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": 12494913536
+    },
+    "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:d2f1390bae906e333a6c9cd50ec35473b0c2c652647849d65ff5253b91bece80
+size 412107088

model_00002-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fcdf1e837accfe287ebd4feacb94346858ce49ed9e337fd5ca4f544c58646e1
+size 402760936

model_00003-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:931835d20fc70023ad19baf2c9e60d31330ad0c53187fe8a970f8c0f68a65b01
+size 402760936

model_00004-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71e0d54dbd0536714ef29998f074bfec23866646eddbc42347f5f1aa846fe8c6
+size 402760936

model_00005-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3e7b1f402e2e2f1dd254e6b7aa2ea752c176bc317985483c1c72e11ea2899f3
+size 402760936

model_00006-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41db93b0dc06a923436f70bd0f53f438074467d543b0d1150f493a0ed1c3fba2
+size 402760936

model_00007-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2a369ed2a23fd1cc10f7bb76c0b7b3c180e121441f53244e4f9fac0551908a5
+size 402760936

model_00008-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:138dc3eb34fcdd026876cfdf22b58d0561df09835ffd92b5879c4ff0c2ef79fb
+size 402760936

model_00009-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d2312ab28421cfbff0ffd2c1723f7beee7ff9a92394d77d2087cb9421394f27
+size 402760936

model_00010-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f3138eea856f5a10872005b52dc378badd8f2f7e24972f95a5efb2f6e50a064
+size 402760936

model_00011-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ff4a5f42f366579e662fb2ceacc8ba3a8edeeba6d67cd994fdfdfd32d4f7f68
+size 402760936

model_00012-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffe25adb542ea296171fa711d1b818fba485d3aa4dabc38f6403ca976ef3c2c0
+size 402760944

model_00013-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:363931fb820305eac2192fe6f11a1682d6be8ba5657d0f11f3b1f6530e35dff9
+size 402760944

model_00014-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1904358bcaf7f054b9ca975f84a9b460b48f8031efa4b3cfa6152278f3e5d22e
+size 402760944

model_00015-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c3d12b804003d03109604de36902ccbb1ec6ed878b11aeb9088c909828b08dd
+size 402760944

model_00016-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5822d9edcbe3d76320fde21938fcbb4054e895da42d025b4a22808c2bf5e3d6b
+size 402760944

model_00017-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc82373b5ff8ac1921ab40866e8c6c461e2772eb81e0bd813193710de17a7d01
+size 402760944

model_00018-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d0fac7636c0aa081edeea29625e1211a4811a61f09549083b5bb577b1724d07
+size 402760944

model_00019-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ac8ec803bfb2fcded4ad54673c5a7f6e6946f7b2293f2afe2e3dff0e06aaa68
+size 402760944

model_00020-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7b01b5f6337377f3e301407260d080e9aa869c06760e7581057985d3b036fd2
+size 402760944

model_00021-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d46d97fe0a91d82afebd43afa4bc75f2f33e598d08f740666ec96003f823eff
+size 402760944

model_00022-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24b30e5832d42bc57edba94f5a8157c54fb7daca86280b5f5a9bc487f6005020
+size 402760944

model_00023-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0460f1f98f3c607b0ab6c44cdf292e5ad06e120ddda7656de0c02136e9838248
+size 402760944

model_00024-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe2b9316fc6323f9802aa47a942159224e96d533e7f898741df89f39a4aed764
+size 402760944

model_00025-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe866d2c5e11e9c57fc8153e32942c30808637c268aa9c98b2a44ceb69def8fe
+size 402760944

model_00026-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:230da742298b9a5e592067485ae54cbb6a1e420ca7a0c2b40ad9f4b53662ac5e
+size 402760944

model_00027-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bd1aef90f9423712b9c8e4777e7fe3b9cfa74f705c5b69f29f2b79161708bf4
+size 402760944

model_00028-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbe503ca0c9ffdf840633547be18d066eef6eda8f5e32557ce7698deb92b1bcd
+size 402760944

model_00029-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abccf4f71f8a66b2aa9f67f72d50f2bc4b022f288fea07e7cd0f6870734fb6b6
+size 402760944

model_00030-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0ab130d8209c0f71f5f1e879e0579988ee5b02d5e13b5ad953b8f797ee65637
+size 402760944

model_00031-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c8a84de9a59027f1a66ff0188cc95a508d4cd3061f4c7766ad5bc6c70cfa9fc
+size 402760944

model_00032-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6d3e81db1cbe40a1ce9c5489e197c615eef5496f59033ed076c6f6485d11b76
+size 16568