From e5bcfe45c970408bb58c32570e9616d2c4bd6b2b Mon Sep 17 00:00:00 2001 From: Haijunlv <248354172@qq.com> Date: Wed, 15 Jan 2025 11:06:48 +0000 Subject: [PATCH] bf16 ckpt upload --- model-00001-of-00002.safetensors | 3 + model-00001-of-00004.safetensors | 3 - model-00002-of-00002.safetensors | 3 + model-00002-of-00004.safetensors | 3 - model-00003-of-00004.safetensors | 3 - model-00004-of-00004.safetensors | 3 - model.safetensors.index.json | 872 +++++++++++++++---------------- 7 files changed, 442 insertions(+), 448 deletions(-) create mode 100644 model-00001-of-00002.safetensors delete mode 100644 model-00001-of-00004.safetensors create mode 100644 model-00002-of-00002.safetensors delete mode 100644 model-00002-of-00004.safetensors delete mode 100644 model-00003-of-00004.safetensors delete mode 100644 model-00004-of-00004.safetensors diff --git a/model-00001-of-00002.safetensors b/model-00001-of-00002.safetensors new file mode 100644 index 0000000..2783011 --- /dev/null +++ b/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a18eb700cd28f03c0745ac75ab53ead514cfa703fabb82c61a37b85cb593ff4 +size 9928388896 diff --git a/model-00001-of-00004.safetensors b/model-00001-of-00004.safetensors deleted file mode 100644 index b9b1a7e..0000000 --- a/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:f8a1b8c2aecbe72356241a5b5e861ba029f4e61189c4c0a9ca9821e66679f6f5 -size 9999626944 diff --git a/model-00002-of-00002.safetensors b/model-00002-of-00002.safetensors new file mode 100644 index 0000000..c5800ae --- /dev/null +++ b/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e324110df616ca5190f20469528f13421476f38f0e2597dac4d9ee0bdcede797 +size 7680144544 diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors deleted file mode 100644 index 38a5d23..0000000 --- a/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:7eefc1671b07fe3aefb5011f381eb4524c27595cab06e56fbeac256ebe24b18d -size 9857121648 diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors deleted file mode 100644 index 0742534..0000000 --- a/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:536775814f5fd4327c11ae5dcdab5f537ab733aae90df9ef425ea06984802fe5 -size 9857121632 diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors deleted file mode 100644 index 2d38c90..0000000 --- a/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:e6b47cfd723371ff07d585cc48355c16f15b03a48281f7933ecf339a299d64b3 -size 5503145608 diff --git a/model.safetensors.index.json b/model.safetensors.index.json index d474737..d731713 100644 --- a/model.safetensors.index.json +++ b/model.safetensors.index.json @@ -1,442 +1,442 @@ { "metadata": { - "total_size": 35216965632 + "total_size": 17608482816 }, "weight_map": { - "lm_head.weight": "model-00004-of-00004.safetensors", - "model.embed_tokens.weight": "model-00001-of-00004.safetensors", - "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", - "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", - "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", - "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", - "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors", - "model.layers.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", - "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors", - "model.layers.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", - "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors", - "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", - "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors", - "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", - "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors", - "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", - "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors", - "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", - "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors", - "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", - "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors", - "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", - "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors", - "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", - "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors", - "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", - "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", - "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", - "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors", - "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", - "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors", - "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", - "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors", - "model.layers.22.mlp.down_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", - "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors", - "model.layers.23.mlp.down_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", - "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.24.input_layernorm.weight": "model-00002-of-00004.safetensors", - "model.layers.24.mlp.down_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", - "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.25.input_layernorm.weight": "model-00002-of-00004.safetensors", - "model.layers.25.mlp.down_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", - "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.26.input_layernorm.weight": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.down_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", - "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", - "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", - "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", - "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", - "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", - "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", - "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", - "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", - "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", - "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", - "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", - "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", - "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", - "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors", - "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", - "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors", - "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", - "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors", - "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", - "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.35.input_layernorm.weight": "model-00003-of-00004.safetensors", - "model.layers.35.mlp.down_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.35.mlp.up_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", - "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.36.input_layernorm.weight": "model-00003-of-00004.safetensors", - "model.layers.36.mlp.down_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.36.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.36.mlp.up_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.36.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", - "model.layers.36.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.36.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.36.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.36.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.37.input_layernorm.weight": "model-00003-of-00004.safetensors", - "model.layers.37.mlp.down_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.37.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.37.mlp.up_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.37.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", - "model.layers.37.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.37.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.37.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.37.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.38.input_layernorm.weight": "model-00003-of-00004.safetensors", - "model.layers.38.mlp.down_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.38.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.38.mlp.up_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", - "model.layers.38.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.38.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.38.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.38.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.39.input_layernorm.weight": "model-00003-of-00004.safetensors", - "model.layers.39.mlp.down_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.39.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.39.mlp.up_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.39.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", - "model.layers.39.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.39.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.39.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.39.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", - "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", - "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.40.input_layernorm.weight": "model-00003-of-00004.safetensors", - "model.layers.40.mlp.down_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.40.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.40.mlp.up_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.40.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", - "model.layers.40.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.40.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.40.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.40.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.41.input_layernorm.weight": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.down_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.41.mlp.up_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.41.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", - "model.layers.41.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.41.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.41.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.41.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.42.input_layernorm.weight": "model-00004-of-00004.safetensors", - "model.layers.42.mlp.down_proj.weight": "model-00004-of-00004.safetensors", - "model.layers.42.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.42.mlp.up_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.42.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", - "model.layers.42.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.42.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.42.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.42.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", - "model.layers.43.input_layernorm.weight": "model-00004-of-00004.safetensors", - "model.layers.43.mlp.down_proj.weight": "model-00004-of-00004.safetensors", - "model.layers.43.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", - "model.layers.43.mlp.up_proj.weight": "model-00004-of-00004.safetensors", - "model.layers.43.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", - "model.layers.43.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", - "model.layers.43.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", - "model.layers.43.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", - "model.layers.43.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", - "model.layers.44.input_layernorm.weight": "model-00004-of-00004.safetensors", - "model.layers.44.mlp.down_proj.weight": "model-00004-of-00004.safetensors", - "model.layers.44.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", - "model.layers.44.mlp.up_proj.weight": "model-00004-of-00004.safetensors", - "model.layers.44.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", - "model.layers.44.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", - "model.layers.44.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", - "model.layers.44.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", - "model.layers.44.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", - "model.layers.45.input_layernorm.weight": "model-00004-of-00004.safetensors", - "model.layers.45.mlp.down_proj.weight": "model-00004-of-00004.safetensors", - "model.layers.45.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", - "model.layers.45.mlp.up_proj.weight": "model-00004-of-00004.safetensors", - "model.layers.45.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", - "model.layers.45.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", - "model.layers.45.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", - "model.layers.45.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", - "model.layers.45.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", - "model.layers.46.input_layernorm.weight": "model-00004-of-00004.safetensors", - "model.layers.46.mlp.down_proj.weight": "model-00004-of-00004.safetensors", - "model.layers.46.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", - "model.layers.46.mlp.up_proj.weight": "model-00004-of-00004.safetensors", - "model.layers.46.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", - "model.layers.46.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", - "model.layers.46.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", - "model.layers.46.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", - "model.layers.46.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", - "model.layers.47.input_layernorm.weight": "model-00004-of-00004.safetensors", - "model.layers.47.mlp.down_proj.weight": "model-00004-of-00004.safetensors", - "model.layers.47.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", - "model.layers.47.mlp.up_proj.weight": "model-00004-of-00004.safetensors", - "model.layers.47.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", - "model.layers.47.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", - "model.layers.47.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", - "model.layers.47.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", - "model.layers.47.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", - "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors", - "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", - "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors", - "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", - "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors", - "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", - "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors", - "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", - "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors", - "model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", - "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", - "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", - "model.norm.weight": "model-00004-of-00004.safetensors" + "lm_head.weight": "model-00002-of-00002.safetensors", + "model.embed_tokens.weight": "model-00001-of-00002.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.36.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.36.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.36.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.36.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.37.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.37.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.37.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.37.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.38.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.38.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.38.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.38.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.39.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.39.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.39.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.39.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.40.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.40.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.40.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.40.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.41.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.41.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.41.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.41.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.42.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.42.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.42.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.42.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.43.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.43.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.43.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.43.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.44.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.44.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.44.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.44.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.45.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.45.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.45.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.45.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.46.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.46.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.46.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.46.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.46.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.46.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.46.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.46.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.47.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.47.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.47.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.47.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.47.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.47.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.47.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.47.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.norm.weight": "model-00002-of-00002.safetensors" } }