converted weights to bfloat16

model-00001-of-00005.safetensors → model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5d9e891e9ddf087b29ad5127b8ab20beeb8e94ab60209f0f4a2b81a10ca0f24
-size 4987196936
+oid sha256:f3fef19ad1b20a191da0fa5710b59f3c8ae81e11fe09380ccb9ddd3eeb9cf585
+size 9942998312

model-00002-of-00005.safetensors → model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95c760fff7199f7947f1ba02301242a3121e9d292f97696ec77b7d3d2c4fb9c7
-size 4899116440
+oid sha256:f3cdd4a4869ac2b62f69e0425d9fb22c5694d647516a12e5be45317520b0ae35
+size 1050699328

model-00003-of-00005.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5fa28bdda4140e796e982032dfc97a1f837bd29c5f709992cd93f8011a3f5919
-size 4999813120

model-00004-of-00005.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0410cb6078a4fe852794f50dc380087ebf5070c1749b77c5053ba96b5dbdff62
-size 4999813128

model-00005-of-00005.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c3bc9f065a4c75e622d75eae4676e10c370559d9213f21490948700d8d401d49
-size 2101430048

model.safetensors.index.json

@@ -1,226 +1 @@
-{
-  "metadata": {
-    "total_size": 21987344384
-  },
-  "weight_map": {
-    "lm_head.weight": "model-00005-of-00005.safetensors",
-    "model.embed_tokens.weight": "model-00001-of-00005.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00005-of-00005.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00005-of-00005.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-    "model.norm.weight": "model-00005-of-00005.safetensors"
-  }
-}
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 10993672192}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00002.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.norm.weight": "model-00002-of-00002.safetensors", "lm_head.weight": "model-00002-of-00002.safetensors"}}