diff --git a/.gitattributes b/.gitattributes
index e2edc667ad8fc054852644470bb308cf8d6080ae..12d4bbf103a3df6a0f4a7222332cc4e38a919235 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -36,3 +36,74 @@ logs/logs/xp3capmixnewcodelonglossseq/main_log.txt filter=lfs diff=lfs merge=lfs
 logs/logs/xp3mt/main_log.txt filter=lfs diff=lfs merge=lfs -text
 logs/logs/xp3zhmt/main_log.txt filter=lfs diff=lfs merge=lfs -text
 logs/logs/xp3zzlossseq/main_log.txt filter=lfs diff=lfs merge=lfs -text
+model_00042-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00017-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00068-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00010-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00063-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00033-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00023-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00030-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00022-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00024-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00058-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00056-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00048-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00027-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00044-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00060-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00064-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00021-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00050-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00025-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00052-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00001-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00032-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00055-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00066-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00018-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00013-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00038-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00006-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00029-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00020-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00065-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00062-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00039-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00036-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00057-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00041-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00034-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00002-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00046-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00015-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00049-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00005-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00043-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00070-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00045-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00014-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00037-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00069-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00061-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00067-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00035-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00008-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00004-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00011-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00031-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00053-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00051-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00054-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00012-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00016-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00059-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00047-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00003-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00019-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00009-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00026-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00028-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00007-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00040-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00071-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
diff --git a/model.safetensors.index.json b/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..d652e5199c3d6e1e49b812e5702f5d80d1b10cf8
--- /dev/null
+++ b/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"
+    }
+}
\ No newline at end of file
diff --git a/model_00001-of-00072.safetensors b/model_00001-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..038b83f82ce5132b8aefa4610d8e35503ebbd6f2
--- /dev/null
+++ b/model_00001-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc1f2b3dc91b673e292f75ebdfad8e1be446531f9e334f82aeabd940e9e3d986
+size 7193289056
diff --git a/model_00002-of-00072.safetensors b/model_00002-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..78c56f6e032863a56f059a1d1b489c3b6ca00abe
--- /dev/null
+++ b/model_00002-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28d493105602650360efaeaa5a66d93e85455040bb75c11ccda455930ab59409
+size 4932875536
diff --git a/model_00003-of-00072.safetensors b/model_00003-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..07edb69b06d55725fc613e9f4c8de60ac9c8b6ec
--- /dev/null
+++ b/model_00003-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16477e3ab282d36519c28c89e10961bebdb0153835043ee3a383587c0846444d
+size 4932875536
diff --git a/model_00004-of-00072.safetensors b/model_00004-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..9a46a9f10d6fd8407a351528c54a1a34b2cbbb43
--- /dev/null
+++ b/model_00004-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e38f98333acb23f64bb02e55ba4c93779e23c72dc4eeac5017990fe6012502a
+size 4932875536
diff --git a/model_00005-of-00072.safetensors b/model_00005-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..46d6b1cb1182b19f3171aea522c52943a61dc4a1
--- /dev/null
+++ b/model_00005-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb098370666a52c918ea4bc6a28268cfdfc4a82523c06e2d7a6dfa8955449393
+size 4932875536
diff --git a/model_00006-of-00072.safetensors b/model_00006-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..0a821d891c249ff2ca3a59f4abf6914a3c6d6ed2
--- /dev/null
+++ b/model_00006-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4732abc5bf68239c0935fc138b4d1b6086a8ab15a082f6c4f1a1f77d22eab08
+size 4932875536
diff --git a/model_00007-of-00072.safetensors b/model_00007-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..80f4e8957f6ac199df314fdb69debc546e70359f
--- /dev/null
+++ b/model_00007-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66ebe579fcdd57c98ffd1c7492994b89d0efc9a9bd1e2afe12f99bf9599adb5d
+size 4932875536
diff --git a/model_00008-of-00072.safetensors b/model_00008-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..e36a7e467250a750c5bc3b9db357b58e6632d7c3
--- /dev/null
+++ b/model_00008-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d65950119fb0ed3c8e1ff1b4030a829b4ed2db9a66b5b1f164bb710d4706d00
+size 4932875536
diff --git a/model_00009-of-00072.safetensors b/model_00009-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..91bb9ddc93db318bc6dfb09bbcb1a7203e664ebc
--- /dev/null
+++ b/model_00009-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e00f723015b439af3a580473b28012480209617b0d7d7c4db40628862fcbe2c
+size 4932875536
diff --git a/model_00010-of-00072.safetensors b/model_00010-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..2d6527c16fd595ffa1d0146039dc2678382e2d52
--- /dev/null
+++ b/model_00010-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6eabb6b6f3df267e32b4c77cceec37a22f065a84c60e24acfc3bbe0916a0ab5f
+size 4932875536
diff --git a/model_00011-of-00072.safetensors b/model_00011-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ad3240ed002cead9a1790c189f0a916324862ac9
--- /dev/null
+++ b/model_00011-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53333b1c14963545251875f9d1ce6cb86afb4da1f73f5c0d0f8abca48beee540
+size 4932875536
diff --git a/model_00012-of-00072.safetensors b/model_00012-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..00e50ab91d4d0667d5e34a1fe7398d601bf2582d
--- /dev/null
+++ b/model_00012-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e97c713cb3339bfa416f3eeedcca93ee872fa2aff9d7194cfe569162ff6af109
+size 4932875544
diff --git a/model_00013-of-00072.safetensors b/model_00013-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..946d4c897b6aa4bc8671cfe6eea7ec5a4400093a
--- /dev/null
+++ b/model_00013-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:954a9cd60d3fd96555241f1f0b47d80b91c03c57fef000bdb1e9fdd0793fa3d4
+size 4932875544
diff --git a/model_00014-of-00072.safetensors b/model_00014-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..0fb3e6f1d8fd73e184084bfd2df692f1a8ec0e87
--- /dev/null
+++ b/model_00014-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aad67171292233b336329ec9f815e37655bbdf2cd48d5c3c36622a6cc2467e3b
+size 4932875544
diff --git a/model_00015-of-00072.safetensors b/model_00015-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..40133f7ed0356d176550399097652c6ecb3a5a18
--- /dev/null
+++ b/model_00015-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8154d7f8efa30b07d3bbbcabc36470025f60613bb292c9da896dc2f0695c38d
+size 4932875544
diff --git a/model_00016-of-00072.safetensors b/model_00016-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a098a72cf87652c036ed54e48f1679e8159aebb2
--- /dev/null
+++ b/model_00016-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38201f0f16ef4933bf216d089cb0649b3a21c4dc5af9f427d693b7bec2aa23a3
+size 4932875544
diff --git a/model_00017-of-00072.safetensors b/model_00017-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..0e855be012f46688a7523384786632c35c838d78
--- /dev/null
+++ b/model_00017-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61539b7f9b4d3246b2cabc72f1f5fbb8d07d355edc97d3e513293b5327f086ef
+size 4932875544
diff --git a/model_00018-of-00072.safetensors b/model_00018-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a6107d315259e1e958af349c9def18a28e9b5df0
--- /dev/null
+++ b/model_00018-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21b23b6d0f7a477d50e14e5b8b4dc448498921ab4cff7f5c16bf4e50eda62288
+size 4932875544
diff --git a/model_00019-of-00072.safetensors b/model_00019-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..66dc7b5521fadf8b0c17ba728d13f4cae10085da
--- /dev/null
+++ b/model_00019-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:265005f5f93e382de5c24cfbcb5d5edbd8b5f53fb93f7b2eb86cc45b0a1a1061
+size 4932875544
diff --git a/model_00020-of-00072.safetensors b/model_00020-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..beaba860a0fe78503219c9b1ac87ea077d606525
--- /dev/null
+++ b/model_00020-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7530b219e18ebe72146bbd8dfc49a59b9b26905ed2cb8994baa10d973b503ca5
+size 4932875544
diff --git a/model_00021-of-00072.safetensors b/model_00021-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..13af5da996a5c6be99d5899186e6ad5aaf156ff1
--- /dev/null
+++ b/model_00021-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4329d235306ba8ad684b2afe9388c91e1af7dc6edbb409dabde480ffaa578560
+size 4932875544
diff --git a/model_00022-of-00072.safetensors b/model_00022-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..85119a4a56394ef68435144db7a22358efdeff85
--- /dev/null
+++ b/model_00022-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8b919dce1e10ce5fb5e5340e93b3cb023d9e3e379a4079a2182edf9c57ebdc3
+size 4932875544
diff --git a/model_00023-of-00072.safetensors b/model_00023-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..48b5ee0ddf2f9276f62ccf30e4fefe93073ae1ff
--- /dev/null
+++ b/model_00023-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c150cde24d9b5c6e4c6855347fd8eefb3881569d4e83e4e0f160a3ded7f1eee5
+size 4932875544
diff --git a/model_00024-of-00072.safetensors b/model_00024-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..6629b92e94fa267830670c492d5c66a82b63c62c
--- /dev/null
+++ b/model_00024-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e37c294e53e05e10ce2623c5d6d1ce29f23d9bc60e69deb552d53dbf0371592
+size 4932875544
diff --git a/model_00025-of-00072.safetensors b/model_00025-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..0c108ad3fa9a3e5cf4dfed8e4982c41409f46dc1
--- /dev/null
+++ b/model_00025-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f251f81f7286266e45c1c74d44f807f6f0e09b25f51a6fa019f7fe9a21fc96b7
+size 4932875544
diff --git a/model_00026-of-00072.safetensors b/model_00026-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..0e07ae824e9eb681aeb5fb51dc0f3add99f20665
--- /dev/null
+++ b/model_00026-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b821218c876072a64aedbed696f7ff98a7f31a37d2dcfce4ff9434eedb78727a
+size 4932875544
diff --git a/model_00027-of-00072.safetensors b/model_00027-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..5022faea51314a05bff77fcddb4c6a4fe1ad8486
--- /dev/null
+++ b/model_00027-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e92443f8039467b5c3bf56c47fc497af99788ae4a71b3d80c2c096875b8f7833
+size 4932875544
diff --git a/model_00028-of-00072.safetensors b/model_00028-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..f5f00743c89491fb026fb78decc73d73013eff26
--- /dev/null
+++ b/model_00028-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7709b28d71663735ee8800548ef7f84227e878f545fc6cae170c426cb0c4cd0
+size 4932875544
diff --git a/model_00029-of-00072.safetensors b/model_00029-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..5857428f3d13fca9cb283de4f8d31113f1951d5d
--- /dev/null
+++ b/model_00029-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c24fdc4d2936fa6b9e6bc1cb40151176aafbf6c6594bb7da50e905a1616ead79
+size 4932875544
diff --git a/model_00030-of-00072.safetensors b/model_00030-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..c93ea1bc009bbe5aaf9584fb3853dee95b9a43e8
--- /dev/null
+++ b/model_00030-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4000b0cf51a167f6e3c424e3e87bf9bd752ace22029a856f2852287e4c1654f
+size 4932875544
diff --git a/model_00031-of-00072.safetensors b/model_00031-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..471846e7ee5af25b199ccb77c2530fea35ef4958
--- /dev/null
+++ b/model_00031-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8114a77411c2dce66b1a2236ff882b3168f478da8e682cdf18865368a6466d4
+size 4932875544
diff --git a/model_00032-of-00072.safetensors b/model_00032-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..7a25a0bc63dfa565cbc951d83a1fdec80d8b77bb
--- /dev/null
+++ b/model_00032-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce5263ebc417eb3e1f6fd014ad1fc0b234528f39b6c5cb71b3c63c4b19b6e3b9
+size 4932875544
diff --git a/model_00033-of-00072.safetensors b/model_00033-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d98418a6377de566d79f120116c889282517612a
--- /dev/null
+++ b/model_00033-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80db77c65cd107620f7721b05f590b7b9a202e88a1b89d3c62e7315023a43b2e
+size 4932875544
diff --git a/model_00034-of-00072.safetensors b/model_00034-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..1dc94fb7af86f8a43573d81a394b72694c10b063
--- /dev/null
+++ b/model_00034-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d822a86617a9eb6a0e4ac489a3f7dfeabe053b0cfcc09710185a38d79f07318
+size 4932875544
diff --git a/model_00035-of-00072.safetensors b/model_00035-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..b86664edb294e812d0aa4f72231514e8e3ea1991
--- /dev/null
+++ b/model_00035-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb27342552a7a3a051096763aadb641a72fde2cd9c22e57706d0cdb2c1cee088
+size 4932875544
diff --git a/model_00036-of-00072.safetensors b/model_00036-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..3551d39f62eeaae52ea2e398e1f3e6dc7f8facae
--- /dev/null
+++ b/model_00036-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:debc50db5d84e6529c8570ab1a2bdc7b2c11c153dacc0e7345c0244b00b19af2
+size 4932875544
diff --git a/model_00037-of-00072.safetensors b/model_00037-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..82607946c272894b1aae861b0a4941606f603cb1
--- /dev/null
+++ b/model_00037-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:213cd977a1fbcb255c5616789902ee7c0c3326d8eefe94af038610d038eea5b2
+size 4932875544
diff --git a/model_00038-of-00072.safetensors b/model_00038-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..257b5852dac55f2486da54110d0b3e4df85f7177
--- /dev/null
+++ b/model_00038-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f57c7ff7d89a298077c9189ae0ffea31c3a083f064c15bff13e670e4cba74b83
+size 4932875544
diff --git a/model_00039-of-00072.safetensors b/model_00039-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a4bcd46ef531478ab2eb1c391df90ed979dbd589
--- /dev/null
+++ b/model_00039-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81ded7fe284337425812bff2fcc17b44885679231376f6b144ddc8186cefa1ee
+size 4932875544
diff --git a/model_00040-of-00072.safetensors b/model_00040-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..2dd4cad6fb4d4237014398989172fac47dd84c51
--- /dev/null
+++ b/model_00040-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69a29a91410865a14db27b17d648f3cebea4d9458b73214c9f5b6c8115e0e398
+size 4932875544
diff --git a/model_00041-of-00072.safetensors b/model_00041-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..8c6376015e7289b7f9a0bc9dc66c0164daebe6ca
--- /dev/null
+++ b/model_00041-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aacd586ba01ce3332c4ff088ef543721744912f76229b2076856bbd6f03b1842
+size 4932875544
diff --git a/model_00042-of-00072.safetensors b/model_00042-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a0014480b6b1c07f8e6f7507baa9fdaf1da8aa93
--- /dev/null
+++ b/model_00042-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81ca43e475a91edebab1a43ffb18009b19ca97479789613c82209120ced8b0b3
+size 4932875544
diff --git a/model_00043-of-00072.safetensors b/model_00043-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..da3a1d96d01756ad0b41ffa57603fba75e56b3ee
--- /dev/null
+++ b/model_00043-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b15928566d08bb4d4c5336b329309be72099ed3cba9b5558dfecb758bbd5bcc7
+size 4932875544
diff --git a/model_00044-of-00072.safetensors b/model_00044-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..7d612d65ff84a357cbafad407171206c8322ea8b
--- /dev/null
+++ b/model_00044-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:725912d51928bf76df753b9cf159eca1c6d1d51a1b717fe35e9690367aebbc84
+size 4932875544
diff --git a/model_00045-of-00072.safetensors b/model_00045-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..1a1cc207d74f56d94a463deb4c5c91133a88bf43
--- /dev/null
+++ b/model_00045-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67329ef857589fd0628769de130be62becdf343c9f342f100da7bbe630e70ff1
+size 4932875544
diff --git a/model_00046-of-00072.safetensors b/model_00046-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..1d63914d01551f26029aa6e6950f6084bd78417e
--- /dev/null
+++ b/model_00046-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df2da989b10aebfdc67d59a1f2bb4a47abfc1c5632908387968226051213a06f
+size 4932875544
diff --git a/model_00047-of-00072.safetensors b/model_00047-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d4d53b78254b0d9305eafa7b6ea4e16c0ebeab5a
--- /dev/null
+++ b/model_00047-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58ed7bc73ab22b16f5eb48c90cf8a0fc6ef0ced1cd265f3fbc99fcde34f6bb87
+size 4932875544
diff --git a/model_00048-of-00072.safetensors b/model_00048-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..5ca38f7b7031afedb4ce4b970c80044093ee3df8
--- /dev/null
+++ b/model_00048-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa8962a27cffe76b6975b21a35de7bf31d41c60ea1f21272d0ef21129b2022a6
+size 4932875544
diff --git a/model_00049-of-00072.safetensors b/model_00049-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..c5a77490fd5239a29db50770cedec0eb3301389f
--- /dev/null
+++ b/model_00049-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6975811b839219f5bf6414b7fcd770198690af5a19503e957f764437b45c46e6
+size 4932875544
diff --git a/model_00050-of-00072.safetensors b/model_00050-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..c8a9fc85d62861f95f28b11c2f475e28e64b2635
--- /dev/null
+++ b/model_00050-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:def6a84c229c739aa15aa6677dec7722895fcf956c6e5a765f2c9fda3a46fae5
+size 4932875544
diff --git a/model_00051-of-00072.safetensors b/model_00051-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..00f077c3247e37480dad179c52f9ae766478e04b
--- /dev/null
+++ b/model_00051-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe2543167a1249d94cdae9d356e323264a69111dacab88a121e19236c693f0c6
+size 4932875544
diff --git a/model_00052-of-00072.safetensors b/model_00052-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..65c0aa7413a941482b346188bd676bdb5e572b2f
--- /dev/null
+++ b/model_00052-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4be21d7da7af20d260fa46547d98528731f4d115ec5eec58a0e21609b0443478
+size 4932875544
diff --git a/model_00053-of-00072.safetensors b/model_00053-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..e5fd397768a3ce7248f987cec7d426af2b3954d1
--- /dev/null
+++ b/model_00053-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6637ea47c2ba355fd7706eb1a025bba73d00032ddd2639951f4ab2ac2ad9b3f
+size 4932875544
diff --git a/model_00054-of-00072.safetensors b/model_00054-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..7b6aae830d33b163a9222cc52a15a70d4b61bd29
--- /dev/null
+++ b/model_00054-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1f6a26dc18231782c7eb0e1b078e3c35d89220e1e6530f0c5fe876dd1ab9373
+size 4932875544
diff --git a/model_00055-of-00072.safetensors b/model_00055-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..01fe6d8f26be9065ee5c2de1b6f89c4bbc0d06c6
--- /dev/null
+++ b/model_00055-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ee67f20d804338043ab47f6cb50298c07c6efa4a01fd6584c26b235f054dff4
+size 4932875544
diff --git a/model_00056-of-00072.safetensors b/model_00056-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..18353f1e163840011f1a1a1c3a02748a89ec7db2
--- /dev/null
+++ b/model_00056-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:866326f838f645db52b1bf6a95a688ae2800121e8ba76b4d7b81c3672187be32
+size 4932875544
diff --git a/model_00057-of-00072.safetensors b/model_00057-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..fa1ed13bd73b4e3a5f33b936e8e3afab5d35b600
--- /dev/null
+++ b/model_00057-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbb012af312f92d1977f2dda2f374687da94a780c9b2dcc89aedf9cff66f3a2a
+size 4932875544
diff --git a/model_00058-of-00072.safetensors b/model_00058-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..106a7dee3a7c19d8a1601d8b5e8dd3607e7e980f
--- /dev/null
+++ b/model_00058-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30ed44ebca1a3ee2fe08c051c0507788ff95b60e78c12f942c5a9d7580aa3a47
+size 4932875544
diff --git a/model_00059-of-00072.safetensors b/model_00059-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..6c5d144a16a74ce911b59e681d1e3a83d186b559
--- /dev/null
+++ b/model_00059-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49dbd7d2bf243d4ba992672e01b460c3a6c5eeaea7854fb84669a9dbf46e0e14
+size 4932875544
diff --git a/model_00060-of-00072.safetensors b/model_00060-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..cf611f6fc251054fc64405e3ed498681e5a94cbf
--- /dev/null
+++ b/model_00060-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d789b092df781d196d45c6f887d77f5601279c51032c7e7347c75c1f363818d2
+size 4932875544
diff --git a/model_00061-of-00072.safetensors b/model_00061-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..17a8451998b00c64426b941d079ac9bb38e65d6a
--- /dev/null
+++ b/model_00061-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db6afa177379ad3942c4756837f4cd9232f9e9ba111e73f79a18c56f6aa6c5ff
+size 4932875544
diff --git a/model_00062-of-00072.safetensors b/model_00062-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..6f903bc317e9a51b20cc899408be35ff9da968fa
--- /dev/null
+++ b/model_00062-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bed0bad3b33368a0eb045744fa9a058e3d9bad0c730a785bf39e071e6ad8bec
+size 4932875544
diff --git a/model_00063-of-00072.safetensors b/model_00063-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d0f0797664ee22b688ac71a074de6714bbf011f9
--- /dev/null
+++ b/model_00063-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8cd125ab3d01453643ade444dcfe3b6bbc4f90cb1ee9f859676c9c7c056b058
+size 4932875544
diff --git a/model_00064-of-00072.safetensors b/model_00064-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..4a507b90d4b96063a4a4ba699feb925c1617f519
--- /dev/null
+++ b/model_00064-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f653335fb0128932a859adbb53e1803a90beb9d665ff79d138a5b4ea86199785
+size 4932875544
diff --git a/model_00065-of-00072.safetensors b/model_00065-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..50a7debe52a49c2a259ba14ada6d9bed46f85cde
--- /dev/null
+++ b/model_00065-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6eff53a33826f5defd392e3ebbc4f3bc6346180b6204c209554febb58f364f80
+size 4932875544
diff --git a/model_00066-of-00072.safetensors b/model_00066-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..6edbd584b066bf6fb5a9927c7d44fb61ea6d2c25
--- /dev/null
+++ b/model_00066-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7a5d3e47df9fe8489eb737e598ef2bd37ad75fe07d3855742aa6df62061b966
+size 4932875544
diff --git a/model_00067-of-00072.safetensors b/model_00067-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..e76c1c8f9b3b00c74c143935517800389e4b1dc5
--- /dev/null
+++ b/model_00067-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7baec3c0750cf3b97228f24d9d162d264193e833d636f9357edf8edb67af6ec
+size 4932875544
diff --git a/model_00068-of-00072.safetensors b/model_00068-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..eb643587065ab22e8ee358027c5012f30750bd9f
--- /dev/null
+++ b/model_00068-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a57801967e89aaee9a5ded5849b249ace12f3ef5f69721b682948437c133f042
+size 4932875544
diff --git a/model_00069-of-00072.safetensors b/model_00069-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..2c24e4b188f70a111f64cbd2934f355054b6eb14
--- /dev/null
+++ b/model_00069-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84cd9b812972bf914d921da0474b23278554e03ff0c0b49da2d9cd60e187b77b
+size 4932875544
diff --git a/model_00070-of-00072.safetensors b/model_00070-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..00e3969bc47c5b7e19ea84f8f84c82ce9b94381f
--- /dev/null
+++ b/model_00070-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9154ff247b76d059cb24be9ae78aec21477f779a6f99e004727a202a74b40ec9
+size 4932875544
diff --git a/model_00071-of-00072.safetensors b/model_00071-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..4371bcb00f9c85f55cc07dd387280ea7e3befae2
--- /dev/null
+++ b/model_00071-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:543af97a2c7b7e15568f548c88226f7b7b25714b2a199b87a13c5b541a57263a
+size 4932875544
diff --git a/model_00072-of-00072.safetensors b/model_00072-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..8c48fb2faa9a776d7c921c4de6f19e0c9bfad67f
Binary files /dev/null and b/model_00072-of-00072.safetensors differ