size 8388848 diff --git a/_init_1.5B_seed42/0/model/model/decoder/18/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/18/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1ce008b37416e0d42e117c6b97ff2140cfb693b5 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/18/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 sha256:104f6d585b53877a0210963371f0bda36b99d6f0c41e8165ee15a893850799aa +size 25166192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/18/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/model/model/decoder/18/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/18/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/18/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/18/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cccbb91590788f97820b30b3ad11e93b0c130363 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/18/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 sha256:456926b24acdd0985be9a225c1c211ede9df5c64f620c7ad6cd74efdd968108b +size 23068912 diff --git a/_init_1.5B_seed42/0/model/model/decoder/18/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/18/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..186cf01fd80aa0f95574c25dd595d9d40f35df9f --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/18/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 sha256:08b36d2aa8c7eecdd00305b912eb540ad4bf6e7d1997fff291a9e06e1cbcbbb4 +size 46137656 diff --git a/_init_1.5B_seed42/0/model/model/decoder/18/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/model/model/decoder/18/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/18/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/input_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/model/model/decoder/19/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed42/0/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_seed42/0/model/model/decoder/19/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/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_seed42/0/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_seed42/0/model/model/decoder/2/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/2/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ad428f48471e79a294325d6703d6cb853406a23a --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/2/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 sha256:00d7dadd06ab51ea148c2df4bfde7f250bbe18a2210a3c680dc1edd3751cdc14 +size 25166192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/2/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/2/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..87aab1647836243ce0423efab4b639e0e601153f --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/2/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 sha256:03f7832c71b599d4c90457a400f840499b1dcfac8ef6759553d2500de8c2103f +size 46137656 diff --git a/_init_1.5B_seed42/0/model/model/decoder/20/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/20/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cdeff11ae8ed529c03d369d2b3a68ccc3115b3b7 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/20/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:f6b1ad7dd9eb4862e603aa92dea2983b2bcd5ffa0547a7f2b3d1fc40b9fd5a79 +size 8388848 diff --git a/_init_1.5B_seed42/0/model/model/decoder/20/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/20/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..344943d8f9595d7a0a207583792323e270ad0fe3 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/20/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:cb10353d8fa254041f9d1b5a835439a3ee5c24190a922a654f61db1cbf1c23a5 +size 25166192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/20/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/model/model/decoder/20/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/20/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/20/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/20/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3d769897097083e34ea2e1b7434c5ac587c1343b --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/20/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:be167ef313a166eef1776794e539b55c9732afe9da22211ca8040828480e4fa1 +size 23068912 diff --git a/_init_1.5B_seed42/0/model/model/decoder/20/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/20/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..a0ce7b0e7eed1b71d895beef87b32bbd7cd1d110 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/20/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 sha256:37fc0f538986272dd2c3dd68f31623596cbe1afae09da1a6f17498028d9f8e3c +size 46137656 diff --git a/_init_1.5B_seed42/0/model/model/decoder/20/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/model/model/decoder/20/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/20/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/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/22/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a55a1eb0cf59082b523656ee5a11477d7243a802 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/22/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 sha256:0fe12c8ccdd86a1fb4a46a6907db6d48838dd6ce22bdac131c5602ae59791329 +size 8388848 diff --git a/_init_1.5B_seed42/0/model/model/decoder/22/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/22/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a870b5c8b5ed41264a55c348ac3da8d201b39924 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/22/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:fd3683c45aa4f037235fd0f1b20242e242a0f0a25f040fce5f489eae98f2dda2 +size 25166192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/22/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/model/model/decoder/22/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/22/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/22/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/22/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..97dfad5bb6a86ce2146c91cdbc8f5b32f66d66f1 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/22/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 sha256:26d3ce2081400ee53255dcb4a7ac85cf4d89fc7b5b91cf996713245424bf9342 +size 23068912 diff --git a/_init_1.5B_seed42/0/model/model/decoder/22/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/model/model/decoder/22/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/22/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/23/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/23/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2bb3dca5da0114beb20ab1ff1538a7e11a51a89d --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/23/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 sha256:2b052af6b78d4e2f34572f9160e7be87c885955b8609abb275de65b8c0e78b05 +size 8388848 diff --git a/_init_1.5B_seed42/0/model/model/decoder/23/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/23/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..beb6e3032fdcadca410fbbfb024f841336513538 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/23/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:a72f884d0741515fb2e4d44bff5e1b478e0f91d9a99f4b66eeba967fdeb5b928 +size 25166192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/23/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/model/model/decoder/23/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/23/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/23/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/23/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6493294bc0d509f67b59b0dbcef5b253230cad8c --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/23/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 sha256:060201b1c7c394e7a63b0f3fe5c19de44c83607e32fc017e8acf3a455cc9b103 +size 23068912 diff --git a/_init_1.5B_seed42/0/model/model/decoder/23/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/23/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..a516d1b27650065c780567b972e752a28f6e8b9a --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/23/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 sha256:03463037e47a3dc486d89863f7748115fe4e634c0a66dfba344f84edbb023258 +size 46137656 diff --git a/_init_1.5B_seed42/0/model/model/decoder/23/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/model/model/decoder/23/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/23/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/25/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/25/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bd83ec6c0ea24cdc923fd6c96254e34b086ce59b --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/25/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 sha256:8f9da3e936e1edf57fb9003ae5cf5b6d28e47a8a93562cdbb4b204bfa5b8ab99 +size 8388848 diff --git a/_init_1.5B_seed42/0/model/model/decoder/25/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/25/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b5e413328095e199543985a4cf618d521770e83a --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/25/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 sha256:6d5f3cd3ea94d9ab66e3c5bca616997fcb018c20262f315e17be5e910a31670f +size 25166192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/25/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/model/model/decoder/25/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/25/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/25/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/25/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e87c9dd151724f0b9539ef3b4a0f19d21b390638 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/25/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 sha256:900c4968e877d949173534743539685ba92c791dce1fec582e9bd524e4139807 +size 23068912 diff --git a/_init_1.5B_seed42/0/model/model/decoder/25/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/25/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..74f5a92661b1aa92e51945597c2867b3f0354cba --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/25/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 sha256:002312c51362947c5a12666f4522427781037d99131cad9f77f4b84f59a177fc +size 46137656 diff --git a/_init_1.5B_seed42/0/model/model/decoder/25/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/model/model/decoder/25/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/25/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/5/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/5/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..39344937c06dd06feacdab954a311a372485dc51 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/5/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:a1b6790fb6839a1645ddfa46e832d940f2fcea128241b24536213e262d6aa853 +size 8388848 diff --git a/_init_1.5B_seed42/0/model/model/decoder/5/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/5/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..68a35f6699a9d45dc1677131dd3338cd9e525ed0 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/5/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 sha256:03bcd576043964ac3e054a3224a966a29762a350f0b1188eb7bc0617aaddd8b8 +size 25166192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/5/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/model/model/decoder/5/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/5/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/5/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/5/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0f7ab31b75229a2def31fa10503929ad339c8b99 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/5/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 sha256:40a25e027673ae8d49397f5d157ff41283664abefe8e841f93b1dbf3e9591c99 +size 23068912 diff --git a/_init_1.5B_seed42/0/model/model/decoder/5/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/5/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..4fd70d3aa534f252722d65df3528ba9e29207141 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/5/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 sha256:8fedf514dcf5dee68201c1ac3b9ac47822cb13db00fd72b4ff720dd65e7c7abd +size 46137656 diff --git a/_init_1.5B_seed42/0/model/model/decoder/5/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/model/model/decoder/5/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/5/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/6/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/6/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..636dc990b21e17052ac3da05c07f66b5d583eee3 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/6/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 sha256:968ebebe9f6d46cadc3cae4b2215b5fccdf9f12e1c2774d96ba29ea9ca0cc47c +size 8388848 diff --git a/_init_1.5B_seed42/0/model/model/decoder/6/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/6/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b880cb5417dd713dfb1ca4661967a6e5540e848f --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/6/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:c060c066463f7699d4dfde114d5ce49dd1a058780b05ef2a71215a0216633658 +size 25166192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/6/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/model/model/decoder/6/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/6/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/6/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/6/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e53bb7feb24c79c98187e71d812ca89fb60fade6 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/6/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 sha256:21c02e9590946f70e018832285a707121a1b468a7c4eebd5e87d1656993301ce +size 23068912 diff --git a/_init_1.5B_seed42/0/model/model/decoder/6/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/6/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..54286d2a02bc17091172e4c566def5226e7e7b0a --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/6/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 sha256:6d939ac539eec90405747378123e01c8dfb1b5f77a4f5aebd34acb756503a96c +size 46137656 diff --git a/_init_1.5B_seed42/0/model/model/decoder/7/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/7/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e246b63f60c0d39651a243b8a4890a719fcca277 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/7/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 sha256:107d4fe85a51fbf1856ba32d9c1b5e9939baaba108193587a1c067612e86e10e +size 8388848 diff --git a/_init_1.5B_seed42/0/model/model/decoder/7/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/7/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..46330493d6b88d7da7c2f93d27d9482afdad084d --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/7/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:e6b5e74a5f6618dbff0f36d752ff346e09475fe24602d49dcd533c8c77232175 +size 25166192 diff --git a/_init_1.5B_seed42/0/model/model/decoder/7/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/model/model/decoder/7/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/7/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/7/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/7/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..05089c5c3477b7bf778866070ada17f52308f39b --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/7/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 sha256:41c507fc7e754197b5661fee495f5f9beb95fe700d6be0099480ef46f8a461e3 +size 23068912 diff --git a/_init_1.5B_seed42/0/model/model/decoder/7/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/7/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..076e74f13d5e71d6f89da0e6b11d326f21d5425d --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/decoder/7/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:f167274ac5a2aea243e88014f71b59b8a9f4c128c7fb3bbbe6461608974c46c4 +size 46137656 diff --git a/_init_1.5B_seed42/0/model/model/decoder/7/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed42/0/model/model/decoder/7/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/7/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