diff --git a/.gitattributes b/.gitattributes
index 917503d6d28e0d36fbb50bfee1f315239dd049bc..b310bdeba150340595720836fcb4f14021040eb3 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -34,3 +34,74 @@ tokenizer.json filter=lfs diff=lfs merge=lfs -text
 */tokenizer.json filter=lfs diff=lfs merge=lfs -text
 tr13-176B-ml-t0-logs/logs/p31lossseq/main_log.txt filter=lfs diff=lfs merge=lfs -text
 tr13-176B-ml-t0-logs/logs/xp3capmixnewcodelonglossseq/main_log.txt filter=lfs diff=lfs merge=lfs -text
+model_00041-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00029-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00053-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00064-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00020-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00023-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00047-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00030-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00061-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00009-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00045-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00012-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00050-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00005-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00057-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00070-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00062-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00038-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00048-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00022-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00044-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00065-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00043-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00058-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00069-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00016-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00039-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00014-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00006-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00051-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00004-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00031-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00068-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00034-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00035-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00063-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00066-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00001-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00019-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00040-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00024-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00015-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00056-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00027-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00028-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00008-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00013-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00060-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00042-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00046-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00021-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00052-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00003-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00055-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00002-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00010-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00032-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00011-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00017-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00025-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00007-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00037-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00067-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00059-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00049-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00036-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00071-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00054-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00018-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00026-of-00072.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00033-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..fb7f3ad8e4b79e7ed88f90f0073680c7ed736616
--- /dev/null
+++ b/model_00001-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5813751564350af2aebf0977bbffdb9ca7243911d581ec67bf6cd4b624674c3
+size 7193289056
diff --git a/model_00002-of-00072.safetensors b/model_00002-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..59a82db6aaa11ecdee97506adca6df9b8ee3924f
--- /dev/null
+++ b/model_00002-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0e254f78818d63e3347e2c94c77792cfd95981c64b99ed0f501731e78f7ce4d
+size 4932875536
diff --git a/model_00003-of-00072.safetensors b/model_00003-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ce727a04eeff488ce0f23d2279f636f417e9359d
--- /dev/null
+++ b/model_00003-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:704dff09f5033788b17fe607e07a295c8f09be7c18b0bb512a286a7f8226ec46
+size 4932875536
diff --git a/model_00004-of-00072.safetensors b/model_00004-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..6a71a20df08c302b2a9e5aa9cf58918fdb718de9
--- /dev/null
+++ b/model_00004-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9cb31c07e548226a2e6b3dd99f806bf00a0668ce44d638a080f31fbd0f0227d
+size 4932875536
diff --git a/model_00005-of-00072.safetensors b/model_00005-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..fb8557ce9f4e05b38872d07a4c8908be4b2c6b9c
--- /dev/null
+++ b/model_00005-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:443fa76ae6755ce092a856330ce6bb04bd7b8a7ae7884f4511a78b619e8e3fc6
+size 4932875536
diff --git a/model_00006-of-00072.safetensors b/model_00006-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..6fc1afa81af1e5b3c5e72d194404d18f49636a7a
--- /dev/null
+++ b/model_00006-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:137b594870deb1919378ee09b837912a8e3b83366f69e2da6c58fbe97069f98c
+size 4932875536
diff --git a/model_00007-of-00072.safetensors b/model_00007-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..56fbe7b3a999d204ec5f81f8b06e41579238a40b
--- /dev/null
+++ b/model_00007-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62b5e5e0936f4debb32b6fd4df1a70ca394f7e94373f96324332c74a955d617e
+size 4932875536
diff --git a/model_00008-of-00072.safetensors b/model_00008-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ec86df705ee0049cf7ab56fe99b10de8e7742ed0
--- /dev/null
+++ b/model_00008-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3017bf5eacb52e9fcb74cc0da355f0a5e4573cc05af25813c1dce284b4d9ce9
+size 4932875536
diff --git a/model_00009-of-00072.safetensors b/model_00009-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..731059075ed0c4d2759d1686248d022e395820ad
--- /dev/null
+++ b/model_00009-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4234dc947e5ddcca33d3dab177895121c8ac7fda18317a74147e7880456d8e18
+size 4932875536
diff --git a/model_00010-of-00072.safetensors b/model_00010-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..98712fd12fa9012f045d25906b81d1f728bc9bab
--- /dev/null
+++ b/model_00010-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36f5ad0199f7079aab6ff2fc1a77a62594ac45ea6794ea81a535acfbf27c33b9
+size 4932875536
diff --git a/model_00011-of-00072.safetensors b/model_00011-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ef9ac532d6834dc707988e9aab77b350a4aff16f
--- /dev/null
+++ b/model_00011-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d5282c113c54b77f109d85d47d9e6ac919d80c9927c4ff6e9986768bf25c52e
+size 4932875536
diff --git a/model_00012-of-00072.safetensors b/model_00012-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..928c44bbaefe7e473b5634353e1cdc1fd96a5b69
--- /dev/null
+++ b/model_00012-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7caef75b4b7ea8e0d5634b298acf60d980afa29d429c0ffeb5d8f563c06135a9
+size 4932875544
diff --git a/model_00013-of-00072.safetensors b/model_00013-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d84df14923bb9568d20f44e7852865c9169c37f3
--- /dev/null
+++ b/model_00013-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79f5d4a13164f36d85bad862d6eddbf5b4cd2acdaed5bc007a2f6fef1ed3be1e
+size 4932875544
diff --git a/model_00014-of-00072.safetensors b/model_00014-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..8b78380cd015498e54d585dacf956385c4f1e1e6
--- /dev/null
+++ b/model_00014-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6d9c4297ab55bb5ec718fb179d42bc5912584d2c0ecc71447c15f8fafde181e
+size 4932875544
diff --git a/model_00015-of-00072.safetensors b/model_00015-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..915d3b2d9dd112c29f8a70778920c031af895657
--- /dev/null
+++ b/model_00015-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18f13a321d393657ae51a1ad2ad731ef58c2b84927ed2cd9156cff56618bd806
+size 4932875544
diff --git a/model_00016-of-00072.safetensors b/model_00016-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..479108f02b0e152b7de44caa95640fcf7bbad952
--- /dev/null
+++ b/model_00016-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e8633296be25b33834e5ecc54f54bd3edf886464771e64c10bb026c0cdb1020
+size 4932875544
diff --git a/model_00017-of-00072.safetensors b/model_00017-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..728ae3e30c52c03edf2f9a894f2ef4c69c56b63d
--- /dev/null
+++ b/model_00017-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7abe28255c57bbe165b902ad92a906a93aca685ceafa721c744860396ce338aa
+size 4932875544
diff --git a/model_00018-of-00072.safetensors b/model_00018-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a4b13e3a4ef0e7aa8257479aca3cfdff86b1d36a
--- /dev/null
+++ b/model_00018-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c10f7b0f6674a541819b9bb8ee91fbfd26e5790a2d098357f967bdfa57a07d76
+size 4932875544
diff --git a/model_00019-of-00072.safetensors b/model_00019-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..092297f21eeab0eae4c76b1cff4f9919b3d33694
--- /dev/null
+++ b/model_00019-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fce9bba6503b214f5efc278498698febc5a856a2950bb93fa4045ca47982fd54
+size 4932875544
diff --git a/model_00020-of-00072.safetensors b/model_00020-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..881c7ed04e3f3e6970f25e37637b565d9a411466
--- /dev/null
+++ b/model_00020-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc2efea2b1e50f9ee406c3a3b75cdbf45aca47a9ca1572cdbbd1c3755168be01
+size 4932875544
diff --git a/model_00021-of-00072.safetensors b/model_00021-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..3ba5a2134213895bfbe57dea4b08c10f2fd0c0a3
--- /dev/null
+++ b/model_00021-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0684de4a00af61d3b7058567af619631517b51a57758f152529e9ae437fc5415
+size 4932875544
diff --git a/model_00022-of-00072.safetensors b/model_00022-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..edc4ac9a918d5d70240ed1e243d217cc58be2e24
--- /dev/null
+++ b/model_00022-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d599eb52954fb3ee07ee28fb3dfe29347cfd3b444b4c6b1970358b177108430
+size 4932875544
diff --git a/model_00023-of-00072.safetensors b/model_00023-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..b569835abb7981fd80b5d543c681a8a53c55c501
--- /dev/null
+++ b/model_00023-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8a97ae0355faad917deea693fcbdc41493e9c366017b705faf3de3613d095b5
+size 4932875544
diff --git a/model_00024-of-00072.safetensors b/model_00024-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..052ced654094380010dae5791bd347a490f55888
--- /dev/null
+++ b/model_00024-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99e5ff59282fd582be6853d449344bd52294217e15de24ca7b251ec279a09e6f
+size 4932875544
diff --git a/model_00025-of-00072.safetensors b/model_00025-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a928d6a8024a22d798dd8859531cf1a5b003c5cf
--- /dev/null
+++ b/model_00025-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:664f26856457b0ee78858ccd715bade767aa4fdd536ffebcc97a89fe74a8ed45
+size 4932875544
diff --git a/model_00026-of-00072.safetensors b/model_00026-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..e81c3ad0dd55358badea8fc3ea5fcc6b0d7257a6
--- /dev/null
+++ b/model_00026-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a4a1721d985c3465f3df93e008276c71e0890b8e998342e2144248748bbb726
+size 4932875544
diff --git a/model_00027-of-00072.safetensors b/model_00027-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..67c58c8ed8e254e91630b0bc30436dd88219f373
--- /dev/null
+++ b/model_00027-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1622aa637915bf9a5bdb14b742af77189edc68671a1ee1e7d4a479f71fd5afa
+size 4932875544
diff --git a/model_00028-of-00072.safetensors b/model_00028-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..332b97644f2dcf73f9bdc858d94c3b0806a5dbe2
--- /dev/null
+++ b/model_00028-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb619e92b67e388c81e0101e576ea1c549d7fa1770d0f43651bc0450e0110a60
+size 4932875544
diff --git a/model_00029-of-00072.safetensors b/model_00029-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..3b2c3efebcf160afe178351cfa2eeba478aba8d8
--- /dev/null
+++ b/model_00029-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:202dad5e65cfb9dd7337ace243977d5fafc591b4646abc25e6ccaf53eddc4575
+size 4932875544
diff --git a/model_00030-of-00072.safetensors b/model_00030-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..08767e937fefb7a33403f072685022a7652b5b48
--- /dev/null
+++ b/model_00030-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1520a08f6781a10d5402646cd75b9b3ee0e71a5cf2f54f08b39af8092a40b91e
+size 4932875544
diff --git a/model_00031-of-00072.safetensors b/model_00031-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..771a49171280967d2dbbcaa22a046bd78e75ba6a
--- /dev/null
+++ b/model_00031-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c58375a0ce892955fdbeee51f50146f08caa1d72c220b18d5c53ba1e8db0aece
+size 4932875544
diff --git a/model_00032-of-00072.safetensors b/model_00032-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..04a4e5d273ada6e6a89919e334cdf1eb0a08c358
--- /dev/null
+++ b/model_00032-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6b6d2b6cb216b9454483545a66bbcf03098698fb901d5ea9ff39892d8f0f91a
+size 4932875544
diff --git a/model_00033-of-00072.safetensors b/model_00033-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..070ad7323cb9833d591e95f18e0d15db4076ce4d
--- /dev/null
+++ b/model_00033-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de92b8035d0babf52ef62ab519d88e3c00099571ddcdd92a316569c7c60993c9
+size 4932875544
diff --git a/model_00034-of-00072.safetensors b/model_00034-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..e492c0450853161f0c9f79a9cfbbf18dfc64e062
--- /dev/null
+++ b/model_00034-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcbe9dd8899b5db2418d695d619a364f84371a398a21abf15548672a8a8387f6
+size 4932875544
diff --git a/model_00035-of-00072.safetensors b/model_00035-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..18fc59c131d049afa000644b5cbd27f1664135bb
--- /dev/null
+++ b/model_00035-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f46a4c75f13339361e4f4c50d5cbabc480f0b88c33cf7421253fb917237fff89
+size 4932875544
diff --git a/model_00036-of-00072.safetensors b/model_00036-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d72e90c97a14120bd6b48844008788bce0fb407d
--- /dev/null
+++ b/model_00036-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e409bbfda3b800d5edc017e5c7e52cec520f27cab36f47657acb588092f9a02e
+size 4932875544
diff --git a/model_00037-of-00072.safetensors b/model_00037-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..3e0f15763e9a8f413f562efac121f13111e89113
--- /dev/null
+++ b/model_00037-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75cd030f7ca560d1b2b76063230ecc05c7df7f9116da6b5a1be1936f7b50838c
+size 4932875544
diff --git a/model_00038-of-00072.safetensors b/model_00038-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..0c6f7bf60e766f27e6ca8f65923bdb6a8b06e54a
--- /dev/null
+++ b/model_00038-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdefadd16343634295bb1a780eb2889e2fe4d1b6d6af003c6fb19cedb97173cc
+size 4932875544
diff --git a/model_00039-of-00072.safetensors b/model_00039-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..8c86b6574d2353deeda58b4279563dc7888c88ec
--- /dev/null
+++ b/model_00039-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc74eacacc8da8f441720301da7fd351ed14f09e8244bb79376c7a175f69b332
+size 4932875544
diff --git a/model_00040-of-00072.safetensors b/model_00040-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..b261e66135cf1fd1f920dc2246987f80aa2c217e
--- /dev/null
+++ b/model_00040-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dca2432752ea988831a79339d7d3efc4ac308397d1f24f500a2f8279b84b06f6
+size 4932875544
diff --git a/model_00041-of-00072.safetensors b/model_00041-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..856ca6a4f908693cc13e14db1c8b4f369fe05360
--- /dev/null
+++ b/model_00041-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13a0e4948b349e4910f85b52c674a1a64b4dbf47e2cf8ca3528fd4c257abce1d
+size 4932875544
diff --git a/model_00042-of-00072.safetensors b/model_00042-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..c6dc9bae427c477c1a1af655aef2bae4a21d32e4
--- /dev/null
+++ b/model_00042-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e2f86957659defafa239e49fcb08e72e2edd90397195fbbc58b880c3ed83125
+size 4932875544
diff --git a/model_00043-of-00072.safetensors b/model_00043-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..e49a86e4148e27e0f3b8c81e2462af944bf85e28
--- /dev/null
+++ b/model_00043-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c7a9f02f164441ecf727213da6ddc398b7afaaa540f25106e1bb5952a97d9ca
+size 4932875544
diff --git a/model_00044-of-00072.safetensors b/model_00044-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..5907e04b54cca0f43f5b2292b899e9c85c258724
--- /dev/null
+++ b/model_00044-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44921340b0fd4caf85927dd70fd0e561fb172bb6dbc927f9b1f369cddf24c8c1
+size 4932875544
diff --git a/model_00045-of-00072.safetensors b/model_00045-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..5a16d9517044843a0c933aa9ebca3a647d9ce1e1
--- /dev/null
+++ b/model_00045-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9b88662e0def3368c2c32ff0fd9f2f257106a78b4e8af0deac40011e604ed71
+size 4932875544
diff --git a/model_00046-of-00072.safetensors b/model_00046-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..27392967279a1cfd4a81611a09237f8ae6eddf13
--- /dev/null
+++ b/model_00046-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:298960832a755e4868ac2134674a686aaf8c29322861f63779fdb964e29eede6
+size 4932875544
diff --git a/model_00047-of-00072.safetensors b/model_00047-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d0c7346299d6df63f19cb71ee72497a580cf3dbb
--- /dev/null
+++ b/model_00047-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aaa8e5665c53f170dc97166ec3e585290f4434f46834c229d6925349409c0a75
+size 4932875544
diff --git a/model_00048-of-00072.safetensors b/model_00048-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d91cca35293e5831b8808ad117f51e097ca0a9c3
--- /dev/null
+++ b/model_00048-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e507fb065484e3b51fd1bbf83c91c1f2096082d0266989803f2c3233f72e30db
+size 4932875544
diff --git a/model_00049-of-00072.safetensors b/model_00049-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..3f4aeaa48fd5401c095a4e79ce6ae064af331d08
--- /dev/null
+++ b/model_00049-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc20ae2f50e1073f96c738ad7dae15a55c52a3a93927629b1365913c9443f849
+size 4932875544
diff --git a/model_00050-of-00072.safetensors b/model_00050-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..b0c72051dede185b9366ae3f75203f8000820dc3
--- /dev/null
+++ b/model_00050-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c62a84bcca716fe1c98d93d0bfe4d16adaf9ce1accaf366134d9cf545b2d8d3b
+size 4932875544
diff --git a/model_00051-of-00072.safetensors b/model_00051-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..7fd7403d739e9e3cb9957daca71a89aeeb45bdfa
--- /dev/null
+++ b/model_00051-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85482c601314eefcf2eb6739a9cc4919e016d8536af1e646ba1d00ceaec92687
+size 4932875544
diff --git a/model_00052-of-00072.safetensors b/model_00052-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..e33e9a4d4aa65fbe4ff22d6d7ec7a73463d54b39
--- /dev/null
+++ b/model_00052-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd2a609fd69db427ee89d78fe127c8ccdbf2451699e59ff7b68bb764c0ce02e0
+size 4932875544
diff --git a/model_00053-of-00072.safetensors b/model_00053-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..77af3eeba82c0ce1494f9808a95e7de0e116c83a
--- /dev/null
+++ b/model_00053-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afdfc40b67e80f8b25b8cf88820794ab0dbf5a861d632c749a7ff18988171718
+size 4932875544
diff --git a/model_00054-of-00072.safetensors b/model_00054-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a59f6ccca3618b1c0ba794ef6bed2aacba36be60
--- /dev/null
+++ b/model_00054-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff1b65d4f2a04376e1c5f62c029775593d377d98d086f96e5b9a1fe7fb5e796
+size 4932875544
diff --git a/model_00055-of-00072.safetensors b/model_00055-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..1f67979b698198b2332968b62e97f6675938e8c7
--- /dev/null
+++ b/model_00055-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e36645b5d1c4a72e41752a56b68f8d4ff5263f0b42e1355f289a3491c1a6b6d6
+size 4932875544
diff --git a/model_00056-of-00072.safetensors b/model_00056-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d6b156f039f0ff9e2b8f9bc4d22454f0425a3a85
--- /dev/null
+++ b/model_00056-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b84629f4c2f9c6e2cf97f55c0cac113868b8871082a556d58a01a3951eff291
+size 4932875544
diff --git a/model_00057-of-00072.safetensors b/model_00057-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..4f3fdb1ac1368066021f967bc5e89cf067aadac5
--- /dev/null
+++ b/model_00057-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ec8b113783e78ade4b64a20405dff9b96f63e95777e4aae777a3a984b81b8ef
+size 4932875544
diff --git a/model_00058-of-00072.safetensors b/model_00058-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..b3fad0a59bbf6a6a2ce4757f3973bee4a23e49bf
--- /dev/null
+++ b/model_00058-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:227572c72ba003d75cdc695d5f8026b79100ee7956c0af22f6aee86ef261b2bf
+size 4932875544
diff --git a/model_00059-of-00072.safetensors b/model_00059-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..7ac51edb09e91ef6c756ac4b48cb93020854e1de
--- /dev/null
+++ b/model_00059-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a542c1c4a6db03794b9d24833c855a375afdd2ca8e69ef5d2548f7694b718ad9
+size 4932875544
diff --git a/model_00060-of-00072.safetensors b/model_00060-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..168181fadda62aeec3e2172851efe02fb49e21e1
--- /dev/null
+++ b/model_00060-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4935184b3c54c51be3642ba6868e15bf150c06a347b5ca2ec8233c692e3a87dc
+size 4932875544
diff --git a/model_00061-of-00072.safetensors b/model_00061-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..3eca8f91e9e03666d7e4fc033292c4b91139c18d
--- /dev/null
+++ b/model_00061-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6a6309a9c7bb97cebeab66028b7e90edc7650ef5fac2078da8d020dbcc5783e
+size 4932875544
diff --git a/model_00062-of-00072.safetensors b/model_00062-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..9d62e6a850c1fe0dce3e3d56b3355b2bd2b4b8d5
--- /dev/null
+++ b/model_00062-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a2cfbe904dfca71b3468599b5595bd94df7a1dd189acaedf1325d91f04aaff7
+size 4932875544
diff --git a/model_00063-of-00072.safetensors b/model_00063-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..1ed10d018f1e879fb9c0c0173f10c78f9a2d07f1
--- /dev/null
+++ b/model_00063-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9ea3e2bc4e8473ee80bc920114b0ab947928ef0ee7a42df26d1edeab9f1681b
+size 4932875544
diff --git a/model_00064-of-00072.safetensors b/model_00064-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..0e97fd55644e4b058621fa270d06f26661233bbb
--- /dev/null
+++ b/model_00064-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5091ee2824e96462dfd5245cf1bdd3ce2505807b1f263f477566fbd2c7ea75c5
+size 4932875544
diff --git a/model_00065-of-00072.safetensors b/model_00065-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a67ebcb4a771ebad0110251146897c0b92699f41
--- /dev/null
+++ b/model_00065-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b72fb40bcbfc463aa8ea1fa9e0f905fdf7b291ab12b75bcd67dee3f260f8a24
+size 4932875544
diff --git a/model_00066-of-00072.safetensors b/model_00066-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..9147b5f6a67ab31996e65e4501f1ad01d3355053
--- /dev/null
+++ b/model_00066-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b14fcdb4e8f0512b8a2a2f1ac0b54e5332e97b415ae49b1816b676325d435f86
+size 4932875544
diff --git a/model_00067-of-00072.safetensors b/model_00067-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..961bb86c3cad3f66b3e11834e7f726be60588c3b
--- /dev/null
+++ b/model_00067-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f917f82a7b8849febcfd185705cc7a448bc6dbc92f8b5b12aab2c90fd01929d4
+size 4932875544
diff --git a/model_00068-of-00072.safetensors b/model_00068-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..085dc86b85535aa3a598e7c75098f3fc6de4a966
--- /dev/null
+++ b/model_00068-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:904d3545cae36cadc2606a71f1149120802a7b7f7a4d44de889426230afd0cca
+size 4932875544
diff --git a/model_00069-of-00072.safetensors b/model_00069-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..fcf2595dd3719ab4e83709afb1a9ab616e070c4b
--- /dev/null
+++ b/model_00069-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d3ffb8083702edcd4ceac85e6a35cc346f937c39459f51aedb7f5d73709e58b
+size 4932875544
diff --git a/model_00070-of-00072.safetensors b/model_00070-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..10d56456a22cfec34585cbe94d5f9b45c12c0b75
--- /dev/null
+++ b/model_00070-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2bba13a0953f68d7e70f091ba4ac732fdd37db28f1fe9245121d0ef5fb1671a
+size 4932875544
diff --git a/model_00071-of-00072.safetensors b/model_00071-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..dd90547ef610cb32814f70c5300af022d8c08b48
--- /dev/null
+++ b/model_00071-of-00072.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e568bd04bfeb045995c4288fd458571c5db25d8a06e8e4801ae42830095b6081
+size 4932875544
diff --git a/model_00072-of-00072.safetensors b/model_00072-of-00072.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..f408f758f60888971281077cac868ec064355322
Binary files /dev/null and b/model_00072-of-00072.safetensors differ