Adding `safetensors` variant of this model

This is an automated PR created with https://huggingface.co/spaces/safetensors/convert

This new file is equivalent to `pytorch_model.bin` but safe in the sense that
no arbitrary code can be put into it.

These files also happen to load much faster than their pytorch counterpart:
https://colab.research.google.com/github/huggingface/notebooks/blob/main/safetensors_doc/en/speed.ipynb

The widgets on your model page will run using this model even if this is not merged
making sure the file actually works.

If you find any issues: please report here: https://huggingface.co/spaces/safetensors/convert/discussions

Feel free to ignore this PR.

model.safetensors.index.json

@@ -0,0 +1,372 @@
+{
+    "metadata": {
+        "total_size": 14138032128
+    },
+    "weight_map": {
+        "h.0.input_layernorm.bias": "model_00002-of-00032.safetensors",
+        "h.0.input_layernorm.weight": "model_00002-of-00032.safetensors",
+        "h.0.mlp.dense_4h_to_h.bias": "model_00002-of-00032.safetensors",
+        "h.0.mlp.dense_4h_to_h.weight": "model_00002-of-00032.safetensors",
+        "h.0.mlp.dense_h_to_4h.bias": "model_00002-of-00032.safetensors",
+        "h.0.mlp.dense_h_to_4h.weight": "model_00002-of-00032.safetensors",
+        "h.0.post_attention_layernorm.bias": "model_00002-of-00032.safetensors",
+        "h.0.post_attention_layernorm.weight": "model_00002-of-00032.safetensors",
+        "h.0.self_attention.dense.bias": "model_00002-of-00032.safetensors",
+        "h.0.self_attention.dense.weight": "model_00002-of-00032.safetensors",
+        "h.0.self_attention.query_key_value.bias": "model_00002-of-00032.safetensors",
+        "h.0.self_attention.query_key_value.weight": "model_00002-of-00032.safetensors",
+        "h.1.input_layernorm.bias": "model_00003-of-00032.safetensors",
+        "h.1.input_layernorm.weight": "model_00003-of-00032.safetensors",
+        "h.1.mlp.dense_4h_to_h.bias": "model_00003-of-00032.safetensors",
+        "h.1.mlp.dense_4h_to_h.weight": "model_00003-of-00032.safetensors",
+        "h.1.mlp.dense_h_to_4h.bias": "model_00003-of-00032.safetensors",
+        "h.1.mlp.dense_h_to_4h.weight": "model_00003-of-00032.safetensors",
+        "h.1.post_attention_layernorm.bias": "model_00003-of-00032.safetensors",
+        "h.1.post_attention_layernorm.weight": "model_00003-of-00032.safetensors",
+        "h.1.self_attention.dense.bias": "model_00003-of-00032.safetensors",
+        "h.1.self_attention.dense.weight": "model_00003-of-00032.safetensors",
+        "h.1.self_attention.query_key_value.bias": "model_00003-of-00032.safetensors",
+        "h.1.self_attention.query_key_value.weight": "model_00003-of-00032.safetensors",
+        "h.10.input_layernorm.bias": "model_00012-of-00032.safetensors",
+        "h.10.input_layernorm.weight": "model_00012-of-00032.safetensors",
+        "h.10.mlp.dense_4h_to_h.bias": "model_00012-of-00032.safetensors",
+        "h.10.mlp.dense_4h_to_h.weight": "model_00012-of-00032.safetensors",
+        "h.10.mlp.dense_h_to_4h.bias": "model_00012-of-00032.safetensors",
+        "h.10.mlp.dense_h_to_4h.weight": "model_00012-of-00032.safetensors",
+        "h.10.post_attention_layernorm.bias": "model_00012-of-00032.safetensors",
+        "h.10.post_attention_layernorm.weight": "model_00012-of-00032.safetensors",
+        "h.10.self_attention.dense.bias": "model_00012-of-00032.safetensors",
+        "h.10.self_attention.dense.weight": "model_00012-of-00032.safetensors",
+        "h.10.self_attention.query_key_value.bias": "model_00012-of-00032.safetensors",
+        "h.10.self_attention.query_key_value.weight": "model_00012-of-00032.safetensors",
+        "h.11.input_layernorm.bias": "model_00013-of-00032.safetensors",
+        "h.11.input_layernorm.weight": "model_00013-of-00032.safetensors",
+        "h.11.mlp.dense_4h_to_h.bias": "model_00013-of-00032.safetensors",
+        "h.11.mlp.dense_4h_to_h.weight": "model_00013-of-00032.safetensors",
+        "h.11.mlp.dense_h_to_4h.bias": "model_00013-of-00032.safetensors",
+        "h.11.mlp.dense_h_to_4h.weight": "model_00013-of-00032.safetensors",
+        "h.11.post_attention_layernorm.bias": "model_00013-of-00032.safetensors",
+        "h.11.post_attention_layernorm.weight": "model_00013-of-00032.safetensors",
+        "h.11.self_attention.dense.bias": "model_00013-of-00032.safetensors",
+        "h.11.self_attention.dense.weight": "model_00013-of-00032.safetensors",
+        "h.11.self_attention.query_key_value.bias": "model_00013-of-00032.safetensors",
+        "h.11.self_attention.query_key_value.weight": "model_00013-of-00032.safetensors",
+        "h.12.input_layernorm.bias": "model_00014-of-00032.safetensors",
+        "h.12.input_layernorm.weight": "model_00014-of-00032.safetensors",
+        "h.12.mlp.dense_4h_to_h.bias": "model_00014-of-00032.safetensors",
+        "h.12.mlp.dense_4h_to_h.weight": "model_00014-of-00032.safetensors",
+        "h.12.mlp.dense_h_to_4h.bias": "model_00014-of-00032.safetensors",
+        "h.12.mlp.dense_h_to_4h.weight": "model_00014-of-00032.safetensors",
+        "h.12.post_attention_layernorm.bias": "model_00014-of-00032.safetensors",
+        "h.12.post_attention_layernorm.weight": "model_00014-of-00032.safetensors",
+        "h.12.self_attention.dense.bias": "model_00014-of-00032.safetensors",
+        "h.12.self_attention.dense.weight": "model_00014-of-00032.safetensors",
+        "h.12.self_attention.query_key_value.bias": "model_00014-of-00032.safetensors",
+        "h.12.self_attention.query_key_value.weight": "model_00014-of-00032.safetensors",
+        "h.13.input_layernorm.bias": "model_00015-of-00032.safetensors",
+        "h.13.input_layernorm.weight": "model_00015-of-00032.safetensors",
+        "h.13.mlp.dense_4h_to_h.bias": "model_00015-of-00032.safetensors",
+        "h.13.mlp.dense_4h_to_h.weight": "model_00015-of-00032.safetensors",
+        "h.13.mlp.dense_h_to_4h.bias": "model_00015-of-00032.safetensors",
+        "h.13.mlp.dense_h_to_4h.weight": "model_00015-of-00032.safetensors",
+        "h.13.post_attention_layernorm.bias": "model_00015-of-00032.safetensors",
+        "h.13.post_attention_layernorm.weight": "model_00015-of-00032.safetensors",
+        "h.13.self_attention.dense.bias": "model_00015-of-00032.safetensors",
+        "h.13.self_attention.dense.weight": "model_00015-of-00032.safetensors",
+        "h.13.self_attention.query_key_value.bias": "model_00015-of-00032.safetensors",
+        "h.13.self_attention.query_key_value.weight": "model_00015-of-00032.safetensors",
+        "h.14.input_layernorm.bias": "model_00016-of-00032.safetensors",
+        "h.14.input_layernorm.weight": "model_00016-of-00032.safetensors",
+        "h.14.mlp.dense_4h_to_h.bias": "model_00016-of-00032.safetensors",
+        "h.14.mlp.dense_4h_to_h.weight": "model_00016-of-00032.safetensors",
+        "h.14.mlp.dense_h_to_4h.bias": "model_00016-of-00032.safetensors",
+        "h.14.mlp.dense_h_to_4h.weight": "model_00016-of-00032.safetensors",
+        "h.14.post_attention_layernorm.bias": "model_00016-of-00032.safetensors",
+        "h.14.post_attention_layernorm.weight": "model_00016-of-00032.safetensors",
+        "h.14.self_attention.dense.bias": "model_00016-of-00032.safetensors",
+        "h.14.self_attention.dense.weight": "model_00016-of-00032.safetensors",
+        "h.14.self_attention.query_key_value.bias": "model_00016-of-00032.safetensors",
+        "h.14.self_attention.query_key_value.weight": "model_00016-of-00032.safetensors",
+        "h.15.input_layernorm.bias": "model_00017-of-00032.safetensors",
+        "h.15.input_layernorm.weight": "model_00017-of-00032.safetensors",
+        "h.15.mlp.dense_4h_to_h.bias": "model_00017-of-00032.safetensors",
+        "h.15.mlp.dense_4h_to_h.weight": "model_00017-of-00032.safetensors",
+        "h.15.mlp.dense_h_to_4h.bias": "model_00017-of-00032.safetensors",
+        "h.15.mlp.dense_h_to_4h.weight": "model_00017-of-00032.safetensors",
+        "h.15.post_attention_layernorm.bias": "model_00017-of-00032.safetensors",
+        "h.15.post_attention_layernorm.weight": "model_00017-of-00032.safetensors",
+        "h.15.self_attention.dense.bias": "model_00017-of-00032.safetensors",
+        "h.15.self_attention.dense.weight": "model_00017-of-00032.safetensors",
+        "h.15.self_attention.query_key_value.bias": "model_00017-of-00032.safetensors",
+        "h.15.self_attention.query_key_value.weight": "model_00017-of-00032.safetensors",
+        "h.16.input_layernorm.bias": "model_00018-of-00032.safetensors",
+        "h.16.input_layernorm.weight": "model_00018-of-00032.safetensors",
+        "h.16.mlp.dense_4h_to_h.bias": "model_00018-of-00032.safetensors",
+        "h.16.mlp.dense_4h_to_h.weight": "model_00018-of-00032.safetensors",
+        "h.16.mlp.dense_h_to_4h.bias": "model_00018-of-00032.safetensors",
+        "h.16.mlp.dense_h_to_4h.weight": "model_00018-of-00032.safetensors",
+        "h.16.post_attention_layernorm.bias": "model_00018-of-00032.safetensors",
+        "h.16.post_attention_layernorm.weight": "model_00018-of-00032.safetensors",
+        "h.16.self_attention.dense.bias": "model_00018-of-00032.safetensors",
+        "h.16.self_attention.dense.weight": "model_00018-of-00032.safetensors",
+        "h.16.self_attention.query_key_value.bias": "model_00018-of-00032.safetensors",
+        "h.16.self_attention.query_key_value.weight": "model_00018-of-00032.safetensors",
+        "h.17.input_layernorm.bias": "model_00019-of-00032.safetensors",
+        "h.17.input_layernorm.weight": "model_00019-of-00032.safetensors",
+        "h.17.mlp.dense_4h_to_h.bias": "model_00019-of-00032.safetensors",
+        "h.17.mlp.dense_4h_to_h.weight": "model_00019-of-00032.safetensors",
+        "h.17.mlp.dense_h_to_4h.bias": "model_00019-of-00032.safetensors",
+        "h.17.mlp.dense_h_to_4h.weight": "model_00019-of-00032.safetensors",
+        "h.17.post_attention_layernorm.bias": "model_00019-of-00032.safetensors",
+        "h.17.post_attention_layernorm.weight": "model_00019-of-00032.safetensors",
+        "h.17.self_attention.dense.bias": "model_00019-of-00032.safetensors",
+        "h.17.self_attention.dense.weight": "model_00019-of-00032.safetensors",
+        "h.17.self_attention.query_key_value.bias": "model_00019-of-00032.safetensors",
+        "h.17.self_attention.query_key_value.weight": "model_00019-of-00032.safetensors",
+        "h.18.input_layernorm.bias": "model_00020-of-00032.safetensors",
+        "h.18.input_layernorm.weight": "model_00020-of-00032.safetensors",
+        "h.18.mlp.dense_4h_to_h.bias": "model_00020-of-00032.safetensors",
+        "h.18.mlp.dense_4h_to_h.weight": "model_00020-of-00032.safetensors",
+        "h.18.mlp.dense_h_to_4h.bias": "model_00020-of-00032.safetensors",
+        "h.18.mlp.dense_h_to_4h.weight": "model_00020-of-00032.safetensors",
+        "h.18.post_attention_layernorm.bias": "model_00020-of-00032.safetensors",
+        "h.18.post_attention_layernorm.weight": "model_00020-of-00032.safetensors",
+        "h.18.self_attention.dense.bias": "model_00020-of-00032.safetensors",
+        "h.18.self_attention.dense.weight": "model_00020-of-00032.safetensors",
+        "h.18.self_attention.query_key_value.bias": "model_00020-of-00032.safetensors",
+        "h.18.self_attention.query_key_value.weight": "model_00020-of-00032.safetensors",
+        "h.19.input_layernorm.bias": "model_00021-of-00032.safetensors",
+        "h.19.input_layernorm.weight": "model_00021-of-00032.safetensors",
+        "h.19.mlp.dense_4h_to_h.bias": "model_00021-of-00032.safetensors",
+        "h.19.mlp.dense_4h_to_h.weight": "model_00021-of-00032.safetensors",
+        "h.19.mlp.dense_h_to_4h.bias": "model_00021-of-00032.safetensors",
+        "h.19.mlp.dense_h_to_4h.weight": "model_00021-of-00032.safetensors",
+        "h.19.post_attention_layernorm.bias": "model_00021-of-00032.safetensors",
+        "h.19.post_attention_layernorm.weight": "model_00021-of-00032.safetensors",
+        "h.19.self_attention.dense.bias": "model_00021-of-00032.safetensors",
+        "h.19.self_attention.dense.weight": "model_00021-of-00032.safetensors",
+        "h.19.self_attention.query_key_value.bias": "model_00021-of-00032.safetensors",
+        "h.19.self_attention.query_key_value.weight": "model_00021-of-00032.safetensors",
+        "h.2.input_layernorm.bias": "model_00004-of-00032.safetensors",
+        "h.2.input_layernorm.weight": "model_00004-of-00032.safetensors",
+        "h.2.mlp.dense_4h_to_h.bias": "model_00004-of-00032.safetensors",
+        "h.2.mlp.dense_4h_to_h.weight": "model_00004-of-00032.safetensors",
+        "h.2.mlp.dense_h_to_4h.bias": "model_00004-of-00032.safetensors",
+        "h.2.mlp.dense_h_to_4h.weight": "model_00004-of-00032.safetensors",
+        "h.2.post_attention_layernorm.bias": "model_00004-of-00032.safetensors",
+        "h.2.post_attention_layernorm.weight": "model_00004-of-00032.safetensors",
+        "h.2.self_attention.dense.bias": "model_00004-of-00032.safetensors",
+        "h.2.self_attention.dense.weight": "model_00004-of-00032.safetensors",
+        "h.2.self_attention.query_key_value.bias": "model_00004-of-00032.safetensors",
+        "h.2.self_attention.query_key_value.weight": "model_00004-of-00032.safetensors",
+        "h.20.input_layernorm.bias": "model_00022-of-00032.safetensors",
+        "h.20.input_layernorm.weight": "model_00022-of-00032.safetensors",
+        "h.20.mlp.dense_4h_to_h.bias": "model_00022-of-00032.safetensors",
+        "h.20.mlp.dense_4h_to_h.weight": "model_00022-of-00032.safetensors",
+        "h.20.mlp.dense_h_to_4h.bias": "model_00022-of-00032.safetensors",
+        "h.20.mlp.dense_h_to_4h.weight": "model_00022-of-00032.safetensors",
+        "h.20.post_attention_layernorm.bias": "model_00022-of-00032.safetensors",
+        "h.20.post_attention_layernorm.weight": "model_00022-of-00032.safetensors",
+        "h.20.self_attention.dense.bias": "model_00022-of-00032.safetensors",
+        "h.20.self_attention.dense.weight": "model_00022-of-00032.safetensors",
+        "h.20.self_attention.query_key_value.bias": "model_00022-of-00032.safetensors",
+        "h.20.self_attention.query_key_value.weight": "model_00022-of-00032.safetensors",
+        "h.21.input_layernorm.bias": "model_00023-of-00032.safetensors",
+        "h.21.input_layernorm.weight": "model_00023-of-00032.safetensors",
+        "h.21.mlp.dense_4h_to_h.bias": "model_00023-of-00032.safetensors",
+        "h.21.mlp.dense_4h_to_h.weight": "model_00023-of-00032.safetensors",
+        "h.21.mlp.dense_h_to_4h.bias": "model_00023-of-00032.safetensors",
+        "h.21.mlp.dense_h_to_4h.weight": "model_00023-of-00032.safetensors",
+        "h.21.post_attention_layernorm.bias": "model_00023-of-00032.safetensors",
+        "h.21.post_attention_layernorm.weight": "model_00023-of-00032.safetensors",
+        "h.21.self_attention.dense.bias": "model_00023-of-00032.safetensors",
+        "h.21.self_attention.dense.weight": "model_00023-of-00032.safetensors",
+        "h.21.self_attention.query_key_value.bias": "model_00023-of-00032.safetensors",
+        "h.21.self_attention.query_key_value.weight": "model_00023-of-00032.safetensors",
+        "h.22.input_layernorm.bias": "model_00024-of-00032.safetensors",
+        "h.22.input_layernorm.weight": "model_00024-of-00032.safetensors",
+        "h.22.mlp.dense_4h_to_h.bias": "model_00024-of-00032.safetensors",
+        "h.22.mlp.dense_4h_to_h.weight": "model_00024-of-00032.safetensors",
+        "h.22.mlp.dense_h_to_4h.bias": "model_00024-of-00032.safetensors",
+        "h.22.mlp.dense_h_to_4h.weight": "model_00024-of-00032.safetensors",
+        "h.22.post_attention_layernorm.bias": "model_00024-of-00032.safetensors",
+        "h.22.post_attention_layernorm.weight": "model_00024-of-00032.safetensors",
+        "h.22.self_attention.dense.bias": "model_00024-of-00032.safetensors",
+        "h.22.self_attention.dense.weight": "model_00024-of-00032.safetensors",
+        "h.22.self_attention.query_key_value.bias": "model_00024-of-00032.safetensors",
+        "h.22.self_attention.query_key_value.weight": "model_00024-of-00032.safetensors",
+        "h.23.input_layernorm.bias": "model_00025-of-00032.safetensors",
+        "h.23.input_layernorm.weight": "model_00025-of-00032.safetensors",
+        "h.23.mlp.dense_4h_to_h.bias": "model_00025-of-00032.safetensors",
+        "h.23.mlp.dense_4h_to_h.weight": "model_00025-of-00032.safetensors",
+        "h.23.mlp.dense_h_to_4h.bias": "model_00025-of-00032.safetensors",
+        "h.23.mlp.dense_h_to_4h.weight": "model_00025-of-00032.safetensors",
+        "h.23.post_attention_layernorm.bias": "model_00025-of-00032.safetensors",
+        "h.23.post_attention_layernorm.weight": "model_00025-of-00032.safetensors",
+        "h.23.self_attention.dense.bias": "model_00025-of-00032.safetensors",
+        "h.23.self_attention.dense.weight": "model_00025-of-00032.safetensors",
+        "h.23.self_attention.query_key_value.bias": "model_00025-of-00032.safetensors",
+        "h.23.self_attention.query_key_value.weight": "model_00025-of-00032.safetensors",
+        "h.24.input_layernorm.bias": "model_00026-of-00032.safetensors",
+        "h.24.input_layernorm.weight": "model_00026-of-00032.safetensors",
+        "h.24.mlp.dense_4h_to_h.bias": "model_00026-of-00032.safetensors",
+        "h.24.mlp.dense_4h_to_h.weight": "model_00026-of-00032.safetensors",
+        "h.24.mlp.dense_h_to_4h.bias": "model_00026-of-00032.safetensors",
+        "h.24.mlp.dense_h_to_4h.weight": "model_00026-of-00032.safetensors",
+        "h.24.post_attention_layernorm.bias": "model_00026-of-00032.safetensors",
+        "h.24.post_attention_layernorm.weight": "model_00026-of-00032.safetensors",
+        "h.24.self_attention.dense.bias": "model_00026-of-00032.safetensors",
+        "h.24.self_attention.dense.weight": "model_00026-of-00032.safetensors",
+        "h.24.self_attention.query_key_value.bias": "model_00026-of-00032.safetensors",
+        "h.24.self_attention.query_key_value.weight": "model_00026-of-00032.safetensors",
+        "h.25.input_layernorm.bias": "model_00027-of-00032.safetensors",
+        "h.25.input_layernorm.weight": "model_00027-of-00032.safetensors",
+        "h.25.mlp.dense_4h_to_h.bias": "model_00027-of-00032.safetensors",
+        "h.25.mlp.dense_4h_to_h.weight": "model_00027-of-00032.safetensors",
+        "h.25.mlp.dense_h_to_4h.bias": "model_00027-of-00032.safetensors",
+        "h.25.mlp.dense_h_to_4h.weight": "model_00027-of-00032.safetensors",
+        "h.25.post_attention_layernorm.bias": "model_00027-of-00032.safetensors",
+        "h.25.post_attention_layernorm.weight": "model_00027-of-00032.safetensors",
+        "h.25.self_attention.dense.bias": "model_00027-of-00032.safetensors",
+        "h.25.self_attention.dense.weight": "model_00027-of-00032.safetensors",
+        "h.25.self_attention.query_key_value.bias": "model_00027-of-00032.safetensors",
+        "h.25.self_attention.query_key_value.weight": "model_00027-of-00032.safetensors",
+        "h.26.input_layernorm.bias": "model_00028-of-00032.safetensors",
+        "h.26.input_layernorm.weight": "model_00028-of-00032.safetensors",
+        "h.26.mlp.dense_4h_to_h.bias": "model_00028-of-00032.safetensors",
+        "h.26.mlp.dense_4h_to_h.weight": "model_00028-of-00032.safetensors",
+        "h.26.mlp.dense_h_to_4h.bias": "model_00028-of-00032.safetensors",
+        "h.26.mlp.dense_h_to_4h.weight": "model_00028-of-00032.safetensors",
+        "h.26.post_attention_layernorm.bias": "model_00028-of-00032.safetensors",
+        "h.26.post_attention_layernorm.weight": "model_00028-of-00032.safetensors",
+        "h.26.self_attention.dense.bias": "model_00028-of-00032.safetensors",
+        "h.26.self_attention.dense.weight": "model_00028-of-00032.safetensors",
+        "h.26.self_attention.query_key_value.bias": "model_00028-of-00032.safetensors",
+        "h.26.self_attention.query_key_value.weight": "model_00028-of-00032.safetensors",
+        "h.27.input_layernorm.bias": "model_00029-of-00032.safetensors",
+        "h.27.input_layernorm.weight": "model_00029-of-00032.safetensors",
+        "h.27.mlp.dense_4h_to_h.bias": "model_00029-of-00032.safetensors",
+        "h.27.mlp.dense_4h_to_h.weight": "model_00029-of-00032.safetensors",
+        "h.27.mlp.dense_h_to_4h.bias": "model_00029-of-00032.safetensors",
+        "h.27.mlp.dense_h_to_4h.weight": "model_00029-of-00032.safetensors",
+        "h.27.post_attention_layernorm.bias": "model_00029-of-00032.safetensors",
+        "h.27.post_attention_layernorm.weight": "model_00029-of-00032.safetensors",
+        "h.27.self_attention.dense.bias": "model_00029-of-00032.safetensors",
+        "h.27.self_attention.dense.weight": "model_00029-of-00032.safetensors",
+        "h.27.self_attention.query_key_value.bias": "model_00029-of-00032.safetensors",
+        "h.27.self_attention.query_key_value.weight": "model_00029-of-00032.safetensors",
+        "h.28.input_layernorm.bias": "model_00030-of-00032.safetensors",
+        "h.28.input_layernorm.weight": "model_00030-of-00032.safetensors",
+        "h.28.mlp.dense_4h_to_h.bias": "model_00030-of-00032.safetensors",
+        "h.28.mlp.dense_4h_to_h.weight": "model_00030-of-00032.safetensors",
+        "h.28.mlp.dense_h_to_4h.bias": "model_00030-of-00032.safetensors",
+        "h.28.mlp.dense_h_to_4h.weight": "model_00030-of-00032.safetensors",
+        "h.28.post_attention_layernorm.bias": "model_00030-of-00032.safetensors",
+        "h.28.post_attention_layernorm.weight": "model_00030-of-00032.safetensors",
+        "h.28.self_attention.dense.bias": "model_00030-of-00032.safetensors",
+        "h.28.self_attention.dense.weight": "model_00030-of-00032.safetensors",
+        "h.28.self_attention.query_key_value.bias": "model_00030-of-00032.safetensors",
+        "h.28.self_attention.query_key_value.weight": "model_00030-of-00032.safetensors",
+        "h.29.input_layernorm.bias": "model_00031-of-00032.safetensors",
+        "h.29.input_layernorm.weight": "model_00031-of-00032.safetensors",
+        "h.29.mlp.dense_4h_to_h.bias": "model_00031-of-00032.safetensors",
+        "h.29.mlp.dense_4h_to_h.weight": "model_00031-of-00032.safetensors",
+        "h.29.mlp.dense_h_to_4h.bias": "model_00031-of-00032.safetensors",
+        "h.29.mlp.dense_h_to_4h.weight": "model_00031-of-00032.safetensors",
+        "h.29.post_attention_layernorm.bias": "model_00031-of-00032.safetensors",
+        "h.29.post_attention_layernorm.weight": "model_00031-of-00032.safetensors",
+        "h.29.self_attention.dense.bias": "model_00031-of-00032.safetensors",
+        "h.29.self_attention.dense.weight": "model_00031-of-00032.safetensors",
+        "h.29.self_attention.query_key_value.bias": "model_00031-of-00032.safetensors",
+        "h.29.self_attention.query_key_value.weight": "model_00031-of-00032.safetensors",
+        "h.3.input_layernorm.bias": "model_00005-of-00032.safetensors",
+        "h.3.input_layernorm.weight": "model_00005-of-00032.safetensors",
+        "h.3.mlp.dense_4h_to_h.bias": "model_00005-of-00032.safetensors",
+        "h.3.mlp.dense_4h_to_h.weight": "model_00005-of-00032.safetensors",
+        "h.3.mlp.dense_h_to_4h.bias": "model_00005-of-00032.safetensors",
+        "h.3.mlp.dense_h_to_4h.weight": "model_00005-of-00032.safetensors",
+        "h.3.post_attention_layernorm.bias": "model_00005-of-00032.safetensors",
+        "h.3.post_attention_layernorm.weight": "model_00005-of-00032.safetensors",
+        "h.3.self_attention.dense.bias": "model_00005-of-00032.safetensors",
+        "h.3.self_attention.dense.weight": "model_00005-of-00032.safetensors",
+        "h.3.self_attention.query_key_value.bias": "model_00005-of-00032.safetensors",
+        "h.3.self_attention.query_key_value.weight": "model_00005-of-00032.safetensors",
+        "h.4.input_layernorm.bias": "model_00006-of-00032.safetensors",
+        "h.4.input_layernorm.weight": "model_00006-of-00032.safetensors",
+        "h.4.mlp.dense_4h_to_h.bias": "model_00006-of-00032.safetensors",
+        "h.4.mlp.dense_4h_to_h.weight": "model_00006-of-00032.safetensors",
+        "h.4.mlp.dense_h_to_4h.bias": "model_00006-of-00032.safetensors",
+        "h.4.mlp.dense_h_to_4h.weight": "model_00006-of-00032.safetensors",
+        "h.4.post_attention_layernorm.bias": "model_00006-of-00032.safetensors",
+        "h.4.post_attention_layernorm.weight": "model_00006-of-00032.safetensors",
+        "h.4.self_attention.dense.bias": "model_00006-of-00032.safetensors",
+        "h.4.self_attention.dense.weight": "model_00006-of-00032.safetensors",
+        "h.4.self_attention.query_key_value.bias": "model_00006-of-00032.safetensors",
+        "h.4.self_attention.query_key_value.weight": "model_00006-of-00032.safetensors",
+        "h.5.input_layernorm.bias": "model_00007-of-00032.safetensors",
+        "h.5.input_layernorm.weight": "model_00007-of-00032.safetensors",
+        "h.5.mlp.dense_4h_to_h.bias": "model_00007-of-00032.safetensors",
+        "h.5.mlp.dense_4h_to_h.weight": "model_00007-of-00032.safetensors",
+        "h.5.mlp.dense_h_to_4h.bias": "model_00007-of-00032.safetensors",
+        "h.5.mlp.dense_h_to_4h.weight": "model_00007-of-00032.safetensors",
+        "h.5.post_attention_layernorm.bias": "model_00007-of-00032.safetensors",
+        "h.5.post_attention_layernorm.weight": "model_00007-of-00032.safetensors",
+        "h.5.self_attention.dense.bias": "model_00007-of-00032.safetensors",
+        "h.5.self_attention.dense.weight": "model_00007-of-00032.safetensors",
+        "h.5.self_attention.query_key_value.bias": "model_00007-of-00032.safetensors",
+        "h.5.self_attention.query_key_value.weight": "model_00007-of-00032.safetensors",
+        "h.6.input_layernorm.bias": "model_00008-of-00032.safetensors",
+        "h.6.input_layernorm.weight": "model_00008-of-00032.safetensors",
+        "h.6.mlp.dense_4h_to_h.bias": "model_00008-of-00032.safetensors",
+        "h.6.mlp.dense_4h_to_h.weight": "model_00008-of-00032.safetensors",
+        "h.6.mlp.dense_h_to_4h.bias": "model_00008-of-00032.safetensors",
+        "h.6.mlp.dense_h_to_4h.weight": "model_00008-of-00032.safetensors",
+        "h.6.post_attention_layernorm.bias": "model_00008-of-00032.safetensors",
+        "h.6.post_attention_layernorm.weight": "model_00008-of-00032.safetensors",
+        "h.6.self_attention.dense.bias": "model_00008-of-00032.safetensors",
+        "h.6.self_attention.dense.weight": "model_00008-of-00032.safetensors",
+        "h.6.self_attention.query_key_value.bias": "model_00008-of-00032.safetensors",
+        "h.6.self_attention.query_key_value.weight": "model_00008-of-00032.safetensors",
+        "h.7.input_layernorm.bias": "model_00009-of-00032.safetensors",
+        "h.7.input_layernorm.weight": "model_00009-of-00032.safetensors",
+        "h.7.mlp.dense_4h_to_h.bias": "model_00009-of-00032.safetensors",
+        "h.7.mlp.dense_4h_to_h.weight": "model_00009-of-00032.safetensors",
+        "h.7.mlp.dense_h_to_4h.bias": "model_00009-of-00032.safetensors",
+        "h.7.mlp.dense_h_to_4h.weight": "model_00009-of-00032.safetensors",
+        "h.7.post_attention_layernorm.bias": "model_00009-of-00032.safetensors",
+        "h.7.post_attention_layernorm.weight": "model_00009-of-00032.safetensors",
+        "h.7.self_attention.dense.bias": "model_00009-of-00032.safetensors",
+        "h.7.self_attention.dense.weight": "model_00009-of-00032.safetensors",
+        "h.7.self_attention.query_key_value.bias": "model_00009-of-00032.safetensors",
+        "h.7.self_attention.query_key_value.weight": "model_00009-of-00032.safetensors",
+        "h.8.input_layernorm.bias": "model_00010-of-00032.safetensors",
+        "h.8.input_layernorm.weight": "model_00010-of-00032.safetensors",
+        "h.8.mlp.dense_4h_to_h.bias": "model_00010-of-00032.safetensors",
+        "h.8.mlp.dense_4h_to_h.weight": "model_00010-of-00032.safetensors",
+        "h.8.mlp.dense_h_to_4h.bias": "model_00010-of-00032.safetensors",
+        "h.8.mlp.dense_h_to_4h.weight": "model_00010-of-00032.safetensors",
+        "h.8.post_attention_layernorm.bias": "model_00010-of-00032.safetensors",
+        "h.8.post_attention_layernorm.weight": "model_00010-of-00032.safetensors",
+        "h.8.self_attention.dense.bias": "model_00010-of-00032.safetensors",
+        "h.8.self_attention.dense.weight": "model_00010-of-00032.safetensors",
+        "h.8.self_attention.query_key_value.bias": "model_00010-of-00032.safetensors",
+        "h.8.self_attention.query_key_value.weight": "model_00010-of-00032.safetensors",
+        "h.9.input_layernorm.bias": "model_00011-of-00032.safetensors",
+        "h.9.input_layernorm.weight": "model_00011-of-00032.safetensors",
+        "h.9.mlp.dense_4h_to_h.bias": "model_00011-of-00032.safetensors",
+        "h.9.mlp.dense_4h_to_h.weight": "model_00011-of-00032.safetensors",
+        "h.9.mlp.dense_h_to_4h.bias": "model_00011-of-00032.safetensors",
+        "h.9.mlp.dense_h_to_4h.weight": "model_00011-of-00032.safetensors",
+        "h.9.post_attention_layernorm.bias": "model_00011-of-00032.safetensors",
+        "h.9.post_attention_layernorm.weight": "model_00011-of-00032.safetensors",
+        "h.9.self_attention.dense.bias": "model_00011-of-00032.safetensors",
+        "h.9.self_attention.dense.weight": "model_00011-of-00032.safetensors",
+        "h.9.self_attention.query_key_value.bias": "model_00011-of-00032.safetensors",
+        "h.9.self_attention.query_key_value.weight": "model_00011-of-00032.safetensors",
+        "ln_f.bias": "model_00032-of-00032.safetensors",
+        "ln_f.weight": "model_00032-of-00032.safetensors",
+        "word_embeddings.weight": "model_00001-of-00032.safetensors",
+        "word_embeddings_layernorm.bias": "model_00001-of-00032.safetensors",
+        "word_embeddings_layernorm.weight": "model_00001-of-00032.safetensors"
+    }
+}

model_00001-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:846bf82a5f378d6b6bcdfe7fc895fad50550de188b91443190fe7ef19cdd979f
+size 2055225688

model_00002-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a4dfc0a22b52b0cc2dc19e60b2b104c991e219d93264b09efffab361b53a4df
+size 402760936

model_00003-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36f4fd85aa9fcc853b0390b101b2458c2a0a636b0b68d157f965470fd2adc437
+size 402760936

model_00004-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cfd389b68807991c801a08b327c047820b0102b3ae0b7ea3348e8930ebc0475
+size 402760936

model_00005-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2de9c8fd80534c3158dc885d941dec73d60b129dad83e549693c0bd4aabd6cd0
+size 402760936

model_00006-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ef19237c0767254cd919513f56bbf1a7b905553d7384803c7f2cdf92d795bf7
+size 402760936

model_00007-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc89cfd2ce2766d6bbc0eb595d5f29e4c5db8cf694b9038df5ecaf14d590e211
+size 402760936

model_00008-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5e7e6f4bb4c2107b030f4d7bc3296cf4b3dbe5a5008ce8227977eca6cb31e4f
+size 402760936

model_00009-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03749a41eb325334fc7b4f75214c90869721eb64461e620e85791846c8c5dd30
+size 402760936

model_00010-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7890e7cf717bcafae3a650cffe5c68f02a48533cbdf7c2eca1eb1bc4fb8ac67
+size 402760936

model_00011-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fa83ae15bdd69c4351fc2ce1de81dbbddcdf0cdf306930f2e55f2ebb35ab9fe
+size 402760936

model_00012-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dbb9821ac75935934522cf7cd37ccdf858037f680578240269bae094b85569d
+size 402760944

model_00013-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7bb2003780610fe620180c8cef910e043fa81e66819a920cb6e6f3cc14cc0d6
+size 402760944

model_00014-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f43c52d212b3e54c5e9f885e0ddcda57035e6511322413c2ca339f5b568df09d
+size 402760944

model_00015-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6d18960eb9f4af8e9b99e36b2e3392330583c246edbb2445a808c985f03910f
+size 402760944

model_00016-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7f38fd970aafe114fb91dc102f66bbb8aa478c3bf46f68f2072185d6d88f532
+size 402760944

model_00017-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7937412cf61fa1de13a088c56150e113d6c277680f543026dbef608dc291af33
+size 402760944

model_00018-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef051dfe5245283bb8eaf78dad735e2e4242abd19edd30e55748ca7393436486
+size 402760944

model_00019-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:372c654a409e6e8c6c0f579e997325bc8c64708271b3f02c626be4d7641d8313
+size 402760944

model_00020-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b7553bba596b3cae58e54912be93bcbf1e75b08b07703b4f62b8edec970264a
+size 402760944

model_00021-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63019d31e618b2553e75851bd5e149093b99992599b9be9e003e7df1e2b04b8b
+size 402760944

model_00022-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf80f0d54d93ba8801bcd09ee027aed6530b8fc1753dce9192f90861c7d73d65
+size 402760944

model_00023-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6588e4b3b47765068aedb0be4d2d7cb1f75a1ce21ab5985fad9f739af53ae558
+size 402760944

model_00024-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5065235371f8906e4945276f21a52b95428f467cd5ae8499be4e9e35c1afa5ec
+size 402760944

model_00025-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:835c5df479ba0bde323421d50669b1996dd7c6f0be7e8de02affd212f3922ce5
+size 402760944

model_00026-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82fd07cf04f2a27a3ab7fe687125b99750054b2f2a0ac4b31fbe617f235e8758
+size 402760944

model_00027-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08f079829dbe1bb89affa6576994c2b39447a197e07c4cc17c299f37f17dac82
+size 402760944

model_00028-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da7af05c66577e71ff466f3c984ef6abbe8af7a5f5d4a0fb105809eb76f3d358
+size 402760944

model_00029-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc17caffe74a8f5ca12ba1f15dc8255e31c63f7fb2b86fc8c3b3248c5c1070c7
+size 402760944

model_00030-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9f753eb7a6ed5f6f246abe41557d3ac4808c3f589d1584b55b0628b4c1a093c
+size 402760944

model_00031-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6aae64b7655748735775ba83875c5d01475557cbbb8c7f778a6af824a212b8fa
+size 402760944

model_00032-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:405d23c04d72e9ee258fd840c588c32df74ec2af5c17aadcfc079d3519fb8249
+size 16568