Fixed tokenizer

model-00005-of-00009.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1d56824727ffaf568f7a1c7770fd5cb531df71ebe143567b1cb3968aca7f98cd
-size 4983012192

model-00006-of-00009.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9f30bb3fdbcad8d1c00e0b421908bebc6cb5544669cd3c916ae592acb7263ae4
-size 4957821336

model-00007-of-00009.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:54eb704485dce4f8c7c245169d25f394ea08dec1562a1ab981715f294ef93314
-size 4882323744

model-00008-of-00009.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:cfbe26e02d475904ecc92cbe54a614607156aabed3503867d8af5023673d6374
-size 4983012192

model-00009-of-00009.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c834720ddae75dc683e52284ffe27ea35f48eb2c5500c71025925fe0dd398a8c
-size 4982999056

model.safetensors.index.json

@@ -1,514 +0,0 @@
-{
-    "metadata": {
-        "total_size": 44494565376
-    },
-    "weight_map": {
-        "lm_head.weight": "model-00009-of-00009.safetensors",
-        "model.embed_tokens.weight": "model-00001-of-00009.safetensors",
-        "model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors",
-        "model.layers.0.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
-        "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
-        "model.layers.0.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
-        "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
-        "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
-        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
-        "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
-        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
-        "model.layers.1.input_layernorm.weight": "model-00001-of-00009.safetensors",
-        "model.layers.1.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
-        "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
-        "model.layers.1.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
-        "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
-        "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
-        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
-        "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
-        "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
-        "model.layers.10.input_layernorm.weight": "model-00002-of-00009.safetensors",
-        "model.layers.10.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
-        "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
-        "model.layers.10.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
-        "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
-        "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
-        "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
-        "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
-        "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
-        "model.layers.11.input_layernorm.weight": "model-00002-of-00009.safetensors",
-        "model.layers.11.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
-        "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
-        "model.layers.11.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
-        "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
-        "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
-        "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
-        "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
-        "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
-        "model.layers.12.input_layernorm.weight": "model-00003-of-00009.safetensors",
-        "model.layers.12.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
-        "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
-        "model.layers.12.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
-        "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
-        "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
-        "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
-        "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
-        "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
-        "model.layers.13.input_layernorm.weight": "model-00003-of-00009.safetensors",
-        "model.layers.13.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
-        "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
-        "model.layers.13.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
-        "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
-        "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
-        "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
-        "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
-        "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
-        "model.layers.14.input_layernorm.weight": "model-00003-of-00009.safetensors",
-        "model.layers.14.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
-        "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
-        "model.layers.14.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
-        "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
-        "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
-        "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
-        "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
-        "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
-        "model.layers.15.input_layernorm.weight": "model-00003-of-00009.safetensors",
-        "model.layers.15.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
-        "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
-        "model.layers.15.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
-        "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
-        "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
-        "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
-        "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
-        "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
-        "model.layers.16.input_layernorm.weight": "model-00003-of-00009.safetensors",
-        "model.layers.16.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
-        "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
-        "model.layers.16.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
-        "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
-        "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
-        "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
-        "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
-        "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
-        "model.layers.17.input_layernorm.weight": "model-00003-of-00009.safetensors",
-        "model.layers.17.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
-        "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
-        "model.layers.17.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
-        "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
-        "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
-        "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
-        "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
-        "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
-        "model.layers.18.input_layernorm.weight": "model-00004-of-00009.safetensors",
-        "model.layers.18.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
-        "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
-        "model.layers.18.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
-        "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
-        "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
-        "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
-        "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
-        "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
-        "model.layers.19.input_layernorm.weight": "model-00004-of-00009.safetensors",
-        "model.layers.19.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
-        "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
-        "model.layers.19.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
-        "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
-        "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
-        "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
-        "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
-        "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
-        "model.layers.2.input_layernorm.weight": "model-00001-of-00009.safetensors",
-        "model.layers.2.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
-        "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
-        "model.layers.2.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
-        "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
-        "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
-        "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
-        "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
-        "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
-        "model.layers.20.input_layernorm.weight": "model-00004-of-00009.safetensors",
-        "model.layers.20.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
-        "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
-        "model.layers.20.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
-        "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
-        "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
-        "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
-        "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
-        "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
-        "model.layers.21.input_layernorm.weight": "model-00004-of-00009.safetensors",
-        "model.layers.21.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
-        "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
-        "model.layers.21.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
-        "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
-        "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
-        "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
-        "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
-        "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
-        "model.layers.22.input_layernorm.weight": "model-00004-of-00009.safetensors",
-        "model.layers.22.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
-        "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
-        "model.layers.22.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
-        "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
-        "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
-        "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
-        "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
-        "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
-        "model.layers.23.input_layernorm.weight": "model-00004-of-00009.safetensors",
-        "model.layers.23.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
-        "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
-        "model.layers.23.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
-        "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
-        "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
-        "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
-        "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
-        "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
-        "model.layers.24.input_layernorm.weight": "model-00005-of-00009.safetensors",
-        "model.layers.24.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
-        "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
-        "model.layers.24.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
-        "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
-        "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
-        "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
-        "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
-        "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
-        "model.layers.25.input_layernorm.weight": "model-00005-of-00009.safetensors",
-        "model.layers.25.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
-        "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
-        "model.layers.25.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
-        "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
-        "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
-        "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
-        "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
-        "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
-        "model.layers.26.input_layernorm.weight": "model-00005-of-00009.safetensors",
-        "model.layers.26.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
-        "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
-        "model.layers.26.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
-        "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
-        "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
-        "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
-        "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
-        "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
-        "model.layers.27.input_layernorm.weight": "model-00005-of-00009.safetensors",
-        "model.layers.27.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
-        "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
-        "model.layers.27.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
-        "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
-        "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
-        "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
-        "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
-        "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
-        "model.layers.28.input_layernorm.weight": "model-00005-of-00009.safetensors",
-        "model.layers.28.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
-        "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
-        "model.layers.28.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
-        "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
-        "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
-        "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
-        "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
-        "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
-        "model.layers.29.input_layernorm.weight": "model-00005-of-00009.safetensors",
-        "model.layers.29.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
-        "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
-        "model.layers.29.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
-        "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
-        "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
-        "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
-        "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
-        "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
-        "model.layers.3.input_layernorm.weight": "model-00001-of-00009.safetensors",
-        "model.layers.3.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
-        "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
-        "model.layers.3.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
-        "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
-        "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
-        "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
-        "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
-        "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
-        "model.layers.30.input_layernorm.weight": "model-00005-of-00009.safetensors",
-        "model.layers.30.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
-        "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
-        "model.layers.30.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
-        "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
-        "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
-        "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
-        "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
-        "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
-        "model.layers.31.input_layernorm.weight": "model-00006-of-00009.safetensors",
-        "model.layers.31.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
-        "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
-        "model.layers.31.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
-        "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
-        "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
-        "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
-        "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
-        "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
-        "model.layers.32.input_layernorm.weight": "model-00006-of-00009.safetensors",
-        "model.layers.32.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
-        "model.layers.32.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
-        "model.layers.32.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
-        "model.layers.32.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
-        "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
-        "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
-        "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
-        "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
-        "model.layers.33.input_layernorm.weight": "model-00006-of-00009.safetensors",
-        "model.layers.33.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
-        "model.layers.33.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
-        "model.layers.33.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
-        "model.layers.33.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
-        "model.layers.33.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
-        "model.layers.33.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
-        "model.layers.33.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
-        "model.layers.33.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
-        "model.layers.34.input_layernorm.weight": "model-00006-of-00009.safetensors",
-        "model.layers.34.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
-        "model.layers.34.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
-        "model.layers.34.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
-        "model.layers.34.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
-        "model.layers.34.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
-        "model.layers.34.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
-        "model.layers.34.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
-        "model.layers.34.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
-        "model.layers.35.input_layernorm.weight": "model-00006-of-00009.safetensors",
-        "model.layers.35.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
-        "model.layers.35.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
-        "model.layers.35.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
-        "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
-        "model.layers.35.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
-        "model.layers.35.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
-        "model.layers.35.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
-        "model.layers.35.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
-        "model.layers.36.input_layernorm.weight": "model-00006-of-00009.safetensors",
-        "model.layers.36.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
-        "model.layers.36.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
-        "model.layers.36.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
-        "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
-        "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
-        "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
-        "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
-        "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
-        "model.layers.37.input_layernorm.weight": "model-00007-of-00009.safetensors",
-        "model.layers.37.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
-        "model.layers.37.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
-        "model.layers.37.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
-        "model.layers.37.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
-        "model.layers.37.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
-        "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
-        "model.layers.37.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
-        "model.layers.37.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
-        "model.layers.38.input_layernorm.weight": "model-00007-of-00009.safetensors",
-        "model.layers.38.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
-        "model.layers.38.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
-        "model.layers.38.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
-        "model.layers.38.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
-        "model.layers.38.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
-        "model.layers.38.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
-        "model.layers.38.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
-        "model.layers.38.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
-        "model.layers.39.input_layernorm.weight": "model-00007-of-00009.safetensors",
-        "model.layers.39.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
-        "model.layers.39.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
-        "model.layers.39.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
-        "model.layers.39.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
-        "model.layers.39.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
-        "model.layers.39.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
-        "model.layers.39.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
-        "model.layers.39.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
-        "model.layers.4.input_layernorm.weight": "model-00001-of-00009.safetensors",
-        "model.layers.4.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
-        "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
-        "model.layers.4.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
-        "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
-        "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
-        "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
-        "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
-        "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
-        "model.layers.40.input_layernorm.weight": "model-00007-of-00009.safetensors",
-        "model.layers.40.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
-        "model.layers.40.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
-        "model.layers.40.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
-        "model.layers.40.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
-        "model.layers.40.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
-        "model.layers.40.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
-        "model.layers.40.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
-        "model.layers.40.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
-        "model.layers.41.input_layernorm.weight": "model-00007-of-00009.safetensors",
-        "model.layers.41.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
-        "model.layers.41.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
-        "model.layers.41.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
-        "model.layers.41.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
-        "model.layers.41.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
-        "model.layers.41.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
-        "model.layers.41.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
-        "model.layers.41.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
-        "model.layers.42.input_layernorm.weight": "model-00007-of-00009.safetensors",
-        "model.layers.42.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
-        "model.layers.42.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
-        "model.layers.42.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
-        "model.layers.42.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
-        "model.layers.42.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
-        "model.layers.42.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
-        "model.layers.42.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
-        "model.layers.42.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
-        "model.layers.43.input_layernorm.weight": "model-00008-of-00009.safetensors",
-        "model.layers.43.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
-        "model.layers.43.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
-        "model.layers.43.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
-        "model.layers.43.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
-        "model.layers.43.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
-        "model.layers.43.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
-        "model.layers.43.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
-        "model.layers.43.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
-        "model.layers.44.input_layernorm.weight": "model-00008-of-00009.safetensors",
-        "model.layers.44.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
-        "model.layers.44.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
-        "model.layers.44.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
-        "model.layers.44.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
-        "model.layers.44.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
-        "model.layers.44.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
-        "model.layers.44.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
-        "model.layers.44.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
-        "model.layers.45.input_layernorm.weight": "model-00008-of-00009.safetensors",
-        "model.layers.45.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
-        "model.layers.45.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
-        "model.layers.45.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
-        "model.layers.45.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
-        "model.layers.45.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
-        "model.layers.45.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
-        "model.layers.45.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
-        "model.layers.45.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
-        "model.layers.46.input_layernorm.weight": "model-00008-of-00009.safetensors",
-        "model.layers.46.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
-        "model.layers.46.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
-        "model.layers.46.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
-        "model.layers.46.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
-        "model.layers.46.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
-        "model.layers.46.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
-        "model.layers.46.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
-        "model.layers.46.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
-        "model.layers.47.input_layernorm.weight": "model-00008-of-00009.safetensors",
-        "model.layers.47.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
-        "model.layers.47.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
-        "model.layers.47.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
-        "model.layers.47.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
-        "model.layers.47.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
-        "model.layers.47.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
-        "model.layers.47.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
-        "model.layers.47.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
-        "model.layers.48.input_layernorm.weight": "model-00008-of-00009.safetensors",
-        "model.layers.48.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
-        "model.layers.48.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
-        "model.layers.48.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
-        "model.layers.48.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
-        "model.layers.48.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
-        "model.layers.48.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
-        "model.layers.48.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
-        "model.layers.48.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
-        "model.layers.49.input_layernorm.weight": "model-00008-of-00009.safetensors",
-        "model.layers.49.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
-        "model.layers.49.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
-        "model.layers.49.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
-        "model.layers.49.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
-        "model.layers.49.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
-        "model.layers.49.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
-        "model.layers.49.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
-        "model.layers.49.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
-        "model.layers.5.input_layernorm.weight": "model-00002-of-00009.safetensors",
-        "model.layers.5.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
-        "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
-        "model.layers.5.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
-        "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
-        "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
-        "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
-        "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
-        "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
-        "model.layers.50.input_layernorm.weight": "model-00009-of-00009.safetensors",
-        "model.layers.50.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
-        "model.layers.50.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
-        "model.layers.50.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
-        "model.layers.50.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
-        "model.layers.50.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
-        "model.layers.50.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
-        "model.layers.50.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
-        "model.layers.50.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
-        "model.layers.51.input_layernorm.weight": "model-00009-of-00009.safetensors",
-        "model.layers.51.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
-        "model.layers.51.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
-        "model.layers.51.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
-        "model.layers.51.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
-        "model.layers.51.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
-        "model.layers.51.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
-        "model.layers.51.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
-        "model.layers.51.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
-        "model.layers.52.input_layernorm.weight": "model-00009-of-00009.safetensors",
-        "model.layers.52.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
-        "model.layers.52.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
-        "model.layers.52.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
-        "model.layers.52.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
-        "model.layers.52.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
-        "model.layers.52.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
-        "model.layers.52.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
-        "model.layers.52.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
-        "model.layers.53.input_layernorm.weight": "model-00009-of-00009.safetensors",
-        "model.layers.53.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
-        "model.layers.53.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
-        "model.layers.53.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
-        "model.layers.53.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
-        "model.layers.53.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
-        "model.layers.53.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
-        "model.layers.53.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
-        "model.layers.53.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
-        "model.layers.54.input_layernorm.weight": "model-00009-of-00009.safetensors",
-        "model.layers.54.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
-        "model.layers.54.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
-        "model.layers.54.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
-        "model.layers.54.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
-        "model.layers.54.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
-        "model.layers.54.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
-        "model.layers.54.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
-        "model.layers.54.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
-        "model.layers.55.input_layernorm.weight": "model-00009-of-00009.safetensors",
-        "model.layers.55.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
-        "model.layers.55.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
-        "model.layers.55.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
-        "model.layers.55.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
-        "model.layers.55.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
-        "model.layers.55.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
-        "model.layers.55.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
-        "model.layers.55.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
-        "model.layers.6.input_layernorm.weight": "model-00002-of-00009.safetensors",
-        "model.layers.6.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
-        "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
-        "model.layers.6.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
-        "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
-        "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
-        "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
-        "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
-        "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
-        "model.layers.7.input_layernorm.weight": "model-00002-of-00009.safetensors",
-        "model.layers.7.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
-        "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
-        "model.layers.7.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
-        "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
-        "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
-        "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
-        "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
-        "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
-        "model.layers.8.input_layernorm.weight": "model-00002-of-00009.safetensors",
-        "model.layers.8.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
-        "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
-        "model.layers.8.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
-        "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
-        "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
-        "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
-        "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
-        "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
-        "model.layers.9.input_layernorm.weight": "model-00002-of-00009.safetensors",
-        "model.layers.9.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
-        "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
-        "model.layers.9.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
-        "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
-        "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
-        "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
-        "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
-        "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
-        "model.norm.weight": "model-00009-of-00009.safetensors"
-    }
-}

model-00001-of-00009.safetensors → pytorch_model-00001-of-00009.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c911e66544527032c9e49f602ed0645f748045248eb8fb8ec9982866b899674
-size 4882298776
+oid sha256:f2d169a7eefffa4c0d721dc96a4b28d0f73fb3c60d952b0fa91d562d0c5fea12
+size 4882310690

model-00002-of-00009.safetensors → pytorch_model-00002-of-00009.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc1de07197a04eaeeaa6dcb7ed6604f729ed822e92273c25c112f85c366b5696
-size 4983012160
+oid sha256:0b8a822039f8559ff62aa4b4c999e150b4be122ff18fda2cf9f499b73ab5218f
+size 4983025842

model-00003-of-00009.safetensors → pytorch_model-00003-of-00009.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90dc483e3b22d3d21a03edd588a8ffe5743b8dea33fc9f1ffc01eb1e529aedf8
-size 4957821336
+oid sha256:57081ca29e4ed331c6be97bdfa10d02975f85e77f842b9274ae6807779764011
+size 4957834250

model-00004-of-00009.safetensors → pytorch_model-00004-of-00009.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76ee31da7cdd8fde0a257030ffdf7d3fb293935a62b8469f6dec1c1a19e14eee
-size 4882323744
+oid sha256:a0a5c5a69adf3cf1065b6249b0437dda45c580eb7367c03f0c9655db525fcc25
+size 4882336280

pytorch_model-00005-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0945e5ec61f8224b5f3faa7760a2e630d89fff96ecd37a28aa636d5807c6eaf1
+size 4983025906

pytorch_model-00006-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee337d4c1510e8cb2a4d40cd43995fe52706a06b2190962aba0d505de632c27b
+size 4957834250

pytorch_model-00007-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2470f6eabfdb42a11b8fcc23bc3d4925ad8910943f777b465c67458a4bac1f7
+size 4882336280

pytorch_model-00008-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94f300617d691e157744ef8239c8112ba3a6adc0abef94137a72852589febb4e
+size 4983025906

pytorch_model-00009-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bdeb338b300dd4ae38efba0010c1f6d2700f151efcb071ce3c43ed3c9c4caab
+size 4983011248

pytorch_model.bin.index.json

@@ -0,0 +1,514 @@
+{
+  "metadata": {
+    "total_size": 44494565376
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00009-of-00009.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.32.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.40.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.40.mlp.down_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.40.mlp.gate_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.40.mlp.up_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.40.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.41.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.41.mlp.down_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.41.mlp.gate_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.41.mlp.up_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.41.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.42.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.42.mlp.down_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.42.mlp.gate_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.42.mlp.up_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.42.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.43.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.43.mlp.down_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.43.mlp.gate_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.43.mlp.up_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.43.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.44.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.44.mlp.down_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.44.mlp.gate_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.44.mlp.up_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.44.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.45.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.45.mlp.down_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.45.mlp.gate_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.45.mlp.up_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.45.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.46.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.46.mlp.down_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.46.mlp.gate_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.46.mlp.up_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.46.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.47.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.47.mlp.down_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.47.mlp.gate_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.47.mlp.up_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.47.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.48.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.48.mlp.down_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.48.mlp.gate_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.48.mlp.up_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.48.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.48.self_attn.k_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.48.self_attn.o_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.48.self_attn.q_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.48.self_attn.v_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.49.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.49.mlp.down_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.49.mlp.gate_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.49.mlp.up_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.49.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.49.self_attn.k_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.49.self_attn.o_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.49.self_attn.q_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.49.self_attn.v_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.50.input_layernorm.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.50.mlp.down_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.50.mlp.gate_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.50.mlp.up_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.50.post_attention_layernorm.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.50.self_attn.k_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.50.self_attn.o_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.50.self_attn.q_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.50.self_attn.v_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.51.input_layernorm.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.51.mlp.down_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.51.mlp.gate_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.51.mlp.up_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.51.post_attention_layernorm.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.51.self_attn.k_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.51.self_attn.o_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.51.self_attn.q_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.51.self_attn.v_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.52.input_layernorm.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.52.mlp.down_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.52.mlp.gate_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.52.mlp.up_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.52.post_attention_layernorm.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.52.self_attn.k_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.52.self_attn.o_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.52.self_attn.q_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.52.self_attn.v_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.53.input_layernorm.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.53.mlp.down_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.53.mlp.gate_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.53.mlp.up_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.53.post_attention_layernorm.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.53.self_attn.k_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.53.self_attn.o_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.53.self_attn.q_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.53.self_attn.v_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.54.input_layernorm.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.54.mlp.down_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.54.mlp.gate_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.54.mlp.up_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.54.post_attention_layernorm.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.54.self_attn.k_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.54.self_attn.o_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.54.self_attn.q_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.54.self_attn.v_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.55.input_layernorm.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.55.mlp.down_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.55.mlp.gate_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.55.mlp.up_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.55.post_attention_layernorm.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.55.self_attn.k_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.55.self_attn.o_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.55.self_attn.q_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.55.self_attn.v_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.norm.weight": "pytorch_model-00009-of-00009.bin"
+  }
+}

tokenizer.json

@@ -146,10 +146,10 @@
       "[/AVAILABLE_TOOLS]": 7,
       "[TOOL_RESULTS]": 8,
       "[/TOOL_RESULTS]": 9,
-      "[control_8]": 10,
-      "[control_9]": 11,
-      "[control_10]": 12,
-      "[control_11]": 13,
+      "[IMG]": 10,
+      "[PREFIX]": 11,
+      "[MIDDLE]": 12,
+      "[SUFFIX]": 13,
       "[control_12]": 14,
       "[control_13]": 15,
       "[control_14]": 16,
@@ -887,26 +887,26 @@
       "[control_746]": 748,
       "[control_747]": 749,
       "[control_748]": 750,
-      "[control_749]": 751,
-      "[control_750]": 752,
-      "[control_751]": 753,
-      "[control_752]": 754,
-      "[control_753]": 755,
-      "[control_754]": 756,
-      "[control_755]": 757,
-      "[control_756]": 758,
-      "[control_757]": 759,
-      "[control_758]": 760,
-      "[control_759]": 761,
-      "[control_760]": 762,
-      "[control_761]": 763,
-      "[control_762]": 764,
-      "[control_763]": 765,
-      "[control_764]": 766,
-      "[control_765]": 767,
-      "[control_766]": 768,
-      "[control_767]": 769,
-      "[control_768]": 770,
+      "[REFERENCE_DOC_19]": 751,
+      "[REFERENCE_DOC_18]": 752,
+      "[REFERENCE_DOC_17]": 753,
+      "[REFERENCE_DOC_16]": 754,
+      "[REFERENCE_DOC_15]": 755,
+      "[REFERENCE_DOC_14]": 756,
+      "[REFERENCE_DOC_13]": 757,
+      "[REFERENCE_DOC_12]": 758,
+      "[REFERENCE_DOC_11]": 759,
+      "[REFERENCE_DOC_10]": 760,
+      "[REFERENCE_DOC_9]": 761,
+      "[REFERENCE_DOC_8]": 762,
+      "[REFERENCE_DOC_7]": 763,
+      "[REFERENCE_DOC_6]": 764,
+      "[REFERENCE_DOC_5]": 765,
+      "[REFERENCE_DOC_4]": 766,
+      "[REFERENCE_DOC_3]": 767,
+      "[REFERENCE_DOC_2]": 768,
+      "[REFERENCE_DOC_1]": 769,
+      "[REFERENCE_DOC_0]": 770,
       "<0x00>": 771,
       "<0x01>": 772,
       "<0x02>": 773,

tokenizer.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
-size 587404
+oid sha256:9addc8bdce5988448ae81b729336f43a81262160ae8da760674badab9d4c7d33
+size 587591