Adding `safetensors` variant of this model

model.safetensors.index.json

@@ -0,0 +1,852 @@
+{
+    "metadata": {
+        "total_size": 352494542848
+    },
+    "weight_map": {
+        "h.0.input_layernorm.bias": "model_00002-of-00072.safetensors",
+        "h.0.input_layernorm.weight": "model_00002-of-00072.safetensors",
+        "h.0.mlp.dense_4h_to_h.bias": "model_00002-of-00072.safetensors",
+        "h.0.mlp.dense_4h_to_h.weight": "model_00002-of-00072.safetensors",
+        "h.0.mlp.dense_h_to_4h.bias": "model_00002-of-00072.safetensors",
+        "h.0.mlp.dense_h_to_4h.weight": "model_00002-of-00072.safetensors",
+        "h.0.post_attention_layernorm.bias": "model_00002-of-00072.safetensors",
+        "h.0.post_attention_layernorm.weight": "model_00002-of-00072.safetensors",
+        "h.0.self_attention.dense.bias": "model_00002-of-00072.safetensors",
+        "h.0.self_attention.dense.weight": "model_00002-of-00072.safetensors",
+        "h.0.self_attention.query_key_value.bias": "model_00002-of-00072.safetensors",
+        "h.0.self_attention.query_key_value.weight": "model_00002-of-00072.safetensors",
+        "h.1.input_layernorm.bias": "model_00003-of-00072.safetensors",
+        "h.1.input_layernorm.weight": "model_00003-of-00072.safetensors",
+        "h.1.mlp.dense_4h_to_h.bias": "model_00003-of-00072.safetensors",
+        "h.1.mlp.dense_4h_to_h.weight": "model_00003-of-00072.safetensors",
+        "h.1.mlp.dense_h_to_4h.bias": "model_00003-of-00072.safetensors",
+        "h.1.mlp.dense_h_to_4h.weight": "model_00003-of-00072.safetensors",
+        "h.1.post_attention_layernorm.bias": "model_00003-of-00072.safetensors",
+        "h.1.post_attention_layernorm.weight": "model_00003-of-00072.safetensors",
+        "h.1.self_attention.dense.bias": "model_00003-of-00072.safetensors",
+        "h.1.self_attention.dense.weight": "model_00003-of-00072.safetensors",
+        "h.1.self_attention.query_key_value.bias": "model_00003-of-00072.safetensors",
+        "h.1.self_attention.query_key_value.weight": "model_00003-of-00072.safetensors",
+        "h.10.input_layernorm.bias": "model_00012-of-00072.safetensors",
+        "h.10.input_layernorm.weight": "model_00012-of-00072.safetensors",
+        "h.10.mlp.dense_4h_to_h.bias": "model_00012-of-00072.safetensors",
+        "h.10.mlp.dense_4h_to_h.weight": "model_00012-of-00072.safetensors",
+        "h.10.mlp.dense_h_to_4h.bias": "model_00012-of-00072.safetensors",
+        "h.10.mlp.dense_h_to_4h.weight": "model_00012-of-00072.safetensors",
+        "h.10.post_attention_layernorm.bias": "model_00012-of-00072.safetensors",
+        "h.10.post_attention_layernorm.weight": "model_00012-of-00072.safetensors",
+        "h.10.self_attention.dense.bias": "model_00012-of-00072.safetensors",
+        "h.10.self_attention.dense.weight": "model_00012-of-00072.safetensors",
+        "h.10.self_attention.query_key_value.bias": "model_00012-of-00072.safetensors",
+        "h.10.self_attention.query_key_value.weight": "model_00012-of-00072.safetensors",
+        "h.11.input_layernorm.bias": "model_00013-of-00072.safetensors",
+        "h.11.input_layernorm.weight": "model_00013-of-00072.safetensors",
+        "h.11.mlp.dense_4h_to_h.bias": "model_00013-of-00072.safetensors",
+        "h.11.mlp.dense_4h_to_h.weight": "model_00013-of-00072.safetensors",
+        "h.11.mlp.dense_h_to_4h.bias": "model_00013-of-00072.safetensors",
+        "h.11.mlp.dense_h_to_4h.weight": "model_00013-of-00072.safetensors",
+        "h.11.post_attention_layernorm.bias": "model_00013-of-00072.safetensors",
+        "h.11.post_attention_layernorm.weight": "model_00013-of-00072.safetensors",
+        "h.11.self_attention.dense.bias": "model_00013-of-00072.safetensors",
+        "h.11.self_attention.dense.weight": "model_00013-of-00072.safetensors",
+        "h.11.self_attention.query_key_value.bias": "model_00013-of-00072.safetensors",
+        "h.11.self_attention.query_key_value.weight": "model_00013-of-00072.safetensors",
+        "h.12.input_layernorm.bias": "model_00014-of-00072.safetensors",
+        "h.12.input_layernorm.weight": "model_00014-of-00072.safetensors",
+        "h.12.mlp.dense_4h_to_h.bias": "model_00014-of-00072.safetensors",
+        "h.12.mlp.dense_4h_to_h.weight": "model_00014-of-00072.safetensors",
+        "h.12.mlp.dense_h_to_4h.bias": "model_00014-of-00072.safetensors",
+        "h.12.mlp.dense_h_to_4h.weight": "model_00014-of-00072.safetensors",
+        "h.12.post_attention_layernorm.bias": "model_00014-of-00072.safetensors",
+        "h.12.post_attention_layernorm.weight": "model_00014-of-00072.safetensors",
+        "h.12.self_attention.dense.bias": "model_00014-of-00072.safetensors",
+        "h.12.self_attention.dense.weight": "model_00014-of-00072.safetensors",
+        "h.12.self_attention.query_key_value.bias": "model_00014-of-00072.safetensors",
+        "h.12.self_attention.query_key_value.weight": "model_00014-of-00072.safetensors",
+        "h.13.input_layernorm.bias": "model_00015-of-00072.safetensors",
+        "h.13.input_layernorm.weight": "model_00015-of-00072.safetensors",
+        "h.13.mlp.dense_4h_to_h.bias": "model_00015-of-00072.safetensors",
+        "h.13.mlp.dense_4h_to_h.weight": "model_00015-of-00072.safetensors",
+        "h.13.mlp.dense_h_to_4h.bias": "model_00015-of-00072.safetensors",
+        "h.13.mlp.dense_h_to_4h.weight": "model_00015-of-00072.safetensors",
+        "h.13.post_attention_layernorm.bias": "model_00015-of-00072.safetensors",
+        "h.13.post_attention_layernorm.weight": "model_00015-of-00072.safetensors",
+        "h.13.self_attention.dense.bias": "model_00015-of-00072.safetensors",
+        "h.13.self_attention.dense.weight": "model_00015-of-00072.safetensors",
+        "h.13.self_attention.query_key_value.bias": "model_00015-of-00072.safetensors",
+        "h.13.self_attention.query_key_value.weight": "model_00015-of-00072.safetensors",
+        "h.14.input_layernorm.bias": "model_00016-of-00072.safetensors",
+        "h.14.input_layernorm.weight": "model_00016-of-00072.safetensors",
+        "h.14.mlp.dense_4h_to_h.bias": "model_00016-of-00072.safetensors",
+        "h.14.mlp.dense_4h_to_h.weight": "model_00016-of-00072.safetensors",
+        "h.14.mlp.dense_h_to_4h.bias": "model_00016-of-00072.safetensors",
+        "h.14.mlp.dense_h_to_4h.weight": "model_00016-of-00072.safetensors",
+        "h.14.post_attention_layernorm.bias": "model_00016-of-00072.safetensors",
+        "h.14.post_attention_layernorm.weight": "model_00016-of-00072.safetensors",
+        "h.14.self_attention.dense.bias": "model_00016-of-00072.safetensors",
+        "h.14.self_attention.dense.weight": "model_00016-of-00072.safetensors",
+        "h.14.self_attention.query_key_value.bias": "model_00016-of-00072.safetensors",
+        "h.14.self_attention.query_key_value.weight": "model_00016-of-00072.safetensors",
+        "h.15.input_layernorm.bias": "model_00017-of-00072.safetensors",
+        "h.15.input_layernorm.weight": "model_00017-of-00072.safetensors",
+        "h.15.mlp.dense_4h_to_h.bias": "model_00017-of-00072.safetensors",
+        "h.15.mlp.dense_4h_to_h.weight": "model_00017-of-00072.safetensors",
+        "h.15.mlp.dense_h_to_4h.bias": "model_00017-of-00072.safetensors",
+        "h.15.mlp.dense_h_to_4h.weight": "model_00017-of-00072.safetensors",
+        "h.15.post_attention_layernorm.bias": "model_00017-of-00072.safetensors",
+        "h.15.post_attention_layernorm.weight": "model_00017-of-00072.safetensors",
+        "h.15.self_attention.dense.bias": "model_00017-of-00072.safetensors",
+        "h.15.self_attention.dense.weight": "model_00017-of-00072.safetensors",
+        "h.15.self_attention.query_key_value.bias": "model_00017-of-00072.safetensors",
+        "h.15.self_attention.query_key_value.weight": "model_00017-of-00072.safetensors",
+        "h.16.input_layernorm.bias": "model_00018-of-00072.safetensors",
+        "h.16.input_layernorm.weight": "model_00018-of-00072.safetensors",
+        "h.16.mlp.dense_4h_to_h.bias": "model_00018-of-00072.safetensors",
+        "h.16.mlp.dense_4h_to_h.weight": "model_00018-of-00072.safetensors",
+        "h.16.mlp.dense_h_to_4h.bias": "model_00018-of-00072.safetensors",
+        "h.16.mlp.dense_h_to_4h.weight": "model_00018-of-00072.safetensors",
+        "h.16.post_attention_layernorm.bias": "model_00018-of-00072.safetensors",
+        "h.16.post_attention_layernorm.weight": "model_00018-of-00072.safetensors",
+        "h.16.self_attention.dense.bias": "model_00018-of-00072.safetensors",
+        "h.16.self_attention.dense.weight": "model_00018-of-00072.safetensors",
+        "h.16.self_attention.query_key_value.bias": "model_00018-of-00072.safetensors",
+        "h.16.self_attention.query_key_value.weight": "model_00018-of-00072.safetensors",
+        "h.17.input_layernorm.bias": "model_00019-of-00072.safetensors",
+        "h.17.input_layernorm.weight": "model_00019-of-00072.safetensors",
+        "h.17.mlp.dense_4h_to_h.bias": "model_00019-of-00072.safetensors",
+        "h.17.mlp.dense_4h_to_h.weight": "model_00019-of-00072.safetensors",
+        "h.17.mlp.dense_h_to_4h.bias": "model_00019-of-00072.safetensors",
+        "h.17.mlp.dense_h_to_4h.weight": "model_00019-of-00072.safetensors",
+        "h.17.post_attention_layernorm.bias": "model_00019-of-00072.safetensors",
+        "h.17.post_attention_layernorm.weight": "model_00019-of-00072.safetensors",
+        "h.17.self_attention.dense.bias": "model_00019-of-00072.safetensors",
+        "h.17.self_attention.dense.weight": "model_00019-of-00072.safetensors",
+        "h.17.self_attention.query_key_value.bias": "model_00019-of-00072.safetensors",
+        "h.17.self_attention.query_key_value.weight": "model_00019-of-00072.safetensors",
+        "h.18.input_layernorm.bias": "model_00020-of-00072.safetensors",
+        "h.18.input_layernorm.weight": "model_00020-of-00072.safetensors",
+        "h.18.mlp.dense_4h_to_h.bias": "model_00020-of-00072.safetensors",
+        "h.18.mlp.dense_4h_to_h.weight": "model_00020-of-00072.safetensors",
+        "h.18.mlp.dense_h_to_4h.bias": "model_00020-of-00072.safetensors",
+        "h.18.mlp.dense_h_to_4h.weight": "model_00020-of-00072.safetensors",
+        "h.18.post_attention_layernorm.bias": "model_00020-of-00072.safetensors",
+        "h.18.post_attention_layernorm.weight": "model_00020-of-00072.safetensors",
+        "h.18.self_attention.dense.bias": "model_00020-of-00072.safetensors",
+        "h.18.self_attention.dense.weight": "model_00020-of-00072.safetensors",
+        "h.18.self_attention.query_key_value.bias": "model_00020-of-00072.safetensors",
+        "h.18.self_attention.query_key_value.weight": "model_00020-of-00072.safetensors",
+        "h.19.input_layernorm.bias": "model_00021-of-00072.safetensors",
+        "h.19.input_layernorm.weight": "model_00021-of-00072.safetensors",
+        "h.19.mlp.dense_4h_to_h.bias": "model_00021-of-00072.safetensors",
+        "h.19.mlp.dense_4h_to_h.weight": "model_00021-of-00072.safetensors",
+        "h.19.mlp.dense_h_to_4h.bias": "model_00021-of-00072.safetensors",
+        "h.19.mlp.dense_h_to_4h.weight": "model_00021-of-00072.safetensors",
+        "h.19.post_attention_layernorm.bias": "model_00021-of-00072.safetensors",
+        "h.19.post_attention_layernorm.weight": "model_00021-of-00072.safetensors",
+        "h.19.self_attention.dense.bias": "model_00021-of-00072.safetensors",
+        "h.19.self_attention.dense.weight": "model_00021-of-00072.safetensors",
+        "h.19.self_attention.query_key_value.bias": "model_00021-of-00072.safetensors",
+        "h.19.self_attention.query_key_value.weight": "model_00021-of-00072.safetensors",
+        "h.2.input_layernorm.bias": "model_00004-of-00072.safetensors",
+        "h.2.input_layernorm.weight": "model_00004-of-00072.safetensors",
+        "h.2.mlp.dense_4h_to_h.bias": "model_00004-of-00072.safetensors",
+        "h.2.mlp.dense_4h_to_h.weight": "model_00004-of-00072.safetensors",
+        "h.2.mlp.dense_h_to_4h.bias": "model_00004-of-00072.safetensors",
+        "h.2.mlp.dense_h_to_4h.weight": "model_00004-of-00072.safetensors",
+        "h.2.post_attention_layernorm.bias": "model_00004-of-00072.safetensors",
+        "h.2.post_attention_layernorm.weight": "model_00004-of-00072.safetensors",
+        "h.2.self_attention.dense.bias": "model_00004-of-00072.safetensors",
+        "h.2.self_attention.dense.weight": "model_00004-of-00072.safetensors",
+        "h.2.self_attention.query_key_value.bias": "model_00004-of-00072.safetensors",
+        "h.2.self_attention.query_key_value.weight": "model_00004-of-00072.safetensors",
+        "h.20.input_layernorm.bias": "model_00022-of-00072.safetensors",
+        "h.20.input_layernorm.weight": "model_00022-of-00072.safetensors",
+        "h.20.mlp.dense_4h_to_h.bias": "model_00022-of-00072.safetensors",
+        "h.20.mlp.dense_4h_to_h.weight": "model_00022-of-00072.safetensors",
+        "h.20.mlp.dense_h_to_4h.bias": "model_00022-of-00072.safetensors",
+        "h.20.mlp.dense_h_to_4h.weight": "model_00022-of-00072.safetensors",
+        "h.20.post_attention_layernorm.bias": "model_00022-of-00072.safetensors",
+        "h.20.post_attention_layernorm.weight": "model_00022-of-00072.safetensors",
+        "h.20.self_attention.dense.bias": "model_00022-of-00072.safetensors",
+        "h.20.self_attention.dense.weight": "model_00022-of-00072.safetensors",
+        "h.20.self_attention.query_key_value.bias": "model_00022-of-00072.safetensors",
+        "h.20.self_attention.query_key_value.weight": "model_00022-of-00072.safetensors",
+        "h.21.input_layernorm.bias": "model_00023-of-00072.safetensors",
+        "h.21.input_layernorm.weight": "model_00023-of-00072.safetensors",
+        "h.21.mlp.dense_4h_to_h.bias": "model_00023-of-00072.safetensors",
+        "h.21.mlp.dense_4h_to_h.weight": "model_00023-of-00072.safetensors",
+        "h.21.mlp.dense_h_to_4h.bias": "model_00023-of-00072.safetensors",
+        "h.21.mlp.dense_h_to_4h.weight": "model_00023-of-00072.safetensors",
+        "h.21.post_attention_layernorm.bias": "model_00023-of-00072.safetensors",
+        "h.21.post_attention_layernorm.weight": "model_00023-of-00072.safetensors",
+        "h.21.self_attention.dense.bias": "model_00023-of-00072.safetensors",
+        "h.21.self_attention.dense.weight": "model_00023-of-00072.safetensors",
+        "h.21.self_attention.query_key_value.bias": "model_00023-of-00072.safetensors",
+        "h.21.self_attention.query_key_value.weight": "model_00023-of-00072.safetensors",
+        "h.22.input_layernorm.bias": "model_00024-of-00072.safetensors",
+        "h.22.input_layernorm.weight": "model_00024-of-00072.safetensors",
+        "h.22.mlp.dense_4h_to_h.bias": "model_00024-of-00072.safetensors",
+        "h.22.mlp.dense_4h_to_h.weight": "model_00024-of-00072.safetensors",
+        "h.22.mlp.dense_h_to_4h.bias": "model_00024-of-00072.safetensors",
+        "h.22.mlp.dense_h_to_4h.weight": "model_00024-of-00072.safetensors",
+        "h.22.post_attention_layernorm.bias": "model_00024-of-00072.safetensors",
+        "h.22.post_attention_layernorm.weight": "model_00024-of-00072.safetensors",
+        "h.22.self_attention.dense.bias": "model_00024-of-00072.safetensors",
+        "h.22.self_attention.dense.weight": "model_00024-of-00072.safetensors",
+        "h.22.self_attention.query_key_value.bias": "model_00024-of-00072.safetensors",
+        "h.22.self_attention.query_key_value.weight": "model_00024-of-00072.safetensors",
+        "h.23.input_layernorm.bias": "model_00025-of-00072.safetensors",
+        "h.23.input_layernorm.weight": "model_00025-of-00072.safetensors",
+        "h.23.mlp.dense_4h_to_h.bias": "model_00025-of-00072.safetensors",
+        "h.23.mlp.dense_4h_to_h.weight": "model_00025-of-00072.safetensors",
+        "h.23.mlp.dense_h_to_4h.bias": "model_00025-of-00072.safetensors",
+        "h.23.mlp.dense_h_to_4h.weight": "model_00025-of-00072.safetensors",
+        "h.23.post_attention_layernorm.bias": "model_00025-of-00072.safetensors",
+        "h.23.post_attention_layernorm.weight": "model_00025-of-00072.safetensors",
+        "h.23.self_attention.dense.bias": "model_00025-of-00072.safetensors",
+        "h.23.self_attention.dense.weight": "model_00025-of-00072.safetensors",
+        "h.23.self_attention.query_key_value.bias": "model_00025-of-00072.safetensors",
+        "h.23.self_attention.query_key_value.weight": "model_00025-of-00072.safetensors",
+        "h.24.input_layernorm.bias": "model_00026-of-00072.safetensors",
+        "h.24.input_layernorm.weight": "model_00026-of-00072.safetensors",
+        "h.24.mlp.dense_4h_to_h.bias": "model_00026-of-00072.safetensors",
+        "h.24.mlp.dense_4h_to_h.weight": "model_00026-of-00072.safetensors",
+        "h.24.mlp.dense_h_to_4h.bias": "model_00026-of-00072.safetensors",
+        "h.24.mlp.dense_h_to_4h.weight": "model_00026-of-00072.safetensors",
+        "h.24.post_attention_layernorm.bias": "model_00026-of-00072.safetensors",
+        "h.24.post_attention_layernorm.weight": "model_00026-of-00072.safetensors",
+        "h.24.self_attention.dense.bias": "model_00026-of-00072.safetensors",
+        "h.24.self_attention.dense.weight": "model_00026-of-00072.safetensors",
+        "h.24.self_attention.query_key_value.bias": "model_00026-of-00072.safetensors",
+        "h.24.self_attention.query_key_value.weight": "model_00026-of-00072.safetensors",
+        "h.25.input_layernorm.bias": "model_00027-of-00072.safetensors",
+        "h.25.input_layernorm.weight": "model_00027-of-00072.safetensors",
+        "h.25.mlp.dense_4h_to_h.bias": "model_00027-of-00072.safetensors",
+        "h.25.mlp.dense_4h_to_h.weight": "model_00027-of-00072.safetensors",
+        "h.25.mlp.dense_h_to_4h.bias": "model_00027-of-00072.safetensors",
+        "h.25.mlp.dense_h_to_4h.weight": "model_00027-of-00072.safetensors",
+        "h.25.post_attention_layernorm.bias": "model_00027-of-00072.safetensors",
+        "h.25.post_attention_layernorm.weight": "model_00027-of-00072.safetensors",
+        "h.25.self_attention.dense.bias": "model_00027-of-00072.safetensors",
+        "h.25.self_attention.dense.weight": "model_00027-of-00072.safetensors",
+        "h.25.self_attention.query_key_value.bias": "model_00027-of-00072.safetensors",
+        "h.25.self_attention.query_key_value.weight": "model_00027-of-00072.safetensors",
+        "h.26.input_layernorm.bias": "model_00028-of-00072.safetensors",
+        "h.26.input_layernorm.weight": "model_00028-of-00072.safetensors",
+        "h.26.mlp.dense_4h_to_h.bias": "model_00028-of-00072.safetensors",
+        "h.26.mlp.dense_4h_to_h.weight": "model_00028-of-00072.safetensors",
+        "h.26.mlp.dense_h_to_4h.bias": "model_00028-of-00072.safetensors",
+        "h.26.mlp.dense_h_to_4h.weight": "model_00028-of-00072.safetensors",
+        "h.26.post_attention_layernorm.bias": "model_00028-of-00072.safetensors",
+        "h.26.post_attention_layernorm.weight": "model_00028-of-00072.safetensors",
+        "h.26.self_attention.dense.bias": "model_00028-of-00072.safetensors",
+        "h.26.self_attention.dense.weight": "model_00028-of-00072.safetensors",
+        "h.26.self_attention.query_key_value.bias": "model_00028-of-00072.safetensors",
+        "h.26.self_attention.query_key_value.weight": "model_00028-of-00072.safetensors",
+        "h.27.input_layernorm.bias": "model_00029-of-00072.safetensors",
+        "h.27.input_layernorm.weight": "model_00029-of-00072.safetensors",
+        "h.27.mlp.dense_4h_to_h.bias": "model_00029-of-00072.safetensors",
+        "h.27.mlp.dense_4h_to_h.weight": "model_00029-of-00072.safetensors",
+        "h.27.mlp.dense_h_to_4h.bias": "model_00029-of-00072.safetensors",
+        "h.27.mlp.dense_h_to_4h.weight": "model_00029-of-00072.safetensors",
+        "h.27.post_attention_layernorm.bias": "model_00029-of-00072.safetensors",
+        "h.27.post_attention_layernorm.weight": "model_00029-of-00072.safetensors",
+        "h.27.self_attention.dense.bias": "model_00029-of-00072.safetensors",
+        "h.27.self_attention.dense.weight": "model_00029-of-00072.safetensors",
+        "h.27.self_attention.query_key_value.bias": "model_00029-of-00072.safetensors",
+        "h.27.self_attention.query_key_value.weight": "model_00029-of-00072.safetensors",
+        "h.28.input_layernorm.bias": "model_00030-of-00072.safetensors",
+        "h.28.input_layernorm.weight": "model_00030-of-00072.safetensors",
+        "h.28.mlp.dense_4h_to_h.bias": "model_00030-of-00072.safetensors",
+        "h.28.mlp.dense_4h_to_h.weight": "model_00030-of-00072.safetensors",
+        "h.28.mlp.dense_h_to_4h.bias": "model_00030-of-00072.safetensors",
+        "h.28.mlp.dense_h_to_4h.weight": "model_00030-of-00072.safetensors",
+        "h.28.post_attention_layernorm.bias": "model_00030-of-00072.safetensors",
+        "h.28.post_attention_layernorm.weight": "model_00030-of-00072.safetensors",
+        "h.28.self_attention.dense.bias": "model_00030-of-00072.safetensors",
+        "h.28.self_attention.dense.weight": "model_00030-of-00072.safetensors",
+        "h.28.self_attention.query_key_value.bias": "model_00030-of-00072.safetensors",
+        "h.28.self_attention.query_key_value.weight": "model_00030-of-00072.safetensors",
+        "h.29.input_layernorm.bias": "model_00031-of-00072.safetensors",
+        "h.29.input_layernorm.weight": "model_00031-of-00072.safetensors",
+        "h.29.mlp.dense_4h_to_h.bias": "model_00031-of-00072.safetensors",
+        "h.29.mlp.dense_4h_to_h.weight": "model_00031-of-00072.safetensors",
+        "h.29.mlp.dense_h_to_4h.bias": "model_00031-of-00072.safetensors",
+        "h.29.mlp.dense_h_to_4h.weight": "model_00031-of-00072.safetensors",
+        "h.29.post_attention_layernorm.bias": "model_00031-of-00072.safetensors",
+        "h.29.post_attention_layernorm.weight": "model_00031-of-00072.safetensors",
+        "h.29.self_attention.dense.bias": "model_00031-of-00072.safetensors",
+        "h.29.self_attention.dense.weight": "model_00031-of-00072.safetensors",
+        "h.29.self_attention.query_key_value.bias": "model_00031-of-00072.safetensors",
+        "h.29.self_attention.query_key_value.weight": "model_00031-of-00072.safetensors",
+        "h.3.input_layernorm.bias": "model_00005-of-00072.safetensors",
+        "h.3.input_layernorm.weight": "model_00005-of-00072.safetensors",
+        "h.3.mlp.dense_4h_to_h.bias": "model_00005-of-00072.safetensors",
+        "h.3.mlp.dense_4h_to_h.weight": "model_00005-of-00072.safetensors",
+        "h.3.mlp.dense_h_to_4h.bias": "model_00005-of-00072.safetensors",
+        "h.3.mlp.dense_h_to_4h.weight": "model_00005-of-00072.safetensors",
+        "h.3.post_attention_layernorm.bias": "model_00005-of-00072.safetensors",
+        "h.3.post_attention_layernorm.weight": "model_00005-of-00072.safetensors",
+        "h.3.self_attention.dense.bias": "model_00005-of-00072.safetensors",
+        "h.3.self_attention.dense.weight": "model_00005-of-00072.safetensors",
+        "h.3.self_attention.query_key_value.bias": "model_00005-of-00072.safetensors",
+        "h.3.self_attention.query_key_value.weight": "model_00005-of-00072.safetensors",
+        "h.30.input_layernorm.bias": "model_00032-of-00072.safetensors",
+        "h.30.input_layernorm.weight": "model_00032-of-00072.safetensors",
+        "h.30.mlp.dense_4h_to_h.bias": "model_00032-of-00072.safetensors",
+        "h.30.mlp.dense_4h_to_h.weight": "model_00032-of-00072.safetensors",
+        "h.30.mlp.dense_h_to_4h.bias": "model_00032-of-00072.safetensors",
+        "h.30.mlp.dense_h_to_4h.weight": "model_00032-of-00072.safetensors",
+        "h.30.post_attention_layernorm.bias": "model_00032-of-00072.safetensors",
+        "h.30.post_attention_layernorm.weight": "model_00032-of-00072.safetensors",
+        "h.30.self_attention.dense.bias": "model_00032-of-00072.safetensors",
+        "h.30.self_attention.dense.weight": "model_00032-of-00072.safetensors",
+        "h.30.self_attention.query_key_value.bias": "model_00032-of-00072.safetensors",
+        "h.30.self_attention.query_key_value.weight": "model_00032-of-00072.safetensors",
+        "h.31.input_layernorm.bias": "model_00033-of-00072.safetensors",
+        "h.31.input_layernorm.weight": "model_00033-of-00072.safetensors",
+        "h.31.mlp.dense_4h_to_h.bias": "model_00033-of-00072.safetensors",
+        "h.31.mlp.dense_4h_to_h.weight": "model_00033-of-00072.safetensors",
+        "h.31.mlp.dense_h_to_4h.bias": "model_00033-of-00072.safetensors",
+        "h.31.mlp.dense_h_to_4h.weight": "model_00033-of-00072.safetensors",
+        "h.31.post_attention_layernorm.bias": "model_00033-of-00072.safetensors",
+        "h.31.post_attention_layernorm.weight": "model_00033-of-00072.safetensors",
+        "h.31.self_attention.dense.bias": "model_00033-of-00072.safetensors",
+        "h.31.self_attention.dense.weight": "model_00033-of-00072.safetensors",
+        "h.31.self_attention.query_key_value.bias": "model_00033-of-00072.safetensors",
+        "h.31.self_attention.query_key_value.weight": "model_00033-of-00072.safetensors",
+        "h.32.input_layernorm.bias": "model_00034-of-00072.safetensors",
+        "h.32.input_layernorm.weight": "model_00034-of-00072.safetensors",
+        "h.32.mlp.dense_4h_to_h.bias": "model_00034-of-00072.safetensors",
+        "h.32.mlp.dense_4h_to_h.weight": "model_00034-of-00072.safetensors",
+        "h.32.mlp.dense_h_to_4h.bias": "model_00034-of-00072.safetensors",
+        "h.32.mlp.dense_h_to_4h.weight": "model_00034-of-00072.safetensors",
+        "h.32.post_attention_layernorm.bias": "model_00034-of-00072.safetensors",
+        "h.32.post_attention_layernorm.weight": "model_00034-of-00072.safetensors",
+        "h.32.self_attention.dense.bias": "model_00034-of-00072.safetensors",
+        "h.32.self_attention.dense.weight": "model_00034-of-00072.safetensors",
+        "h.32.self_attention.query_key_value.bias": "model_00034-of-00072.safetensors",
+        "h.32.self_attention.query_key_value.weight": "model_00034-of-00072.safetensors",
+        "h.33.input_layernorm.bias": "model_00035-of-00072.safetensors",
+        "h.33.input_layernorm.weight": "model_00035-of-00072.safetensors",
+        "h.33.mlp.dense_4h_to_h.bias": "model_00035-of-00072.safetensors",
+        "h.33.mlp.dense_4h_to_h.weight": "model_00035-of-00072.safetensors",
+        "h.33.mlp.dense_h_to_4h.bias": "model_00035-of-00072.safetensors",
+        "h.33.mlp.dense_h_to_4h.weight": "model_00035-of-00072.safetensors",
+        "h.33.post_attention_layernorm.bias": "model_00035-of-00072.safetensors",
+        "h.33.post_attention_layernorm.weight": "model_00035-of-00072.safetensors",
+        "h.33.self_attention.dense.bias": "model_00035-of-00072.safetensors",
+        "h.33.self_attention.dense.weight": "model_00035-of-00072.safetensors",
+        "h.33.self_attention.query_key_value.bias": "model_00035-of-00072.safetensors",
+        "h.33.self_attention.query_key_value.weight": "model_00035-of-00072.safetensors",
+        "h.34.input_layernorm.bias": "model_00036-of-00072.safetensors",
+        "h.34.input_layernorm.weight": "model_00036-of-00072.safetensors",
+        "h.34.mlp.dense_4h_to_h.bias": "model_00036-of-00072.safetensors",
+        "h.34.mlp.dense_4h_to_h.weight": "model_00036-of-00072.safetensors",
+        "h.34.mlp.dense_h_to_4h.bias": "model_00036-of-00072.safetensors",
+        "h.34.mlp.dense_h_to_4h.weight": "model_00036-of-00072.safetensors",
+        "h.34.post_attention_layernorm.bias": "model_00036-of-00072.safetensors",
+        "h.34.post_attention_layernorm.weight": "model_00036-of-00072.safetensors",
+        "h.34.self_attention.dense.bias": "model_00036-of-00072.safetensors",
+        "h.34.self_attention.dense.weight": "model_00036-of-00072.safetensors",
+        "h.34.self_attention.query_key_value.bias": "model_00036-of-00072.safetensors",
+        "h.34.self_attention.query_key_value.weight": "model_00036-of-00072.safetensors",
+        "h.35.input_layernorm.bias": "model_00037-of-00072.safetensors",
+        "h.35.input_layernorm.weight": "model_00037-of-00072.safetensors",
+        "h.35.mlp.dense_4h_to_h.bias": "model_00037-of-00072.safetensors",
+        "h.35.mlp.dense_4h_to_h.weight": "model_00037-of-00072.safetensors",
+        "h.35.mlp.dense_h_to_4h.bias": "model_00037-of-00072.safetensors",
+        "h.35.mlp.dense_h_to_4h.weight": "model_00037-of-00072.safetensors",
+        "h.35.post_attention_layernorm.bias": "model_00037-of-00072.safetensors",
+        "h.35.post_attention_layernorm.weight": "model_00037-of-00072.safetensors",
+        "h.35.self_attention.dense.bias": "model_00037-of-00072.safetensors",
+        "h.35.self_attention.dense.weight": "model_00037-of-00072.safetensors",
+        "h.35.self_attention.query_key_value.bias": "model_00037-of-00072.safetensors",
+        "h.35.self_attention.query_key_value.weight": "model_00037-of-00072.safetensors",
+        "h.36.input_layernorm.bias": "model_00038-of-00072.safetensors",
+        "h.36.input_layernorm.weight": "model_00038-of-00072.safetensors",
+        "h.36.mlp.dense_4h_to_h.bias": "model_00038-of-00072.safetensors",
+        "h.36.mlp.dense_4h_to_h.weight": "model_00038-of-00072.safetensors",
+        "h.36.mlp.dense_h_to_4h.bias": "model_00038-of-00072.safetensors",
+        "h.36.mlp.dense_h_to_4h.weight": "model_00038-of-00072.safetensors",
+        "h.36.post_attention_layernorm.bias": "model_00038-of-00072.safetensors",
+        "h.36.post_attention_layernorm.weight": "model_00038-of-00072.safetensors",
+        "h.36.self_attention.dense.bias": "model_00038-of-00072.safetensors",
+        "h.36.self_attention.dense.weight": "model_00038-of-00072.safetensors",
+        "h.36.self_attention.query_key_value.bias": "model_00038-of-00072.safetensors",
+        "h.36.self_attention.query_key_value.weight": "model_00038-of-00072.safetensors",
+        "h.37.input_layernorm.bias": "model_00039-of-00072.safetensors",
+        "h.37.input_layernorm.weight": "model_00039-of-00072.safetensors",
+        "h.37.mlp.dense_4h_to_h.bias": "model_00039-of-00072.safetensors",
+        "h.37.mlp.dense_4h_to_h.weight": "model_00039-of-00072.safetensors",
+        "h.37.mlp.dense_h_to_4h.bias": "model_00039-of-00072.safetensors",
+        "h.37.mlp.dense_h_to_4h.weight": "model_00039-of-00072.safetensors",
+        "h.37.post_attention_layernorm.bias": "model_00039-of-00072.safetensors",
+        "h.37.post_attention_layernorm.weight": "model_00039-of-00072.safetensors",
+        "h.37.self_attention.dense.bias": "model_00039-of-00072.safetensors",
+        "h.37.self_attention.dense.weight": "model_00039-of-00072.safetensors",
+        "h.37.self_attention.query_key_value.bias": "model_00039-of-00072.safetensors",
+        "h.37.self_attention.query_key_value.weight": "model_00039-of-00072.safetensors",
+        "h.38.input_layernorm.bias": "model_00040-of-00072.safetensors",
+        "h.38.input_layernorm.weight": "model_00040-of-00072.safetensors",
+        "h.38.mlp.dense_4h_to_h.bias": "model_00040-of-00072.safetensors",
+        "h.38.mlp.dense_4h_to_h.weight": "model_00040-of-00072.safetensors",
+        "h.38.mlp.dense_h_to_4h.bias": "model_00040-of-00072.safetensors",
+        "h.38.mlp.dense_h_to_4h.weight": "model_00040-of-00072.safetensors",
+        "h.38.post_attention_layernorm.bias": "model_00040-of-00072.safetensors",
+        "h.38.post_attention_layernorm.weight": "model_00040-of-00072.safetensors",
+        "h.38.self_attention.dense.bias": "model_00040-of-00072.safetensors",
+        "h.38.self_attention.dense.weight": "model_00040-of-00072.safetensors",
+        "h.38.self_attention.query_key_value.bias": "model_00040-of-00072.safetensors",
+        "h.38.self_attention.query_key_value.weight": "model_00040-of-00072.safetensors",
+        "h.39.input_layernorm.bias": "model_00041-of-00072.safetensors",
+        "h.39.input_layernorm.weight": "model_00041-of-00072.safetensors",
+        "h.39.mlp.dense_4h_to_h.bias": "model_00041-of-00072.safetensors",
+        "h.39.mlp.dense_4h_to_h.weight": "model_00041-of-00072.safetensors",
+        "h.39.mlp.dense_h_to_4h.bias": "model_00041-of-00072.safetensors",
+        "h.39.mlp.dense_h_to_4h.weight": "model_00041-of-00072.safetensors",
+        "h.39.post_attention_layernorm.bias": "model_00041-of-00072.safetensors",
+        "h.39.post_attention_layernorm.weight": "model_00041-of-00072.safetensors",
+        "h.39.self_attention.dense.bias": "model_00041-of-00072.safetensors",
+        "h.39.self_attention.dense.weight": "model_00041-of-00072.safetensors",
+        "h.39.self_attention.query_key_value.bias": "model_00041-of-00072.safetensors",
+        "h.39.self_attention.query_key_value.weight": "model_00041-of-00072.safetensors",
+        "h.4.input_layernorm.bias": "model_00006-of-00072.safetensors",
+        "h.4.input_layernorm.weight": "model_00006-of-00072.safetensors",
+        "h.4.mlp.dense_4h_to_h.bias": "model_00006-of-00072.safetensors",
+        "h.4.mlp.dense_4h_to_h.weight": "model_00006-of-00072.safetensors",
+        "h.4.mlp.dense_h_to_4h.bias": "model_00006-of-00072.safetensors",
+        "h.4.mlp.dense_h_to_4h.weight": "model_00006-of-00072.safetensors",
+        "h.4.post_attention_layernorm.bias": "model_00006-of-00072.safetensors",
+        "h.4.post_attention_layernorm.weight": "model_00006-of-00072.safetensors",
+        "h.4.self_attention.dense.bias": "model_00006-of-00072.safetensors",
+        "h.4.self_attention.dense.weight": "model_00006-of-00072.safetensors",
+        "h.4.self_attention.query_key_value.bias": "model_00006-of-00072.safetensors",
+        "h.4.self_attention.query_key_value.weight": "model_00006-of-00072.safetensors",
+        "h.40.input_layernorm.bias": "model_00042-of-00072.safetensors",
+        "h.40.input_layernorm.weight": "model_00042-of-00072.safetensors",
+        "h.40.mlp.dense_4h_to_h.bias": "model_00042-of-00072.safetensors",
+        "h.40.mlp.dense_4h_to_h.weight": "model_00042-of-00072.safetensors",
+        "h.40.mlp.dense_h_to_4h.bias": "model_00042-of-00072.safetensors",
+        "h.40.mlp.dense_h_to_4h.weight": "model_00042-of-00072.safetensors",
+        "h.40.post_attention_layernorm.bias": "model_00042-of-00072.safetensors",
+        "h.40.post_attention_layernorm.weight": "model_00042-of-00072.safetensors",
+        "h.40.self_attention.dense.bias": "model_00042-of-00072.safetensors",
+        "h.40.self_attention.dense.weight": "model_00042-of-00072.safetensors",
+        "h.40.self_attention.query_key_value.bias": "model_00042-of-00072.safetensors",
+        "h.40.self_attention.query_key_value.weight": "model_00042-of-00072.safetensors",
+        "h.41.input_layernorm.bias": "model_00043-of-00072.safetensors",
+        "h.41.input_layernorm.weight": "model_00043-of-00072.safetensors",
+        "h.41.mlp.dense_4h_to_h.bias": "model_00043-of-00072.safetensors",
+        "h.41.mlp.dense_4h_to_h.weight": "model_00043-of-00072.safetensors",
+        "h.41.mlp.dense_h_to_4h.bias": "model_00043-of-00072.safetensors",
+        "h.41.mlp.dense_h_to_4h.weight": "model_00043-of-00072.safetensors",
+        "h.41.post_attention_layernorm.bias": "model_00043-of-00072.safetensors",
+        "h.41.post_attention_layernorm.weight": "model_00043-of-00072.safetensors",
+        "h.41.self_attention.dense.bias": "model_00043-of-00072.safetensors",
+        "h.41.self_attention.dense.weight": "model_00043-of-00072.safetensors",
+        "h.41.self_attention.query_key_value.bias": "model_00043-of-00072.safetensors",
+        "h.41.self_attention.query_key_value.weight": "model_00043-of-00072.safetensors",
+        "h.42.input_layernorm.bias": "model_00044-of-00072.safetensors",
+        "h.42.input_layernorm.weight": "model_00044-of-00072.safetensors",
+        "h.42.mlp.dense_4h_to_h.bias": "model_00044-of-00072.safetensors",
+        "h.42.mlp.dense_4h_to_h.weight": "model_00044-of-00072.safetensors",
+        "h.42.mlp.dense_h_to_4h.bias": "model_00044-of-00072.safetensors",
+        "h.42.mlp.dense_h_to_4h.weight": "model_00044-of-00072.safetensors",
+        "h.42.post_attention_layernorm.bias": "model_00044-of-00072.safetensors",
+        "h.42.post_attention_layernorm.weight": "model_00044-of-00072.safetensors",
+        "h.42.self_attention.dense.bias": "model_00044-of-00072.safetensors",
+        "h.42.self_attention.dense.weight": "model_00044-of-00072.safetensors",
+        "h.42.self_attention.query_key_value.bias": "model_00044-of-00072.safetensors",
+        "h.42.self_attention.query_key_value.weight": "model_00044-of-00072.safetensors",
+        "h.43.input_layernorm.bias": "model_00045-of-00072.safetensors",
+        "h.43.input_layernorm.weight": "model_00045-of-00072.safetensors",
+        "h.43.mlp.dense_4h_to_h.bias": "model_00045-of-00072.safetensors",
+        "h.43.mlp.dense_4h_to_h.weight": "model_00045-of-00072.safetensors",
+        "h.43.mlp.dense_h_to_4h.bias": "model_00045-of-00072.safetensors",
+        "h.43.mlp.dense_h_to_4h.weight": "model_00045-of-00072.safetensors",
+        "h.43.post_attention_layernorm.bias": "model_00045-of-00072.safetensors",
+        "h.43.post_attention_layernorm.weight": "model_00045-of-00072.safetensors",
+        "h.43.self_attention.dense.bias": "model_00045-of-00072.safetensors",
+        "h.43.self_attention.dense.weight": "model_00045-of-00072.safetensors",
+        "h.43.self_attention.query_key_value.bias": "model_00045-of-00072.safetensors",
+        "h.43.self_attention.query_key_value.weight": "model_00045-of-00072.safetensors",
+        "h.44.input_layernorm.bias": "model_00046-of-00072.safetensors",
+        "h.44.input_layernorm.weight": "model_00046-of-00072.safetensors",
+        "h.44.mlp.dense_4h_to_h.bias": "model_00046-of-00072.safetensors",
+        "h.44.mlp.dense_4h_to_h.weight": "model_00046-of-00072.safetensors",
+        "h.44.mlp.dense_h_to_4h.bias": "model_00046-of-00072.safetensors",
+        "h.44.mlp.dense_h_to_4h.weight": "model_00046-of-00072.safetensors",
+        "h.44.post_attention_layernorm.bias": "model_00046-of-00072.safetensors",
+        "h.44.post_attention_layernorm.weight": "model_00046-of-00072.safetensors",
+        "h.44.self_attention.dense.bias": "model_00046-of-00072.safetensors",
+        "h.44.self_attention.dense.weight": "model_00046-of-00072.safetensors",
+        "h.44.self_attention.query_key_value.bias": "model_00046-of-00072.safetensors",
+        "h.44.self_attention.query_key_value.weight": "model_00046-of-00072.safetensors",
+        "h.45.input_layernorm.bias": "model_00047-of-00072.safetensors",
+        "h.45.input_layernorm.weight": "model_00047-of-00072.safetensors",
+        "h.45.mlp.dense_4h_to_h.bias": "model_00047-of-00072.safetensors",
+        "h.45.mlp.dense_4h_to_h.weight": "model_00047-of-00072.safetensors",
+        "h.45.mlp.dense_h_to_4h.bias": "model_00047-of-00072.safetensors",
+        "h.45.mlp.dense_h_to_4h.weight": "model_00047-of-00072.safetensors",
+        "h.45.post_attention_layernorm.bias": "model_00047-of-00072.safetensors",
+        "h.45.post_attention_layernorm.weight": "model_00047-of-00072.safetensors",
+        "h.45.self_attention.dense.bias": "model_00047-of-00072.safetensors",
+        "h.45.self_attention.dense.weight": "model_00047-of-00072.safetensors",
+        "h.45.self_attention.query_key_value.bias": "model_00047-of-00072.safetensors",
+        "h.45.self_attention.query_key_value.weight": "model_00047-of-00072.safetensors",
+        "h.46.input_layernorm.bias": "model_00048-of-00072.safetensors",
+        "h.46.input_layernorm.weight": "model_00048-of-00072.safetensors",
+        "h.46.mlp.dense_4h_to_h.bias": "model_00048-of-00072.safetensors",
+        "h.46.mlp.dense_4h_to_h.weight": "model_00048-of-00072.safetensors",
+        "h.46.mlp.dense_h_to_4h.bias": "model_00048-of-00072.safetensors",
+        "h.46.mlp.dense_h_to_4h.weight": "model_00048-of-00072.safetensors",
+        "h.46.post_attention_layernorm.bias": "model_00048-of-00072.safetensors",
+        "h.46.post_attention_layernorm.weight": "model_00048-of-00072.safetensors",
+        "h.46.self_attention.dense.bias": "model_00048-of-00072.safetensors",
+        "h.46.self_attention.dense.weight": "model_00048-of-00072.safetensors",
+        "h.46.self_attention.query_key_value.bias": "model_00048-of-00072.safetensors",
+        "h.46.self_attention.query_key_value.weight": "model_00048-of-00072.safetensors",
+        "h.47.input_layernorm.bias": "model_00049-of-00072.safetensors",
+        "h.47.input_layernorm.weight": "model_00049-of-00072.safetensors",
+        "h.47.mlp.dense_4h_to_h.bias": "model_00049-of-00072.safetensors",
+        "h.47.mlp.dense_4h_to_h.weight": "model_00049-of-00072.safetensors",
+        "h.47.mlp.dense_h_to_4h.bias": "model_00049-of-00072.safetensors",
+        "h.47.mlp.dense_h_to_4h.weight": "model_00049-of-00072.safetensors",
+        "h.47.post_attention_layernorm.bias": "model_00049-of-00072.safetensors",
+        "h.47.post_attention_layernorm.weight": "model_00049-of-00072.safetensors",
+        "h.47.self_attention.dense.bias": "model_00049-of-00072.safetensors",
+        "h.47.self_attention.dense.weight": "model_00049-of-00072.safetensors",
+        "h.47.self_attention.query_key_value.bias": "model_00049-of-00072.safetensors",
+        "h.47.self_attention.query_key_value.weight": "model_00049-of-00072.safetensors",
+        "h.48.input_layernorm.bias": "model_00050-of-00072.safetensors",
+        "h.48.input_layernorm.weight": "model_00050-of-00072.safetensors",
+        "h.48.mlp.dense_4h_to_h.bias": "model_00050-of-00072.safetensors",
+        "h.48.mlp.dense_4h_to_h.weight": "model_00050-of-00072.safetensors",
+        "h.48.mlp.dense_h_to_4h.bias": "model_00050-of-00072.safetensors",
+        "h.48.mlp.dense_h_to_4h.weight": "model_00050-of-00072.safetensors",
+        "h.48.post_attention_layernorm.bias": "model_00050-of-00072.safetensors",
+        "h.48.post_attention_layernorm.weight": "model_00050-of-00072.safetensors",
+        "h.48.self_attention.dense.bias": "model_00050-of-00072.safetensors",
+        "h.48.self_attention.dense.weight": "model_00050-of-00072.safetensors",
+        "h.48.self_attention.query_key_value.bias": "model_00050-of-00072.safetensors",
+        "h.48.self_attention.query_key_value.weight": "model_00050-of-00072.safetensors",
+        "h.49.input_layernorm.bias": "model_00051-of-00072.safetensors",
+        "h.49.input_layernorm.weight": "model_00051-of-00072.safetensors",
+        "h.49.mlp.dense_4h_to_h.bias": "model_00051-of-00072.safetensors",
+        "h.49.mlp.dense_4h_to_h.weight": "model_00051-of-00072.safetensors",
+        "h.49.mlp.dense_h_to_4h.bias": "model_00051-of-00072.safetensors",
+        "h.49.mlp.dense_h_to_4h.weight": "model_00051-of-00072.safetensors",
+        "h.49.post_attention_layernorm.bias": "model_00051-of-00072.safetensors",
+        "h.49.post_attention_layernorm.weight": "model_00051-of-00072.safetensors",
+        "h.49.self_attention.dense.bias": "model_00051-of-00072.safetensors",
+        "h.49.self_attention.dense.weight": "model_00051-of-00072.safetensors",
+        "h.49.self_attention.query_key_value.bias": "model_00051-of-00072.safetensors",
+        "h.49.self_attention.query_key_value.weight": "model_00051-of-00072.safetensors",
+        "h.5.input_layernorm.bias": "model_00007-of-00072.safetensors",
+        "h.5.input_layernorm.weight": "model_00007-of-00072.safetensors",
+        "h.5.mlp.dense_4h_to_h.bias": "model_00007-of-00072.safetensors",
+        "h.5.mlp.dense_4h_to_h.weight": "model_00007-of-00072.safetensors",
+        "h.5.mlp.dense_h_to_4h.bias": "model_00007-of-00072.safetensors",
+        "h.5.mlp.dense_h_to_4h.weight": "model_00007-of-00072.safetensors",
+        "h.5.post_attention_layernorm.bias": "model_00007-of-00072.safetensors",
+        "h.5.post_attention_layernorm.weight": "model_00007-of-00072.safetensors",
+        "h.5.self_attention.dense.bias": "model_00007-of-00072.safetensors",
+        "h.5.self_attention.dense.weight": "model_00007-of-00072.safetensors",
+        "h.5.self_attention.query_key_value.bias": "model_00007-of-00072.safetensors",
+        "h.5.self_attention.query_key_value.weight": "model_00007-of-00072.safetensors",
+        "h.50.input_layernorm.bias": "model_00052-of-00072.safetensors",
+        "h.50.input_layernorm.weight": "model_00052-of-00072.safetensors",
+        "h.50.mlp.dense_4h_to_h.bias": "model_00052-of-00072.safetensors",
+        "h.50.mlp.dense_4h_to_h.weight": "model_00052-of-00072.safetensors",
+        "h.50.mlp.dense_h_to_4h.bias": "model_00052-of-00072.safetensors",
+        "h.50.mlp.dense_h_to_4h.weight": "model_00052-of-00072.safetensors",
+        "h.50.post_attention_layernorm.bias": "model_00052-of-00072.safetensors",
+        "h.50.post_attention_layernorm.weight": "model_00052-of-00072.safetensors",
+        "h.50.self_attention.dense.bias": "model_00052-of-00072.safetensors",
+        "h.50.self_attention.dense.weight": "model_00052-of-00072.safetensors",
+        "h.50.self_attention.query_key_value.bias": "model_00052-of-00072.safetensors",
+        "h.50.self_attention.query_key_value.weight": "model_00052-of-00072.safetensors",
+        "h.51.input_layernorm.bias": "model_00053-of-00072.safetensors",
+        "h.51.input_layernorm.weight": "model_00053-of-00072.safetensors",
+        "h.51.mlp.dense_4h_to_h.bias": "model_00053-of-00072.safetensors",
+        "h.51.mlp.dense_4h_to_h.weight": "model_00053-of-00072.safetensors",
+        "h.51.mlp.dense_h_to_4h.bias": "model_00053-of-00072.safetensors",
+        "h.51.mlp.dense_h_to_4h.weight": "model_00053-of-00072.safetensors",
+        "h.51.post_attention_layernorm.bias": "model_00053-of-00072.safetensors",
+        "h.51.post_attention_layernorm.weight": "model_00053-of-00072.safetensors",
+        "h.51.self_attention.dense.bias": "model_00053-of-00072.safetensors",
+        "h.51.self_attention.dense.weight": "model_00053-of-00072.safetensors",
+        "h.51.self_attention.query_key_value.bias": "model_00053-of-00072.safetensors",
+        "h.51.self_attention.query_key_value.weight": "model_00053-of-00072.safetensors",
+        "h.52.input_layernorm.bias": "model_00054-of-00072.safetensors",
+        "h.52.input_layernorm.weight": "model_00054-of-00072.safetensors",
+        "h.52.mlp.dense_4h_to_h.bias": "model_00054-of-00072.safetensors",
+        "h.52.mlp.dense_4h_to_h.weight": "model_00054-of-00072.safetensors",
+        "h.52.mlp.dense_h_to_4h.bias": "model_00054-of-00072.safetensors",
+        "h.52.mlp.dense_h_to_4h.weight": "model_00054-of-00072.safetensors",
+        "h.52.post_attention_layernorm.bias": "model_00054-of-00072.safetensors",
+        "h.52.post_attention_layernorm.weight": "model_00054-of-00072.safetensors",
+        "h.52.self_attention.dense.bias": "model_00054-of-00072.safetensors",
+        "h.52.self_attention.dense.weight": "model_00054-of-00072.safetensors",
+        "h.52.self_attention.query_key_value.bias": "model_00054-of-00072.safetensors",
+        "h.52.self_attention.query_key_value.weight": "model_00054-of-00072.safetensors",
+        "h.53.input_layernorm.bias": "model_00055-of-00072.safetensors",
+        "h.53.input_layernorm.weight": "model_00055-of-00072.safetensors",
+        "h.53.mlp.dense_4h_to_h.bias": "model_00055-of-00072.safetensors",
+        "h.53.mlp.dense_4h_to_h.weight": "model_00055-of-00072.safetensors",
+        "h.53.mlp.dense_h_to_4h.bias": "model_00055-of-00072.safetensors",
+        "h.53.mlp.dense_h_to_4h.weight": "model_00055-of-00072.safetensors",
+        "h.53.post_attention_layernorm.bias": "model_00055-of-00072.safetensors",
+        "h.53.post_attention_layernorm.weight": "model_00055-of-00072.safetensors",
+        "h.53.self_attention.dense.bias": "model_00055-of-00072.safetensors",
+        "h.53.self_attention.dense.weight": "model_00055-of-00072.safetensors",
+        "h.53.self_attention.query_key_value.bias": "model_00055-of-00072.safetensors",
+        "h.53.self_attention.query_key_value.weight": "model_00055-of-00072.safetensors",
+        "h.54.input_layernorm.bias": "model_00056-of-00072.safetensors",
+        "h.54.input_layernorm.weight": "model_00056-of-00072.safetensors",
+        "h.54.mlp.dense_4h_to_h.bias": "model_00056-of-00072.safetensors",
+        "h.54.mlp.dense_4h_to_h.weight": "model_00056-of-00072.safetensors",
+        "h.54.mlp.dense_h_to_4h.bias": "model_00056-of-00072.safetensors",
+        "h.54.mlp.dense_h_to_4h.weight": "model_00056-of-00072.safetensors",
+        "h.54.post_attention_layernorm.bias": "model_00056-of-00072.safetensors",
+        "h.54.post_attention_layernorm.weight": "model_00056-of-00072.safetensors",
+        "h.54.self_attention.dense.bias": "model_00056-of-00072.safetensors",
+        "h.54.self_attention.dense.weight": "model_00056-of-00072.safetensors",
+        "h.54.self_attention.query_key_value.bias": "model_00056-of-00072.safetensors",
+        "h.54.self_attention.query_key_value.weight": "model_00056-of-00072.safetensors",
+        "h.55.input_layernorm.bias": "model_00057-of-00072.safetensors",
+        "h.55.input_layernorm.weight": "model_00057-of-00072.safetensors",
+        "h.55.mlp.dense_4h_to_h.bias": "model_00057-of-00072.safetensors",
+        "h.55.mlp.dense_4h_to_h.weight": "model_00057-of-00072.safetensors",
+        "h.55.mlp.dense_h_to_4h.bias": "model_00057-of-00072.safetensors",
+        "h.55.mlp.dense_h_to_4h.weight": "model_00057-of-00072.safetensors",
+        "h.55.post_attention_layernorm.bias": "model_00057-of-00072.safetensors",
+        "h.55.post_attention_layernorm.weight": "model_00057-of-00072.safetensors",
+        "h.55.self_attention.dense.bias": "model_00057-of-00072.safetensors",
+        "h.55.self_attention.dense.weight": "model_00057-of-00072.safetensors",
+        "h.55.self_attention.query_key_value.bias": "model_00057-of-00072.safetensors",
+        "h.55.self_attention.query_key_value.weight": "model_00057-of-00072.safetensors",
+        "h.56.input_layernorm.bias": "model_00058-of-00072.safetensors",
+        "h.56.input_layernorm.weight": "model_00058-of-00072.safetensors",
+        "h.56.mlp.dense_4h_to_h.bias": "model_00058-of-00072.safetensors",
+        "h.56.mlp.dense_4h_to_h.weight": "model_00058-of-00072.safetensors",
+        "h.56.mlp.dense_h_to_4h.bias": "model_00058-of-00072.safetensors",
+        "h.56.mlp.dense_h_to_4h.weight": "model_00058-of-00072.safetensors",
+        "h.56.post_attention_layernorm.bias": "model_00058-of-00072.safetensors",
+        "h.56.post_attention_layernorm.weight": "model_00058-of-00072.safetensors",
+        "h.56.self_attention.dense.bias": "model_00058-of-00072.safetensors",
+        "h.56.self_attention.dense.weight": "model_00058-of-00072.safetensors",
+        "h.56.self_attention.query_key_value.bias": "model_00058-of-00072.safetensors",
+        "h.56.self_attention.query_key_value.weight": "model_00058-of-00072.safetensors",
+        "h.57.input_layernorm.bias": "model_00059-of-00072.safetensors",
+        "h.57.input_layernorm.weight": "model_00059-of-00072.safetensors",
+        "h.57.mlp.dense_4h_to_h.bias": "model_00059-of-00072.safetensors",
+        "h.57.mlp.dense_4h_to_h.weight": "model_00059-of-00072.safetensors",
+        "h.57.mlp.dense_h_to_4h.bias": "model_00059-of-00072.safetensors",
+        "h.57.mlp.dense_h_to_4h.weight": "model_00059-of-00072.safetensors",
+        "h.57.post_attention_layernorm.bias": "model_00059-of-00072.safetensors",
+        "h.57.post_attention_layernorm.weight": "model_00059-of-00072.safetensors",
+        "h.57.self_attention.dense.bias": "model_00059-of-00072.safetensors",
+        "h.57.self_attention.dense.weight": "model_00059-of-00072.safetensors",
+        "h.57.self_attention.query_key_value.bias": "model_00059-of-00072.safetensors",
+        "h.57.self_attention.query_key_value.weight": "model_00059-of-00072.safetensors",
+        "h.58.input_layernorm.bias": "model_00060-of-00072.safetensors",
+        "h.58.input_layernorm.weight": "model_00060-of-00072.safetensors",
+        "h.58.mlp.dense_4h_to_h.bias": "model_00060-of-00072.safetensors",
+        "h.58.mlp.dense_4h_to_h.weight": "model_00060-of-00072.safetensors",
+        "h.58.mlp.dense_h_to_4h.bias": "model_00060-of-00072.safetensors",
+        "h.58.mlp.dense_h_to_4h.weight": "model_00060-of-00072.safetensors",
+        "h.58.post_attention_layernorm.bias": "model_00060-of-00072.safetensors",
+        "h.58.post_attention_layernorm.weight": "model_00060-of-00072.safetensors",
+        "h.58.self_attention.dense.bias": "model_00060-of-00072.safetensors",
+        "h.58.self_attention.dense.weight": "model_00060-of-00072.safetensors",
+        "h.58.self_attention.query_key_value.bias": "model_00060-of-00072.safetensors",
+        "h.58.self_attention.query_key_value.weight": "model_00060-of-00072.safetensors",
+        "h.59.input_layernorm.bias": "model_00061-of-00072.safetensors",
+        "h.59.input_layernorm.weight": "model_00061-of-00072.safetensors",
+        "h.59.mlp.dense_4h_to_h.bias": "model_00061-of-00072.safetensors",
+        "h.59.mlp.dense_4h_to_h.weight": "model_00061-of-00072.safetensors",
+        "h.59.mlp.dense_h_to_4h.bias": "model_00061-of-00072.safetensors",
+        "h.59.mlp.dense_h_to_4h.weight": "model_00061-of-00072.safetensors",
+        "h.59.post_attention_layernorm.bias": "model_00061-of-00072.safetensors",
+        "h.59.post_attention_layernorm.weight": "model_00061-of-00072.safetensors",
+        "h.59.self_attention.dense.bias": "model_00061-of-00072.safetensors",
+        "h.59.self_attention.dense.weight": "model_00061-of-00072.safetensors",
+        "h.59.self_attention.query_key_value.bias": "model_00061-of-00072.safetensors",
+        "h.59.self_attention.query_key_value.weight": "model_00061-of-00072.safetensors",
+        "h.6.input_layernorm.bias": "model_00008-of-00072.safetensors",
+        "h.6.input_layernorm.weight": "model_00008-of-00072.safetensors",
+        "h.6.mlp.dense_4h_to_h.bias": "model_00008-of-00072.safetensors",
+        "h.6.mlp.dense_4h_to_h.weight": "model_00008-of-00072.safetensors",
+        "h.6.mlp.dense_h_to_4h.bias": "model_00008-of-00072.safetensors",
+        "h.6.mlp.dense_h_to_4h.weight": "model_00008-of-00072.safetensors",
+        "h.6.post_attention_layernorm.bias": "model_00008-of-00072.safetensors",
+        "h.6.post_attention_layernorm.weight": "model_00008-of-00072.safetensors",
+        "h.6.self_attention.dense.bias": "model_00008-of-00072.safetensors",
+        "h.6.self_attention.dense.weight": "model_00008-of-00072.safetensors",
+        "h.6.self_attention.query_key_value.bias": "model_00008-of-00072.safetensors",
+        "h.6.self_attention.query_key_value.weight": "model_00008-of-00072.safetensors",
+        "h.60.input_layernorm.bias": "model_00062-of-00072.safetensors",
+        "h.60.input_layernorm.weight": "model_00062-of-00072.safetensors",
+        "h.60.mlp.dense_4h_to_h.bias": "model_00062-of-00072.safetensors",
+        "h.60.mlp.dense_4h_to_h.weight": "model_00062-of-00072.safetensors",
+        "h.60.mlp.dense_h_to_4h.bias": "model_00062-of-00072.safetensors",
+        "h.60.mlp.dense_h_to_4h.weight": "model_00062-of-00072.safetensors",
+        "h.60.post_attention_layernorm.bias": "model_00062-of-00072.safetensors",
+        "h.60.post_attention_layernorm.weight": "model_00062-of-00072.safetensors",
+        "h.60.self_attention.dense.bias": "model_00062-of-00072.safetensors",
+        "h.60.self_attention.dense.weight": "model_00062-of-00072.safetensors",
+        "h.60.self_attention.query_key_value.bias": "model_00062-of-00072.safetensors",
+        "h.60.self_attention.query_key_value.weight": "model_00062-of-00072.safetensors",
+        "h.61.input_layernorm.bias": "model_00063-of-00072.safetensors",
+        "h.61.input_layernorm.weight": "model_00063-of-00072.safetensors",
+        "h.61.mlp.dense_4h_to_h.bias": "model_00063-of-00072.safetensors",
+        "h.61.mlp.dense_4h_to_h.weight": "model_00063-of-00072.safetensors",
+        "h.61.mlp.dense_h_to_4h.bias": "model_00063-of-00072.safetensors",
+        "h.61.mlp.dense_h_to_4h.weight": "model_00063-of-00072.safetensors",
+        "h.61.post_attention_layernorm.bias": "model_00063-of-00072.safetensors",
+        "h.61.post_attention_layernorm.weight": "model_00063-of-00072.safetensors",
+        "h.61.self_attention.dense.bias": "model_00063-of-00072.safetensors",
+        "h.61.self_attention.dense.weight": "model_00063-of-00072.safetensors",
+        "h.61.self_attention.query_key_value.bias": "model_00063-of-00072.safetensors",
+        "h.61.self_attention.query_key_value.weight": "model_00063-of-00072.safetensors",
+        "h.62.input_layernorm.bias": "model_00064-of-00072.safetensors",
+        "h.62.input_layernorm.weight": "model_00064-of-00072.safetensors",
+        "h.62.mlp.dense_4h_to_h.bias": "model_00064-of-00072.safetensors",
+        "h.62.mlp.dense_4h_to_h.weight": "model_00064-of-00072.safetensors",
+        "h.62.mlp.dense_h_to_4h.bias": "model_00064-of-00072.safetensors",
+        "h.62.mlp.dense_h_to_4h.weight": "model_00064-of-00072.safetensors",
+        "h.62.post_attention_layernorm.bias": "model_00064-of-00072.safetensors",
+        "h.62.post_attention_layernorm.weight": "model_00064-of-00072.safetensors",
+        "h.62.self_attention.dense.bias": "model_00064-of-00072.safetensors",
+        "h.62.self_attention.dense.weight": "model_00064-of-00072.safetensors",
+        "h.62.self_attention.query_key_value.bias": "model_00064-of-00072.safetensors",
+        "h.62.self_attention.query_key_value.weight": "model_00064-of-00072.safetensors",
+        "h.63.input_layernorm.bias": "model_00065-of-00072.safetensors",
+        "h.63.input_layernorm.weight": "model_00065-of-00072.safetensors",
+        "h.63.mlp.dense_4h_to_h.bias": "model_00065-of-00072.safetensors",
+        "h.63.mlp.dense_4h_to_h.weight": "model_00065-of-00072.safetensors",
+        "h.63.mlp.dense_h_to_4h.bias": "model_00065-of-00072.safetensors",
+        "h.63.mlp.dense_h_to_4h.weight": "model_00065-of-00072.safetensors",
+        "h.63.post_attention_layernorm.bias": "model_00065-of-00072.safetensors",
+        "h.63.post_attention_layernorm.weight": "model_00065-of-00072.safetensors",
+        "h.63.self_attention.dense.bias": "model_00065-of-00072.safetensors",
+        "h.63.self_attention.dense.weight": "model_00065-of-00072.safetensors",
+        "h.63.self_attention.query_key_value.bias": "model_00065-of-00072.safetensors",
+        "h.63.self_attention.query_key_value.weight": "model_00065-of-00072.safetensors",
+        "h.64.input_layernorm.bias": "model_00066-of-00072.safetensors",
+        "h.64.input_layernorm.weight": "model_00066-of-00072.safetensors",
+        "h.64.mlp.dense_4h_to_h.bias": "model_00066-of-00072.safetensors",
+        "h.64.mlp.dense_4h_to_h.weight": "model_00066-of-00072.safetensors",
+        "h.64.mlp.dense_h_to_4h.bias": "model_00066-of-00072.safetensors",
+        "h.64.mlp.dense_h_to_4h.weight": "model_00066-of-00072.safetensors",
+        "h.64.post_attention_layernorm.bias": "model_00066-of-00072.safetensors",
+        "h.64.post_attention_layernorm.weight": "model_00066-of-00072.safetensors",
+        "h.64.self_attention.dense.bias": "model_00066-of-00072.safetensors",
+        "h.64.self_attention.dense.weight": "model_00066-of-00072.safetensors",
+        "h.64.self_attention.query_key_value.bias": "model_00066-of-00072.safetensors",
+        "h.64.self_attention.query_key_value.weight": "model_00066-of-00072.safetensors",
+        "h.65.input_layernorm.bias": "model_00067-of-00072.safetensors",
+        "h.65.input_layernorm.weight": "model_00067-of-00072.safetensors",
+        "h.65.mlp.dense_4h_to_h.bias": "model_00067-of-00072.safetensors",
+        "h.65.mlp.dense_4h_to_h.weight": "model_00067-of-00072.safetensors",
+        "h.65.mlp.dense_h_to_4h.bias": "model_00067-of-00072.safetensors",
+        "h.65.mlp.dense_h_to_4h.weight": "model_00067-of-00072.safetensors",
+        "h.65.post_attention_layernorm.bias": "model_00067-of-00072.safetensors",
+        "h.65.post_attention_layernorm.weight": "model_00067-of-00072.safetensors",
+        "h.65.self_attention.dense.bias": "model_00067-of-00072.safetensors",
+        "h.65.self_attention.dense.weight": "model_00067-of-00072.safetensors",
+        "h.65.self_attention.query_key_value.bias": "model_00067-of-00072.safetensors",
+        "h.65.self_attention.query_key_value.weight": "model_00067-of-00072.safetensors",
+        "h.66.input_layernorm.bias": "model_00068-of-00072.safetensors",
+        "h.66.input_layernorm.weight": "model_00068-of-00072.safetensors",
+        "h.66.mlp.dense_4h_to_h.bias": "model_00068-of-00072.safetensors",
+        "h.66.mlp.dense_4h_to_h.weight": "model_00068-of-00072.safetensors",
+        "h.66.mlp.dense_h_to_4h.bias": "model_00068-of-00072.safetensors",
+        "h.66.mlp.dense_h_to_4h.weight": "model_00068-of-00072.safetensors",
+        "h.66.post_attention_layernorm.bias": "model_00068-of-00072.safetensors",
+        "h.66.post_attention_layernorm.weight": "model_00068-of-00072.safetensors",
+        "h.66.self_attention.dense.bias": "model_00068-of-00072.safetensors",
+        "h.66.self_attention.dense.weight": "model_00068-of-00072.safetensors",
+        "h.66.self_attention.query_key_value.bias": "model_00068-of-00072.safetensors",
+        "h.66.self_attention.query_key_value.weight": "model_00068-of-00072.safetensors",
+        "h.67.input_layernorm.bias": "model_00069-of-00072.safetensors",
+        "h.67.input_layernorm.weight": "model_00069-of-00072.safetensors",
+        "h.67.mlp.dense_4h_to_h.bias": "model_00069-of-00072.safetensors",
+        "h.67.mlp.dense_4h_to_h.weight": "model_00069-of-00072.safetensors",
+        "h.67.mlp.dense_h_to_4h.bias": "model_00069-of-00072.safetensors",
+        "h.67.mlp.dense_h_to_4h.weight": "model_00069-of-00072.safetensors",
+        "h.67.post_attention_layernorm.bias": "model_00069-of-00072.safetensors",
+        "h.67.post_attention_layernorm.weight": "model_00069-of-00072.safetensors",
+        "h.67.self_attention.dense.bias": "model_00069-of-00072.safetensors",
+        "h.67.self_attention.dense.weight": "model_00069-of-00072.safetensors",
+        "h.67.self_attention.query_key_value.bias": "model_00069-of-00072.safetensors",
+        "h.67.self_attention.query_key_value.weight": "model_00069-of-00072.safetensors",
+        "h.68.input_layernorm.bias": "model_00070-of-00072.safetensors",
+        "h.68.input_layernorm.weight": "model_00070-of-00072.safetensors",
+        "h.68.mlp.dense_4h_to_h.bias": "model_00070-of-00072.safetensors",
+        "h.68.mlp.dense_4h_to_h.weight": "model_00070-of-00072.safetensors",
+        "h.68.mlp.dense_h_to_4h.bias": "model_00070-of-00072.safetensors",
+        "h.68.mlp.dense_h_to_4h.weight": "model_00070-of-00072.safetensors",
+        "h.68.post_attention_layernorm.bias": "model_00070-of-00072.safetensors",
+        "h.68.post_attention_layernorm.weight": "model_00070-of-00072.safetensors",
+        "h.68.self_attention.dense.bias": "model_00070-of-00072.safetensors",
+        "h.68.self_attention.dense.weight": "model_00070-of-00072.safetensors",
+        "h.68.self_attention.query_key_value.bias": "model_00070-of-00072.safetensors",
+        "h.68.self_attention.query_key_value.weight": "model_00070-of-00072.safetensors",
+        "h.69.input_layernorm.bias": "model_00071-of-00072.safetensors",
+        "h.69.input_layernorm.weight": "model_00071-of-00072.safetensors",
+        "h.69.mlp.dense_4h_to_h.bias": "model_00071-of-00072.safetensors",
+        "h.69.mlp.dense_4h_to_h.weight": "model_00071-of-00072.safetensors",
+        "h.69.mlp.dense_h_to_4h.bias": "model_00071-of-00072.safetensors",
+        "h.69.mlp.dense_h_to_4h.weight": "model_00071-of-00072.safetensors",
+        "h.69.post_attention_layernorm.bias": "model_00071-of-00072.safetensors",
+        "h.69.post_attention_layernorm.weight": "model_00071-of-00072.safetensors",
+        "h.69.self_attention.dense.bias": "model_00071-of-00072.safetensors",
+        "h.69.self_attention.dense.weight": "model_00071-of-00072.safetensors",
+        "h.69.self_attention.query_key_value.bias": "model_00071-of-00072.safetensors",
+        "h.69.self_attention.query_key_value.weight": "model_00071-of-00072.safetensors",
+        "h.7.input_layernorm.bias": "model_00009-of-00072.safetensors",
+        "h.7.input_layernorm.weight": "model_00009-of-00072.safetensors",
+        "h.7.mlp.dense_4h_to_h.bias": "model_00009-of-00072.safetensors",
+        "h.7.mlp.dense_4h_to_h.weight": "model_00009-of-00072.safetensors",
+        "h.7.mlp.dense_h_to_4h.bias": "model_00009-of-00072.safetensors",
+        "h.7.mlp.dense_h_to_4h.weight": "model_00009-of-00072.safetensors",
+        "h.7.post_attention_layernorm.bias": "model_00009-of-00072.safetensors",
+        "h.7.post_attention_layernorm.weight": "model_00009-of-00072.safetensors",
+        "h.7.self_attention.dense.bias": "model_00009-of-00072.safetensors",
+        "h.7.self_attention.dense.weight": "model_00009-of-00072.safetensors",
+        "h.7.self_attention.query_key_value.bias": "model_00009-of-00072.safetensors",
+        "h.7.self_attention.query_key_value.weight": "model_00009-of-00072.safetensors",
+        "h.8.input_layernorm.bias": "model_00010-of-00072.safetensors",
+        "h.8.input_layernorm.weight": "model_00010-of-00072.safetensors",
+        "h.8.mlp.dense_4h_to_h.bias": "model_00010-of-00072.safetensors",
+        "h.8.mlp.dense_4h_to_h.weight": "model_00010-of-00072.safetensors",
+        "h.8.mlp.dense_h_to_4h.bias": "model_00010-of-00072.safetensors",
+        "h.8.mlp.dense_h_to_4h.weight": "model_00010-of-00072.safetensors",
+        "h.8.post_attention_layernorm.bias": "model_00010-of-00072.safetensors",
+        "h.8.post_attention_layernorm.weight": "model_00010-of-00072.safetensors",
+        "h.8.self_attention.dense.bias": "model_00010-of-00072.safetensors",
+        "h.8.self_attention.dense.weight": "model_00010-of-00072.safetensors",
+        "h.8.self_attention.query_key_value.bias": "model_00010-of-00072.safetensors",
+        "h.8.self_attention.query_key_value.weight": "model_00010-of-00072.safetensors",
+        "h.9.input_layernorm.bias": "model_00011-of-00072.safetensors",
+        "h.9.input_layernorm.weight": "model_00011-of-00072.safetensors",
+        "h.9.mlp.dense_4h_to_h.bias": "model_00011-of-00072.safetensors",
+        "h.9.mlp.dense_4h_to_h.weight": "model_00011-of-00072.safetensors",
+        "h.9.mlp.dense_h_to_4h.bias": "model_00011-of-00072.safetensors",
+        "h.9.mlp.dense_h_to_4h.weight": "model_00011-of-00072.safetensors",
+        "h.9.post_attention_layernorm.bias": "model_00011-of-00072.safetensors",
+        "h.9.post_attention_layernorm.weight": "model_00011-of-00072.safetensors",
+        "h.9.self_attention.dense.bias": "model_00011-of-00072.safetensors",
+        "h.9.self_attention.dense.weight": "model_00011-of-00072.safetensors",
+        "h.9.self_attention.query_key_value.bias": "model_00011-of-00072.safetensors",
+        "h.9.self_attention.query_key_value.weight": "model_00011-of-00072.safetensors",
+        "ln_f.bias": "model_00072-of-00072.safetensors",
+        "ln_f.weight": "model_00072-of-00072.safetensors",
+        "word_embeddings.weight": "model_00001-of-00072.safetensors",
+        "word_embeddings_layernorm.bias": "model_00001-of-00072.safetensors",
+        "word_embeddings_layernorm.weight": "model_00001-of-00072.safetensors"
+    }
+}

model_00001-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c215a8b126ca284c20842a467e63de867601b3a134f0836de1cc4b092cc7b362
+size 7193289056

model_00002-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8c3eb0503ff1e919653de89a9e7650606c226e1cb9b4b386e26859dfb5e72dc
+size 4932875536

model_00003-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a91f51847208aeb98022414f181027f45ee1261b0d1e0b9e6a473b16c632071
+size 4932875536

model_00004-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f037073f3bba6f29b4f9254a196d769b06507776eaad445faa6d66e409f356c
+size 4932875536

model_00005-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:823ba717b75f5e239c6058ea068b122780b2154cea0479b06deb2ae82a3b60f0
+size 4932875536

model_00006-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0af95b85ed20129688eb9e17c1c2cb064743e8e05472c84bac12d1cc9399da5
+size 4932875536

model_00007-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c6342c91e380af604a8e2933f5ea3a3bd74a1d3f8b18537c040f815f161416a
+size 4932875536

model_00008-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:deaf61c23b5aa5291970d0efc4a7afbf0b6af7c7a969c75c8da6552e616219dc
+size 4932875536

model_00009-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6c7a2eb7b33df1340379eec64c6d90e339570a63ee666b9ed87cb256bfd887f
+size 4932875536

model_00010-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e393d538aeb4fe8556ec814f4d1c3416cd66b9d851527d1f75ddd43f2f260862
+size 4932875536

model_00011-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:497d9ac29d6546706b38a9ccc9f82769f2456d649dc63f0113be60931badb1a7
+size 4932875536

model_00012-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65708d7c85b91ca68789fb74ec38f7b9b93ebc719bb215fff689cc7063ee8132
+size 4932875544

model_00013-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac0badea5ed6535365ebac018a32c594e78384009be1bf3229c08983c7011067
+size 4932875544

model_00014-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cf27a15765181b93cec010601908187606e7aad4418c3cfde1e43b67a570d60
+size 4932875544

model_00015-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06c8f356ffac20a07d765b9900bcdf22a5ae5e3342f8e4c4bc071acd6edd45f0
+size 4932875544

model_00016-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66cc7c6726c70218068ad40007e72272606bf260923e07c567cf6a89b47928d9
+size 4932875544

model_00017-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b450801775f1e084f2aef3f636eff67f65b6fd19c6982b7f6e0cecf6a662516b
+size 4932875544

model_00018-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdafab0ee75749ae24ee84bf5e01b5b6b4eb7522e9ebdde21d6552542efa3783
+size 4932875544

model_00019-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3b6ca05890e23b60a6ea4b33664b47b53721a50dde6f323ab88ca973e2599da
+size 4932875544

model_00020-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78ff0c3f0ae64c7a1cd727b06b53ce5c1e0ead0a4f89c3069dc3e904546cfc5c
+size 4932875544

model_00021-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41a598d1e26bcf2d62140dd93edd12ee4cdee3a1bacdf242b98e8835fa0a0a58
+size 4932875544

model_00022-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c18c155291b1724c3bae0b319723dcf2c598178eb467f13267886a1bd778012f
+size 4932875544

model_00023-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56722fd4d2774577ecd694ca265b03e7775523c32c4d70bab2c101f7ae9481d4
+size 4932875544

model_00024-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7a91a122c675576d4b336dc077498c6df9f11dbb7d14d74d03da20f8c4afa7e
+size 4932875544

model_00025-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6695af5d5209b48a69b594886609c3b5689c20c46119cdf5ac281c799659402a
+size 4932875544

model_00026-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27ff2200395fa274fab338ee1127054c439974e4688f34c1a631d32989ec72b0
+size 4932875544

model_00027-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b6f2ed83d65103e10849e494921a519d61e34f739abd0312de269adaf6572b5
+size 4932875544

model_00028-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92effe56ce26ddc3bdcbd14943a904d9072ffb74839632fdf3d3b06a24933824
+size 4932875544

model_00029-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e40b5db19fed46d09ed19490b9d5a625dd665ba28dfe3470c79cec0efcb94c8e
+size 4932875544

model_00030-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09b5caca03b5625b6bf96c2c238f5f611c3f29e1f98de4fe547f822ab24c9405
+size 4932875544

model_00031-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4695af290bd0f933bed767697671c1d51ef27dd79524cb5ce52c60efc644272d
+size 4932875544

model_00032-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a5e6f14fca82c2ba45588b0fd7d98137a6882daa63f5e0781584fc54e7b9943
+size 4932875544

model_00033-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:941c591b313cc2f4c64f590d1bb007d9dd4be9bec1436a6505afb9fc804b4139
+size 4932875544

model_00034-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9807128536e26dc384b5fdd46d85d49c487ee4ea5f43c24273f2dbb855b0fa1
+size 4932875544

model_00035-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62397bbb6909cd8fbf8a8f1cc1c8e0d162f0e2e8abd5f5000c6d587da74ae393
+size 4932875544

model_00036-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e93bf4a4210418f4a8f45fa2335a5184b9a551c3c2322440a91addebbfad35f1
+size 4932875544

model_00037-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f494537466c568f34cfa0a2d4c62f5389e5985339ddda75ae69472b77ced4369
+size 4932875544

model_00038-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:019658f4e50e4e7a7e99993bd28f90448605c11de47a796183993cdf4252cd7a
+size 4932875544

model_00039-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67210790777ed6a59a78951b083489b640f3a60db1d7d47b643be54daea5e055
+size 4932875544

model_00040-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee352b1a4d63fd8869bb24778af4a4b044a520932207a6c7e5f447d477196c41
+size 4932875544

model_00041-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:158307f8144b007b160a7c668b5eea6a4314a30949e9f14f27e2a8bebd7960cf
+size 4932875544

model_00042-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c04022a8fe197bf404e96cef6b1674569698a72958a8b46fa6f7ba461f8e260
+size 4932875544

model_00043-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ec54e0896026d84e200ef995d28ceb0ecb0c912483f675e8fae13a8a444af61
+size 4932875544

model_00044-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b3fa246075985575c57cf8ebfeb222f039385db16856c115c629e7a6d614a3f
+size 4932875544

model_00045-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f836519691e834a864cda3ab8cf09575d522a31abae455f3ea2d746db0931842
+size 4932875544

model_00046-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daa14c8c18f1b6a486731ab88de6a71cc31691b341eefb65c99a9c3196396f22
+size 4932875544

model_00047-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2404d5e4c9942e9601794ff1657c5cab56efb6891641f80bf690f3523175850f
+size 4932875544

model_00048-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:778bf477ffdf058fa1581fa553d965af51c7c8f9fae792656ec4a659806b7e20
+size 4932875544

model_00049-of-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de537c207b4195c782609282bc310ce9e65bf0457f445d06f8cf0a8b352a4484
+size 4932875544