Upload folder using huggingface_hub

model-00001-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5e97075e0c19df479262454b603fc30bc5704876aa48450afab3d85b012cac6
+size 943874528

model-00002-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee69597bdc4eb443e8e15c9fb7db429baa3f0b0891bb7ebe8ec081184b32d43b
+size 944060848

model-00003-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd3fd176dde66b967eaa762f685b0372c47180a2b3440d3000a61636a7660e7f
+size 944060848

model-00004-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2248e79deacf416dd7bf5cbc9f4709ed01c129067933dae52281d8ec886d12b8
+size 944060856

model-00005-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4be3c45cf88df087d1cfe92acc989a36820ed0021148722eab430f567276ce2
+size 944060888

model-00006-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42e8f5afb8d5a49b8b43f833efd7c41ee542603f2b5a5b92a82b317398245dde
+size 944060888

model-00007-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67350c3da1a5b08ae842576b58f3ea5c3ec75de2176ddd3252038a70b80ffafb
+size 944060888

model-00008-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e89bb2f02da1b74ad2d730a604d81b2a407138b84e5dbf86fdc9c1222575fc3
+size 944060888

model-00009-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4f3c066e84735164f62f10262ee6bd6124b7869e2154fb54b0e5e9e79906d42
+size 944060888

model-00010-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7687d2afe329ebaca218fe3aaf727508ac3b740d467049faba7424cfa19b102f
+size 944060888

model-00011-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ebbac03ef972dcde03cabb8b43455eaa79a92d4ecf7b3a92105b4f51a184480
+size 944060888

model-00012-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:013f52a1cb64974c888a1bd7395455c6effa33d8b13d32c07b7771251235a6c2
+size 734301192

model.safetensors.index.json

@@ -0,0 +1,460 @@
+{
+  "metadata": {
+    "total_size": 11118735360
+  },
+  "weight_map": {
+    "lm_head.bias": "model-00012-of-00012.safetensors",
+    "lm_head.weight": "model-00012-of-00012.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00012.safetensors",
+    "model.final_layernorm.bias": "model-00012-of-00012.safetensors",
+    "model.final_layernorm.weight": "model-00012-of-00012.safetensors",
+    "model.layers.0.input_layernorm.bias": "model-00001-of-00012.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.mlp.fc1.bias": "model-00001-of-00012.safetensors",
+    "model.layers.0.mlp.fc1.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.mlp.fc2.bias": "model-00001-of-00012.safetensors",
+    "model.layers.0.mlp.fc2.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.self_attn.dense.bias": "model-00001-of-00012.safetensors",
+    "model.layers.0.self_attn.dense.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.input_layernorm.bias": "model-00002-of-00012.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.1.mlp.fc1.bias": "model-00002-of-00012.safetensors",
+    "model.layers.1.mlp.fc1.weight": "model-00002-of-00012.safetensors",
+    "model.layers.1.mlp.fc2.bias": "model-00002-of-00012.safetensors",
+    "model.layers.1.mlp.fc2.weight": "model-00002-of-00012.safetensors",
+    "model.layers.1.self_attn.dense.bias": "model-00001-of-00012.safetensors",
+    "model.layers.1.self_attn.dense.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.10.input_layernorm.bias": "model-00005-of-00012.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00005-of-00012.safetensors",
+    "model.layers.10.mlp.fc1.bias": "model-00005-of-00012.safetensors",
+    "model.layers.10.mlp.fc1.weight": "model-00005-of-00012.safetensors",
+    "model.layers.10.mlp.fc2.bias": "model-00005-of-00012.safetensors",
+    "model.layers.10.mlp.fc2.weight": "model-00005-of-00012.safetensors",
+    "model.layers.10.self_attn.dense.bias": "model-00004-of-00012.safetensors",
+    "model.layers.10.self_attn.dense.weight": "model-00004-of-00012.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00004-of-00012.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00004-of-00012.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00004-of-00012.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.11.input_layernorm.bias": "model-00005-of-00012.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00005-of-00012.safetensors",
+    "model.layers.11.mlp.fc1.bias": "model-00005-of-00012.safetensors",
+    "model.layers.11.mlp.fc1.weight": "model-00005-of-00012.safetensors",
+    "model.layers.11.mlp.fc2.bias": "model-00005-of-00012.safetensors",
+    "model.layers.11.mlp.fc2.weight": "model-00005-of-00012.safetensors",
+    "model.layers.11.self_attn.dense.bias": "model-00005-of-00012.safetensors",
+    "model.layers.11.self_attn.dense.weight": "model-00005-of-00012.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00005-of-00012.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00005-of-00012.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00005-of-00012.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.12.input_layernorm.bias": "model-00005-of-00012.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00005-of-00012.safetensors",
+    "model.layers.12.mlp.fc1.bias": "model-00005-of-00012.safetensors",
+    "model.layers.12.mlp.fc1.weight": "model-00005-of-00012.safetensors",
+    "model.layers.12.mlp.fc2.bias": "model-00005-of-00012.safetensors",
+    "model.layers.12.mlp.fc2.weight": "model-00005-of-00012.safetensors",
+    "model.layers.12.self_attn.dense.bias": "model-00005-of-00012.safetensors",
+    "model.layers.12.self_attn.dense.weight": "model-00005-of-00012.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00005-of-00012.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00005-of-00012.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00005-of-00012.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.13.input_layernorm.bias": "model-00006-of-00012.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.13.mlp.fc1.bias": "model-00006-of-00012.safetensors",
+    "model.layers.13.mlp.fc1.weight": "model-00006-of-00012.safetensors",
+    "model.layers.13.mlp.fc2.bias": "model-00006-of-00012.safetensors",
+    "model.layers.13.mlp.fc2.weight": "model-00006-of-00012.safetensors",
+    "model.layers.13.self_attn.dense.bias": "model-00005-of-00012.safetensors",
+    "model.layers.13.self_attn.dense.weight": "model-00005-of-00012.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00005-of-00012.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00005-of-00012.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00005-of-00012.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.14.input_layernorm.bias": "model-00006-of-00012.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.14.mlp.fc1.bias": "model-00006-of-00012.safetensors",
+    "model.layers.14.mlp.fc1.weight": "model-00006-of-00012.safetensors",
+    "model.layers.14.mlp.fc2.bias": "model-00006-of-00012.safetensors",
+    "model.layers.14.mlp.fc2.weight": "model-00006-of-00012.safetensors",
+    "model.layers.14.self_attn.dense.bias": "model-00006-of-00012.safetensors",
+    "model.layers.14.self_attn.dense.weight": "model-00006-of-00012.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00006-of-00012.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00006-of-00012.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00006-of-00012.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.15.input_layernorm.bias": "model-00006-of-00012.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.15.mlp.fc1.bias": "model-00006-of-00012.safetensors",
+    "model.layers.15.mlp.fc1.weight": "model-00006-of-00012.safetensors",
+    "model.layers.15.mlp.fc2.bias": "model-00006-of-00012.safetensors",
+    "model.layers.15.mlp.fc2.weight": "model-00006-of-00012.safetensors",
+    "model.layers.15.self_attn.dense.bias": "model-00006-of-00012.safetensors",
+    "model.layers.15.self_attn.dense.weight": "model-00006-of-00012.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00006-of-00012.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00006-of-00012.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00006-of-00012.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.16.input_layernorm.bias": "model-00007-of-00012.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00007-of-00012.safetensors",
+    "model.layers.16.mlp.fc1.bias": "model-00007-of-00012.safetensors",
+    "model.layers.16.mlp.fc1.weight": "model-00007-of-00012.safetensors",
+    "model.layers.16.mlp.fc2.bias": "model-00007-of-00012.safetensors",
+    "model.layers.16.mlp.fc2.weight": "model-00007-of-00012.safetensors",
+    "model.layers.16.self_attn.dense.bias": "model-00006-of-00012.safetensors",
+    "model.layers.16.self_attn.dense.weight": "model-00006-of-00012.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00006-of-00012.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00006-of-00012.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00006-of-00012.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.17.input_layernorm.bias": "model-00007-of-00012.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00007-of-00012.safetensors",
+    "model.layers.17.mlp.fc1.bias": "model-00007-of-00012.safetensors",
+    "model.layers.17.mlp.fc1.weight": "model-00007-of-00012.safetensors",
+    "model.layers.17.mlp.fc2.bias": "model-00007-of-00012.safetensors",
+    "model.layers.17.mlp.fc2.weight": "model-00007-of-00012.safetensors",
+    "model.layers.17.self_attn.dense.bias": "model-00007-of-00012.safetensors",
+    "model.layers.17.self_attn.dense.weight": "model-00007-of-00012.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00007-of-00012.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00007-of-00012.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00007-of-00012.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.18.input_layernorm.bias": "model-00007-of-00012.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00007-of-00012.safetensors",
+    "model.layers.18.mlp.fc1.bias": "model-00007-of-00012.safetensors",
+    "model.layers.18.mlp.fc1.weight": "model-00007-of-00012.safetensors",
+    "model.layers.18.mlp.fc2.bias": "model-00007-of-00012.safetensors",
+    "model.layers.18.mlp.fc2.weight": "model-00007-of-00012.safetensors",
+    "model.layers.18.self_attn.dense.bias": "model-00007-of-00012.safetensors",
+    "model.layers.18.self_attn.dense.weight": "model-00007-of-00012.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00007-of-00012.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00007-of-00012.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00007-of-00012.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.19.input_layernorm.bias": "model-00008-of-00012.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.19.mlp.fc1.bias": "model-00008-of-00012.safetensors",
+    "model.layers.19.mlp.fc1.weight": "model-00008-of-00012.safetensors",
+    "model.layers.19.mlp.fc2.bias": "model-00008-of-00012.safetensors",
+    "model.layers.19.mlp.fc2.weight": "model-00008-of-00012.safetensors",
+    "model.layers.19.self_attn.dense.bias": "model-00007-of-00012.safetensors",
+    "model.layers.19.self_attn.dense.weight": "model-00007-of-00012.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00007-of-00012.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00007-of-00012.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00007-of-00012.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.2.input_layernorm.bias": "model-00002-of-00012.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.2.mlp.fc1.bias": "model-00002-of-00012.safetensors",
+    "model.layers.2.mlp.fc1.weight": "model-00002-of-00012.safetensors",
+    "model.layers.2.mlp.fc2.bias": "model-00002-of-00012.safetensors",
+    "model.layers.2.mlp.fc2.weight": "model-00002-of-00012.safetensors",
+    "model.layers.2.self_attn.dense.bias": "model-00002-of-00012.safetensors",
+    "model.layers.2.self_attn.dense.weight": "model-00002-of-00012.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00002-of-00012.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00002-of-00012.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00002-of-00012.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.20.input_layernorm.bias": "model-00008-of-00012.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.20.mlp.fc1.bias": "model-00008-of-00012.safetensors",
+    "model.layers.20.mlp.fc1.weight": "model-00008-of-00012.safetensors",
+    "model.layers.20.mlp.fc2.bias": "model-00008-of-00012.safetensors",
+    "model.layers.20.mlp.fc2.weight": "model-00008-of-00012.safetensors",
+    "model.layers.20.self_attn.dense.bias": "model-00008-of-00012.safetensors",
+    "model.layers.20.self_attn.dense.weight": "model-00008-of-00012.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00008-of-00012.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00008-of-00012.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00008-of-00012.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.21.input_layernorm.bias": "model-00008-of-00012.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.21.mlp.fc1.bias": "model-00008-of-00012.safetensors",
+    "model.layers.21.mlp.fc1.weight": "model-00008-of-00012.safetensors",
+    "model.layers.21.mlp.fc2.bias": "model-00008-of-00012.safetensors",
+    "model.layers.21.mlp.fc2.weight": "model-00008-of-00012.safetensors",
+    "model.layers.21.self_attn.dense.bias": "model-00008-of-00012.safetensors",
+    "model.layers.21.self_attn.dense.weight": "model-00008-of-00012.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00008-of-00012.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00008-of-00012.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00008-of-00012.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.22.input_layernorm.bias": "model-00009-of-00012.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.22.mlp.fc1.bias": "model-00009-of-00012.safetensors",
+    "model.layers.22.mlp.fc1.weight": "model-00009-of-00012.safetensors",
+    "model.layers.22.mlp.fc2.bias": "model-00009-of-00012.safetensors",
+    "model.layers.22.mlp.fc2.weight": "model-00009-of-00012.safetensors",
+    "model.layers.22.self_attn.dense.bias": "model-00008-of-00012.safetensors",
+    "model.layers.22.self_attn.dense.weight": "model-00008-of-00012.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00008-of-00012.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00008-of-00012.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00008-of-00012.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.23.input_layernorm.bias": "model-00009-of-00012.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.23.mlp.fc1.bias": "model-00009-of-00012.safetensors",
+    "model.layers.23.mlp.fc1.weight": "model-00009-of-00012.safetensors",
+    "model.layers.23.mlp.fc2.bias": "model-00009-of-00012.safetensors",
+    "model.layers.23.mlp.fc2.weight": "model-00009-of-00012.safetensors",
+    "model.layers.23.self_attn.dense.bias": "model-00009-of-00012.safetensors",
+    "model.layers.23.self_attn.dense.weight": "model-00009-of-00012.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00009-of-00012.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00009-of-00012.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00009-of-00012.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.24.input_layernorm.bias": "model-00009-of-00012.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.24.mlp.fc1.bias": "model-00009-of-00012.safetensors",
+    "model.layers.24.mlp.fc1.weight": "model-00009-of-00012.safetensors",
+    "model.layers.24.mlp.fc2.bias": "model-00009-of-00012.safetensors",
+    "model.layers.24.mlp.fc2.weight": "model-00009-of-00012.safetensors",
+    "model.layers.24.self_attn.dense.bias": "model-00009-of-00012.safetensors",
+    "model.layers.24.self_attn.dense.weight": "model-00009-of-00012.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00009-of-00012.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00009-of-00012.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00009-of-00012.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.25.input_layernorm.bias": "model-00010-of-00012.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.25.mlp.fc1.bias": "model-00010-of-00012.safetensors",
+    "model.layers.25.mlp.fc1.weight": "model-00010-of-00012.safetensors",
+    "model.layers.25.mlp.fc2.bias": "model-00010-of-00012.safetensors",
+    "model.layers.25.mlp.fc2.weight": "model-00010-of-00012.safetensors",
+    "model.layers.25.self_attn.dense.bias": "model-00009-of-00012.safetensors",
+    "model.layers.25.self_attn.dense.weight": "model-00009-of-00012.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00009-of-00012.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00009-of-00012.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00009-of-00012.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.26.input_layernorm.bias": "model-00010-of-00012.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.26.mlp.fc1.bias": "model-00010-of-00012.safetensors",
+    "model.layers.26.mlp.fc1.weight": "model-00010-of-00012.safetensors",
+    "model.layers.26.mlp.fc2.bias": "model-00010-of-00012.safetensors",
+    "model.layers.26.mlp.fc2.weight": "model-00010-of-00012.safetensors",
+    "model.layers.26.self_attn.dense.bias": "model-00010-of-00012.safetensors",
+    "model.layers.26.self_attn.dense.weight": "model-00010-of-00012.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00010-of-00012.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00010-of-00012.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00010-of-00012.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.27.input_layernorm.bias": "model-00010-of-00012.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.27.mlp.fc1.bias": "model-00010-of-00012.safetensors",
+    "model.layers.27.mlp.fc1.weight": "model-00010-of-00012.safetensors",
+    "model.layers.27.mlp.fc2.bias": "model-00010-of-00012.safetensors",
+    "model.layers.27.mlp.fc2.weight": "model-00010-of-00012.safetensors",
+    "model.layers.27.self_attn.dense.bias": "model-00010-of-00012.safetensors",
+    "model.layers.27.self_attn.dense.weight": "model-00010-of-00012.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00010-of-00012.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00010-of-00012.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00010-of-00012.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.28.input_layernorm.bias": "model-00011-of-00012.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00011-of-00012.safetensors",
+    "model.layers.28.mlp.fc1.bias": "model-00011-of-00012.safetensors",
+    "model.layers.28.mlp.fc1.weight": "model-00011-of-00012.safetensors",
+    "model.layers.28.mlp.fc2.bias": "model-00011-of-00012.safetensors",
+    "model.layers.28.mlp.fc2.weight": "model-00011-of-00012.safetensors",
+    "model.layers.28.self_attn.dense.bias": "model-00010-of-00012.safetensors",
+    "model.layers.28.self_attn.dense.weight": "model-00010-of-00012.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00010-of-00012.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00010-of-00012.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00010-of-00012.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.29.input_layernorm.bias": "model-00011-of-00012.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00011-of-00012.safetensors",
+    "model.layers.29.mlp.fc1.bias": "model-00011-of-00012.safetensors",
+    "model.layers.29.mlp.fc1.weight": "model-00011-of-00012.safetensors",
+    "model.layers.29.mlp.fc2.bias": "model-00011-of-00012.safetensors",
+    "model.layers.29.mlp.fc2.weight": "model-00011-of-00012.safetensors",
+    "model.layers.29.self_attn.dense.bias": "model-00011-of-00012.safetensors",
+    "model.layers.29.self_attn.dense.weight": "model-00011-of-00012.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00011-of-00012.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00011-of-00012.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00011-of-00012.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.3.input_layernorm.bias": "model-00002-of-00012.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.3.mlp.fc1.bias": "model-00002-of-00012.safetensors",
+    "model.layers.3.mlp.fc1.weight": "model-00002-of-00012.safetensors",
+    "model.layers.3.mlp.fc2.bias": "model-00002-of-00012.safetensors",
+    "model.layers.3.mlp.fc2.weight": "model-00002-of-00012.safetensors",
+    "model.layers.3.self_attn.dense.bias": "model-00002-of-00012.safetensors",
+    "model.layers.3.self_attn.dense.weight": "model-00002-of-00012.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00012.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00012.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00012.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.30.input_layernorm.bias": "model-00011-of-00012.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00011-of-00012.safetensors",
+    "model.layers.30.mlp.fc1.bias": "model-00011-of-00012.safetensors",
+    "model.layers.30.mlp.fc1.weight": "model-00011-of-00012.safetensors",
+    "model.layers.30.mlp.fc2.bias": "model-00011-of-00012.safetensors",
+    "model.layers.30.mlp.fc2.weight": "model-00011-of-00012.safetensors",
+    "model.layers.30.self_attn.dense.bias": "model-00011-of-00012.safetensors",
+    "model.layers.30.self_attn.dense.weight": "model-00011-of-00012.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00011-of-00012.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00011-of-00012.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00011-of-00012.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.31.input_layernorm.bias": "model-00012-of-00012.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00012-of-00012.safetensors",
+    "model.layers.31.mlp.fc1.bias": "model-00012-of-00012.safetensors",
+    "model.layers.31.mlp.fc1.weight": "model-00012-of-00012.safetensors",
+    "model.layers.31.mlp.fc2.bias": "model-00012-of-00012.safetensors",
+    "model.layers.31.mlp.fc2.weight": "model-00012-of-00012.safetensors",
+    "model.layers.31.self_attn.dense.bias": "model-00011-of-00012.safetensors",
+    "model.layers.31.self_attn.dense.weight": "model-00011-of-00012.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00011-of-00012.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00011-of-00012.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00011-of-00012.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.4.input_layernorm.bias": "model-00003-of-00012.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00003-of-00012.safetensors",
+    "model.layers.4.mlp.fc1.bias": "model-00003-of-00012.safetensors",
+    "model.layers.4.mlp.fc1.weight": "model-00003-of-00012.safetensors",
+    "model.layers.4.mlp.fc2.bias": "model-00003-of-00012.safetensors",
+    "model.layers.4.mlp.fc2.weight": "model-00003-of-00012.safetensors",
+    "model.layers.4.self_attn.dense.bias": "model-00002-of-00012.safetensors",
+    "model.layers.4.self_attn.dense.weight": "model-00002-of-00012.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00012.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00012.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00012.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.5.input_layernorm.bias": "model-00003-of-00012.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00003-of-00012.safetensors",
+    "model.layers.5.mlp.fc1.bias": "model-00003-of-00012.safetensors",
+    "model.layers.5.mlp.fc1.weight": "model-00003-of-00012.safetensors",
+    "model.layers.5.mlp.fc2.bias": "model-00003-of-00012.safetensors",
+    "model.layers.5.mlp.fc2.weight": "model-00003-of-00012.safetensors",
+    "model.layers.5.self_attn.dense.bias": "model-00003-of-00012.safetensors",
+    "model.layers.5.self_attn.dense.weight": "model-00003-of-00012.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00003-of-00012.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00003-of-00012.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00003-of-00012.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.6.input_layernorm.bias": "model-00003-of-00012.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00003-of-00012.safetensors",
+    "model.layers.6.mlp.fc1.bias": "model-00003-of-00012.safetensors",
+    "model.layers.6.mlp.fc1.weight": "model-00003-of-00012.safetensors",
+    "model.layers.6.mlp.fc2.bias": "model-00003-of-00012.safetensors",
+    "model.layers.6.mlp.fc2.weight": "model-00003-of-00012.safetensors",
+    "model.layers.6.self_attn.dense.bias": "model-00003-of-00012.safetensors",
+    "model.layers.6.self_attn.dense.weight": "model-00003-of-00012.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00003-of-00012.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00003-of-00012.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00003-of-00012.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.input_layernorm.bias": "model-00004-of-00012.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.7.mlp.fc1.bias": "model-00004-of-00012.safetensors",
+    "model.layers.7.mlp.fc1.weight": "model-00004-of-00012.safetensors",
+    "model.layers.7.mlp.fc2.bias": "model-00004-of-00012.safetensors",
+    "model.layers.7.mlp.fc2.weight": "model-00004-of-00012.safetensors",
+    "model.layers.7.self_attn.dense.bias": "model-00003-of-00012.safetensors",
+    "model.layers.7.self_attn.dense.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00003-of-00012.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00003-of-00012.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00003-of-00012.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.8.input_layernorm.bias": "model-00004-of-00012.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.8.mlp.fc1.bias": "model-00004-of-00012.safetensors",
+    "model.layers.8.mlp.fc1.weight": "model-00004-of-00012.safetensors",
+    "model.layers.8.mlp.fc2.bias": "model-00004-of-00012.safetensors",
+    "model.layers.8.mlp.fc2.weight": "model-00004-of-00012.safetensors",
+    "model.layers.8.self_attn.dense.bias": "model-00004-of-00012.safetensors",
+    "model.layers.8.self_attn.dense.weight": "model-00004-of-00012.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00004-of-00012.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00004-of-00012.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00004-of-00012.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.9.input_layernorm.bias": "model-00004-of-00012.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.9.mlp.fc1.bias": "model-00004-of-00012.safetensors",
+    "model.layers.9.mlp.fc1.weight": "model-00004-of-00012.safetensors",
+    "model.layers.9.mlp.fc2.bias": "model-00004-of-00012.safetensors",
+    "model.layers.9.mlp.fc2.weight": "model-00004-of-00012.safetensors",
+    "model.layers.9.self_attn.dense.bias": "model-00004-of-00012.safetensors",
+    "model.layers.9.self_attn.dense.weight": "model-00004-of-00012.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00004-of-00012.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00004-of-00012.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00004-of-00012.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00012.safetensors"
+  }
+}