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.

.gitattributes

@@ -29,3 +29,18 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+model_00007-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00010-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00008-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00002-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00013-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00004-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00009-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00003-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00012-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00015-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00001-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00005-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00011-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00006-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
+model_00014-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text

model.safetensors.index.json

@@ -0,0 +1,517 @@
+{
+    "metadata": {
+        "total_size": 45229301760
+    },
+    "weight_map": {
+        "decoder.block.0.layer.0.SelfAttention.k.weight": "model_00006-of-00015.safetensors",
+        "decoder.block.0.layer.0.SelfAttention.o.weight": "model_00006-of-00015.safetensors",
+        "decoder.block.0.layer.0.SelfAttention.q.weight": "model_00006-of-00015.safetensors",
+        "decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model_00006-of-00015.safetensors",
+        "decoder.block.0.layer.0.SelfAttention.v.weight": "model_00006-of-00015.safetensors",
+        "decoder.block.0.layer.0.layer_norm.weight": "model_00006-of-00015.safetensors",
+        "decoder.block.0.layer.1.EncDecAttention.k.weight": "model_00006-of-00015.safetensors",
+        "decoder.block.0.layer.1.EncDecAttention.o.weight": "model_00007-of-00015.safetensors",
+        "decoder.block.0.layer.1.EncDecAttention.q.weight": "model_00006-of-00015.safetensors",
+        "decoder.block.0.layer.1.EncDecAttention.relative_attention_bias.weight": "model_00007-of-00015.safetensors",
+        "decoder.block.0.layer.1.EncDecAttention.v.weight": "model_00006-of-00015.safetensors",
+        "decoder.block.0.layer.1.layer_norm.weight": "model_00007-of-00015.safetensors",
+        "decoder.block.0.layer.2.DenseReluDense.wi.weight": "model_00007-of-00015.safetensors",
+        "decoder.block.0.layer.2.DenseReluDense.wo.weight": "model_00007-of-00015.safetensors",
+        "decoder.block.0.layer.2.layer_norm.weight": "model_00007-of-00015.safetensors",
+        "decoder.block.1.layer.0.SelfAttention.k.weight": "model_00007-of-00015.safetensors",
+        "decoder.block.1.layer.0.SelfAttention.o.weight": "model_00007-of-00015.safetensors",
+        "decoder.block.1.layer.0.SelfAttention.q.weight": "model_00007-of-00015.safetensors",
+        "decoder.block.1.layer.0.SelfAttention.v.weight": "model_00007-of-00015.safetensors",
+        "decoder.block.1.layer.0.layer_norm.weight": "model_00007-of-00015.safetensors",
+        "decoder.block.1.layer.1.EncDecAttention.k.weight": "model_00007-of-00015.safetensors",
+        "decoder.block.1.layer.1.EncDecAttention.o.weight": "model_00007-of-00015.safetensors",
+        "decoder.block.1.layer.1.EncDecAttention.q.weight": "model_00007-of-00015.safetensors",
+        "decoder.block.1.layer.1.EncDecAttention.v.weight": "model_00007-of-00015.safetensors",
+        "decoder.block.1.layer.1.layer_norm.weight": "model_00007-of-00015.safetensors",
+        "decoder.block.1.layer.2.DenseReluDense.wi.weight": "model_00007-of-00015.safetensors",
+        "decoder.block.1.layer.2.DenseReluDense.wo.weight": "model_00007-of-00015.safetensors",
+        "decoder.block.1.layer.2.layer_norm.weight": "model_00007-of-00015.safetensors",
+        "decoder.block.10.layer.0.SelfAttention.k.weight": "model_00010-of-00015.safetensors",
+        "decoder.block.10.layer.0.SelfAttention.o.weight": "model_00010-of-00015.safetensors",
+        "decoder.block.10.layer.0.SelfAttention.q.weight": "model_00010-of-00015.safetensors",
+        "decoder.block.10.layer.0.SelfAttention.v.weight": "model_00010-of-00015.safetensors",
+        "decoder.block.10.layer.0.layer_norm.weight": "model_00010-of-00015.safetensors",
+        "decoder.block.10.layer.1.EncDecAttention.k.weight": "model_00010-of-00015.safetensors",
+        "decoder.block.10.layer.1.EncDecAttention.o.weight": "model_00010-of-00015.safetensors",
+        "decoder.block.10.layer.1.EncDecAttention.q.weight": "model_00010-of-00015.safetensors",
+        "decoder.block.10.layer.1.EncDecAttention.v.weight": "model_00010-of-00015.safetensors",
+        "decoder.block.10.layer.1.layer_norm.weight": "model_00010-of-00015.safetensors",
+        "decoder.block.10.layer.2.DenseReluDense.wi.weight": "model_00010-of-00015.safetensors",
+        "decoder.block.10.layer.2.DenseReluDense.wo.weight": "model_00010-of-00015.safetensors",
+        "decoder.block.10.layer.2.layer_norm.weight": "model_00010-of-00015.safetensors",
+        "decoder.block.11.layer.0.SelfAttention.k.weight": "model_00011-of-00015.safetensors",
+        "decoder.block.11.layer.0.SelfAttention.o.weight": "model_00011-of-00015.safetensors",
+        "decoder.block.11.layer.0.SelfAttention.q.weight": "model_00011-of-00015.safetensors",
+        "decoder.block.11.layer.0.SelfAttention.v.weight": "model_00011-of-00015.safetensors",
+        "decoder.block.11.layer.0.layer_norm.weight": "model_00011-of-00015.safetensors",
+        "decoder.block.11.layer.1.EncDecAttention.k.weight": "model_00011-of-00015.safetensors",
+        "decoder.block.11.layer.1.EncDecAttention.o.weight": "model_00011-of-00015.safetensors",
+        "decoder.block.11.layer.1.EncDecAttention.q.weight": "model_00011-of-00015.safetensors",
+        "decoder.block.11.layer.1.EncDecAttention.v.weight": "model_00011-of-00015.safetensors",
+        "decoder.block.11.layer.1.layer_norm.weight": "model_00011-of-00015.safetensors",
+        "decoder.block.11.layer.2.DenseReluDense.wi.weight": "model_00011-of-00015.safetensors",
+        "decoder.block.11.layer.2.DenseReluDense.wo.weight": "model_00011-of-00015.safetensors",
+        "decoder.block.11.layer.2.layer_norm.weight": "model_00011-of-00015.safetensors",
+        "decoder.block.12.layer.0.SelfAttention.k.weight": "model_00011-of-00015.safetensors",
+        "decoder.block.12.layer.0.SelfAttention.o.weight": "model_00011-of-00015.safetensors",
+        "decoder.block.12.layer.0.SelfAttention.q.weight": "model_00011-of-00015.safetensors",
+        "decoder.block.12.layer.0.SelfAttention.v.weight": "model_00011-of-00015.safetensors",
+        "decoder.block.12.layer.0.layer_norm.weight": "model_00011-of-00015.safetensors",
+        "decoder.block.12.layer.1.EncDecAttention.k.weight": "model_00011-of-00015.safetensors",
+        "decoder.block.12.layer.1.EncDecAttention.o.weight": "model_00011-of-00015.safetensors",
+        "decoder.block.12.layer.1.EncDecAttention.q.weight": "model_00011-of-00015.safetensors",
+        "decoder.block.12.layer.1.EncDecAttention.v.weight": "model_00011-of-00015.safetensors",
+        "decoder.block.12.layer.1.layer_norm.weight": "model_00011-of-00015.safetensors",
+        "decoder.block.12.layer.2.DenseReluDense.wi.weight": "model_00011-of-00015.safetensors",
+        "decoder.block.12.layer.2.DenseReluDense.wo.weight": "model_00011-of-00015.safetensors",
+        "decoder.block.12.layer.2.layer_norm.weight": "model_00011-of-00015.safetensors",
+        "decoder.block.13.layer.0.SelfAttention.k.weight": "model_00011-of-00015.safetensors",
+        "decoder.block.13.layer.0.SelfAttention.o.weight": "model_00011-of-00015.safetensors",
+        "decoder.block.13.layer.0.SelfAttention.q.weight": "model_00011-of-00015.safetensors",
+        "decoder.block.13.layer.0.SelfAttention.v.weight": "model_00011-of-00015.safetensors",
+        "decoder.block.13.layer.0.layer_norm.weight": "model_00011-of-00015.safetensors",
+        "decoder.block.13.layer.1.EncDecAttention.k.weight": "model_00011-of-00015.safetensors",
+        "decoder.block.13.layer.1.EncDecAttention.o.weight": "model_00012-of-00015.safetensors",
+        "decoder.block.13.layer.1.EncDecAttention.q.weight": "model_00011-of-00015.safetensors",
+        "decoder.block.13.layer.1.EncDecAttention.v.weight": "model_00011-of-00015.safetensors",
+        "decoder.block.13.layer.1.layer_norm.weight": "model_00012-of-00015.safetensors",
+        "decoder.block.13.layer.2.DenseReluDense.wi.weight": "model_00012-of-00015.safetensors",
+        "decoder.block.13.layer.2.DenseReluDense.wo.weight": "model_00012-of-00015.safetensors",
+        "decoder.block.13.layer.2.layer_norm.weight": "model_00012-of-00015.safetensors",
+        "decoder.block.14.layer.0.SelfAttention.k.weight": "model_00012-of-00015.safetensors",
+        "decoder.block.14.layer.0.SelfAttention.o.weight": "model_00012-of-00015.safetensors",
+        "decoder.block.14.layer.0.SelfAttention.q.weight": "model_00012-of-00015.safetensors",
+        "decoder.block.14.layer.0.SelfAttention.v.weight": "model_00012-of-00015.safetensors",
+        "decoder.block.14.layer.0.layer_norm.weight": "model_00012-of-00015.safetensors",
+        "decoder.block.14.layer.1.EncDecAttention.k.weight": "model_00012-of-00015.safetensors",
+        "decoder.block.14.layer.1.EncDecAttention.o.weight": "model_00012-of-00015.safetensors",
+        "decoder.block.14.layer.1.EncDecAttention.q.weight": "model_00012-of-00015.safetensors",
+        "decoder.block.14.layer.1.EncDecAttention.v.weight": "model_00012-of-00015.safetensors",
+        "decoder.block.14.layer.1.layer_norm.weight": "model_00012-of-00015.safetensors",
+        "decoder.block.14.layer.2.DenseReluDense.wi.weight": "model_00012-of-00015.safetensors",
+        "decoder.block.14.layer.2.DenseReluDense.wo.weight": "model_00012-of-00015.safetensors",
+        "decoder.block.14.layer.2.layer_norm.weight": "model_00012-of-00015.safetensors",
+        "decoder.block.15.layer.0.SelfAttention.k.weight": "model_00012-of-00015.safetensors",
+        "decoder.block.15.layer.0.SelfAttention.o.weight": "model_00012-of-00015.safetensors",
+        "decoder.block.15.layer.0.SelfAttention.q.weight": "model_00012-of-00015.safetensors",
+        "decoder.block.15.layer.0.SelfAttention.v.weight": "model_00012-of-00015.safetensors",
+        "decoder.block.15.layer.0.layer_norm.weight": "model_00012-of-00015.safetensors",
+        "decoder.block.15.layer.1.EncDecAttention.k.weight": "model_00012-of-00015.safetensors",
+        "decoder.block.15.layer.1.EncDecAttention.o.weight": "model_00012-of-00015.safetensors",
+        "decoder.block.15.layer.1.EncDecAttention.q.weight": "model_00012-of-00015.safetensors",
+        "decoder.block.15.layer.1.EncDecAttention.v.weight": "model_00012-of-00015.safetensors",
+        "decoder.block.15.layer.1.layer_norm.weight": "model_00012-of-00015.safetensors",
+        "decoder.block.15.layer.2.DenseReluDense.wi.weight": "model_00012-of-00015.safetensors",
+        "decoder.block.15.layer.2.DenseReluDense.wo.weight": "model_00012-of-00015.safetensors",
+        "decoder.block.15.layer.2.layer_norm.weight": "model_00012-of-00015.safetensors",
+        "decoder.block.16.layer.0.SelfAttention.k.weight": "model_00012-of-00015.safetensors",
+        "decoder.block.16.layer.0.SelfAttention.o.weight": "model_00013-of-00015.safetensors",
+        "decoder.block.16.layer.0.SelfAttention.q.weight": "model_00012-of-00015.safetensors",
+        "decoder.block.16.layer.0.SelfAttention.v.weight": "model_00012-of-00015.safetensors",
+        "decoder.block.16.layer.0.layer_norm.weight": "model_00013-of-00015.safetensors",
+        "decoder.block.16.layer.1.EncDecAttention.k.weight": "model_00013-of-00015.safetensors",
+        "decoder.block.16.layer.1.EncDecAttention.o.weight": "model_00013-of-00015.safetensors",
+        "decoder.block.16.layer.1.EncDecAttention.q.weight": "model_00013-of-00015.safetensors",
+        "decoder.block.16.layer.1.EncDecAttention.v.weight": "model_00013-of-00015.safetensors",
+        "decoder.block.16.layer.1.layer_norm.weight": "model_00013-of-00015.safetensors",
+        "decoder.block.16.layer.2.DenseReluDense.wi.weight": "model_00013-of-00015.safetensors",
+        "decoder.block.16.layer.2.DenseReluDense.wo.weight": "model_00013-of-00015.safetensors",
+        "decoder.block.16.layer.2.layer_norm.weight": "model_00013-of-00015.safetensors",
+        "decoder.block.17.layer.0.SelfAttention.k.weight": "model_00013-of-00015.safetensors",
+        "decoder.block.17.layer.0.SelfAttention.o.weight": "model_00013-of-00015.safetensors",
+        "decoder.block.17.layer.0.SelfAttention.q.weight": "model_00013-of-00015.safetensors",
+        "decoder.block.17.layer.0.SelfAttention.v.weight": "model_00013-of-00015.safetensors",
+        "decoder.block.17.layer.0.layer_norm.weight": "model_00013-of-00015.safetensors",
+        "decoder.block.17.layer.1.EncDecAttention.k.weight": "model_00013-of-00015.safetensors",
+        "decoder.block.17.layer.1.EncDecAttention.o.weight": "model_00013-of-00015.safetensors",
+        "decoder.block.17.layer.1.EncDecAttention.q.weight": "model_00013-of-00015.safetensors",
+        "decoder.block.17.layer.1.EncDecAttention.v.weight": "model_00013-of-00015.safetensors",
+        "decoder.block.17.layer.1.layer_norm.weight": "model_00013-of-00015.safetensors",
+        "decoder.block.17.layer.2.DenseReluDense.wi.weight": "model_00013-of-00015.safetensors",
+        "decoder.block.17.layer.2.DenseReluDense.wo.weight": "model_00013-of-00015.safetensors",
+        "decoder.block.17.layer.2.layer_norm.weight": "model_00013-of-00015.safetensors",
+        "decoder.block.18.layer.0.SelfAttention.k.weight": "model_00013-of-00015.safetensors",
+        "decoder.block.18.layer.0.SelfAttention.o.weight": "model_00013-of-00015.safetensors",
+        "decoder.block.18.layer.0.SelfAttention.q.weight": "model_00013-of-00015.safetensors",
+        "decoder.block.18.layer.0.SelfAttention.v.weight": "model_00013-of-00015.safetensors",
+        "decoder.block.18.layer.0.layer_norm.weight": "model_00013-of-00015.safetensors",
+        "decoder.block.18.layer.1.EncDecAttention.k.weight": "model_00013-of-00015.safetensors",
+        "decoder.block.18.layer.1.EncDecAttention.o.weight": "model_00013-of-00015.safetensors",
+        "decoder.block.18.layer.1.EncDecAttention.q.weight": "model_00013-of-00015.safetensors",
+        "decoder.block.18.layer.1.EncDecAttention.v.weight": "model_00013-of-00015.safetensors",
+        "decoder.block.18.layer.1.layer_norm.weight": "model_00013-of-00015.safetensors",
+        "decoder.block.18.layer.2.DenseReluDense.wi.weight": "model_00013-of-00015.safetensors",
+        "decoder.block.18.layer.2.DenseReluDense.wo.weight": "model_00014-of-00015.safetensors",
+        "decoder.block.18.layer.2.layer_norm.weight": "model_00014-of-00015.safetensors",
+        "decoder.block.19.layer.0.SelfAttention.k.weight": "model_00014-of-00015.safetensors",
+        "decoder.block.19.layer.0.SelfAttention.o.weight": "model_00014-of-00015.safetensors",
+        "decoder.block.19.layer.0.SelfAttention.q.weight": "model_00014-of-00015.safetensors",
+        "decoder.block.19.layer.0.SelfAttention.v.weight": "model_00014-of-00015.safetensors",
+        "decoder.block.19.layer.0.layer_norm.weight": "model_00014-of-00015.safetensors",
+        "decoder.block.19.layer.1.EncDecAttention.k.weight": "model_00014-of-00015.safetensors",
+        "decoder.block.19.layer.1.EncDecAttention.o.weight": "model_00014-of-00015.safetensors",
+        "decoder.block.19.layer.1.EncDecAttention.q.weight": "model_00014-of-00015.safetensors",
+        "decoder.block.19.layer.1.EncDecAttention.v.weight": "model_00014-of-00015.safetensors",
+        "decoder.block.19.layer.1.layer_norm.weight": "model_00014-of-00015.safetensors",
+        "decoder.block.19.layer.2.DenseReluDense.wi.weight": "model_00014-of-00015.safetensors",
+        "decoder.block.19.layer.2.DenseReluDense.wo.weight": "model_00014-of-00015.safetensors",
+        "decoder.block.19.layer.2.layer_norm.weight": "model_00014-of-00015.safetensors",
+        "decoder.block.2.layer.0.SelfAttention.k.weight": "model_00007-of-00015.safetensors",
+        "decoder.block.2.layer.0.SelfAttention.o.weight": "model_00007-of-00015.safetensors",
+        "decoder.block.2.layer.0.SelfAttention.q.weight": "model_00007-of-00015.safetensors",
+        "decoder.block.2.layer.0.SelfAttention.v.weight": "model_00007-of-00015.safetensors",
+        "decoder.block.2.layer.0.layer_norm.weight": "model_00007-of-00015.safetensors",
+        "decoder.block.2.layer.1.EncDecAttention.k.weight": "model_00007-of-00015.safetensors",
+        "decoder.block.2.layer.1.EncDecAttention.o.weight": "model_00007-of-00015.safetensors",
+        "decoder.block.2.layer.1.EncDecAttention.q.weight": "model_00007-of-00015.safetensors",
+        "decoder.block.2.layer.1.EncDecAttention.v.weight": "model_00007-of-00015.safetensors",
+        "decoder.block.2.layer.1.layer_norm.weight": "model_00007-of-00015.safetensors",
+        "decoder.block.2.layer.2.DenseReluDense.wi.weight": "model_00007-of-00015.safetensors",
+        "decoder.block.2.layer.2.DenseReluDense.wo.weight": "model_00007-of-00015.safetensors",
+        "decoder.block.2.layer.2.layer_norm.weight": "model_00007-of-00015.safetensors",
+        "decoder.block.20.layer.0.SelfAttention.k.weight": "model_00014-of-00015.safetensors",
+        "decoder.block.20.layer.0.SelfAttention.o.weight": "model_00014-of-00015.safetensors",
+        "decoder.block.20.layer.0.SelfAttention.q.weight": "model_00014-of-00015.safetensors",
+        "decoder.block.20.layer.0.SelfAttention.v.weight": "model_00014-of-00015.safetensors",
+        "decoder.block.20.layer.0.layer_norm.weight": "model_00014-of-00015.safetensors",
+        "decoder.block.20.layer.1.EncDecAttention.k.weight": "model_00014-of-00015.safetensors",
+        "decoder.block.20.layer.1.EncDecAttention.o.weight": "model_00014-of-00015.safetensors",
+        "decoder.block.20.layer.1.EncDecAttention.q.weight": "model_00014-of-00015.safetensors",
+        "decoder.block.20.layer.1.EncDecAttention.v.weight": "model_00014-of-00015.safetensors",
+        "decoder.block.20.layer.1.layer_norm.weight": "model_00014-of-00015.safetensors",
+        "decoder.block.20.layer.2.DenseReluDense.wi.weight": "model_00014-of-00015.safetensors",
+        "decoder.block.20.layer.2.DenseReluDense.wo.weight": "model_00014-of-00015.safetensors",
+        "decoder.block.20.layer.2.layer_norm.weight": "model_00014-of-00015.safetensors",
+        "decoder.block.21.layer.0.SelfAttention.k.weight": "model_00014-of-00015.safetensors",
+        "decoder.block.21.layer.0.SelfAttention.o.weight": "model_00014-of-00015.safetensors",
+        "decoder.block.21.layer.0.SelfAttention.q.weight": "model_00014-of-00015.safetensors",
+        "decoder.block.21.layer.0.SelfAttention.v.weight": "model_00014-of-00015.safetensors",
+        "decoder.block.21.layer.0.layer_norm.weight": "model_00014-of-00015.safetensors",
+        "decoder.block.21.layer.1.EncDecAttention.k.weight": "model_00015-of-00015.safetensors",
+        "decoder.block.21.layer.1.EncDecAttention.o.weight": "model_00015-of-00015.safetensors",
+        "decoder.block.21.layer.1.EncDecAttention.q.weight": "model_00014-of-00015.safetensors",
+        "decoder.block.21.layer.1.EncDecAttention.v.weight": "model_00015-of-00015.safetensors",
+        "decoder.block.21.layer.1.layer_norm.weight": "model_00015-of-00015.safetensors",
+        "decoder.block.21.layer.2.DenseReluDense.wi.weight": "model_00015-of-00015.safetensors",
+        "decoder.block.21.layer.2.DenseReluDense.wo.weight": "model_00015-of-00015.safetensors",
+        "decoder.block.21.layer.2.layer_norm.weight": "model_00015-of-00015.safetensors",
+        "decoder.block.22.layer.0.SelfAttention.k.weight": "model_00015-of-00015.safetensors",
+        "decoder.block.22.layer.0.SelfAttention.o.weight": "model_00015-of-00015.safetensors",
+        "decoder.block.22.layer.0.SelfAttention.q.weight": "model_00015-of-00015.safetensors",
+        "decoder.block.22.layer.0.SelfAttention.v.weight": "model_00015-of-00015.safetensors",
+        "decoder.block.22.layer.0.layer_norm.weight": "model_00015-of-00015.safetensors",
+        "decoder.block.22.layer.1.EncDecAttention.k.weight": "model_00015-of-00015.safetensors",
+        "decoder.block.22.layer.1.EncDecAttention.o.weight": "model_00015-of-00015.safetensors",
+        "decoder.block.22.layer.1.EncDecAttention.q.weight": "model_00015-of-00015.safetensors",
+        "decoder.block.22.layer.1.EncDecAttention.v.weight": "model_00015-of-00015.safetensors",
+        "decoder.block.22.layer.1.layer_norm.weight": "model_00015-of-00015.safetensors",
+        "decoder.block.22.layer.2.DenseReluDense.wi.weight": "model_00015-of-00015.safetensors",
+        "decoder.block.22.layer.2.DenseReluDense.wo.weight": "model_00015-of-00015.safetensors",
+        "decoder.block.22.layer.2.layer_norm.weight": "model_00015-of-00015.safetensors",
+        "decoder.block.23.layer.0.SelfAttention.k.weight": "model_00015-of-00015.safetensors",
+        "decoder.block.23.layer.0.SelfAttention.o.weight": "model_00015-of-00015.safetensors",
+        "decoder.block.23.layer.0.SelfAttention.q.weight": "model_00015-of-00015.safetensors",
+        "decoder.block.23.layer.0.SelfAttention.v.weight": "model_00015-of-00015.safetensors",
+        "decoder.block.23.layer.0.layer_norm.weight": "model_00015-of-00015.safetensors",
+        "decoder.block.23.layer.1.EncDecAttention.k.weight": "model_00015-of-00015.safetensors",
+        "decoder.block.23.layer.1.EncDecAttention.o.weight": "model_00015-of-00015.safetensors",
+        "decoder.block.23.layer.1.EncDecAttention.q.weight": "model_00015-of-00015.safetensors",
+        "decoder.block.23.layer.1.EncDecAttention.v.weight": "model_00015-of-00015.safetensors",
+        "decoder.block.23.layer.1.layer_norm.weight": "model_00015-of-00015.safetensors",
+        "decoder.block.23.layer.2.DenseReluDense.wi.weight": "model_00015-of-00015.safetensors",
+        "decoder.block.23.layer.2.DenseReluDense.wo.weight": "model_00015-of-00015.safetensors",
+        "decoder.block.23.layer.2.layer_norm.weight": "model_00015-of-00015.safetensors",
+        "decoder.block.3.layer.0.SelfAttention.k.weight": "model_00007-of-00015.safetensors",
+        "decoder.block.3.layer.0.SelfAttention.o.weight": "model_00008-of-00015.safetensors",
+        "decoder.block.3.layer.0.SelfAttention.q.weight": "model_00007-of-00015.safetensors",
+        "decoder.block.3.layer.0.SelfAttention.v.weight": "model_00008-of-00015.safetensors",
+        "decoder.block.3.layer.0.layer_norm.weight": "model_00008-of-00015.safetensors",
+        "decoder.block.3.layer.1.EncDecAttention.k.weight": "model_00008-of-00015.safetensors",
+        "decoder.block.3.layer.1.EncDecAttention.o.weight": "model_00008-of-00015.safetensors",
+        "decoder.block.3.layer.1.EncDecAttention.q.weight": "model_00008-of-00015.safetensors",
+        "decoder.block.3.layer.1.EncDecAttention.v.weight": "model_00008-of-00015.safetensors",
+        "decoder.block.3.layer.1.layer_norm.weight": "model_00008-of-00015.safetensors",
+        "decoder.block.3.layer.2.DenseReluDense.wi.weight": "model_00008-of-00015.safetensors",
+        "decoder.block.3.layer.2.DenseReluDense.wo.weight": "model_00008-of-00015.safetensors",
+        "decoder.block.3.layer.2.layer_norm.weight": "model_00008-of-00015.safetensors",
+        "decoder.block.4.layer.0.SelfAttention.k.weight": "model_00008-of-00015.safetensors",
+        "decoder.block.4.layer.0.SelfAttention.o.weight": "model_00008-of-00015.safetensors",
+        "decoder.block.4.layer.0.SelfAttention.q.weight": "model_00008-of-00015.safetensors",
+        "decoder.block.4.layer.0.SelfAttention.v.weight": "model_00008-of-00015.safetensors",
+        "decoder.block.4.layer.0.layer_norm.weight": "model_00008-of-00015.safetensors",
+        "decoder.block.4.layer.1.EncDecAttention.k.weight": "model_00008-of-00015.safetensors",
+        "decoder.block.4.layer.1.EncDecAttention.o.weight": "model_00008-of-00015.safetensors",
+        "decoder.block.4.layer.1.EncDecAttention.q.weight": "model_00008-of-00015.safetensors",
+        "decoder.block.4.layer.1.EncDecAttention.v.weight": "model_00008-of-00015.safetensors",
+        "decoder.block.4.layer.1.layer_norm.weight": "model_00008-of-00015.safetensors",
+        "decoder.block.4.layer.2.DenseReluDense.wi.weight": "model_00008-of-00015.safetensors",
+        "decoder.block.4.layer.2.DenseReluDense.wo.weight": "model_00008-of-00015.safetensors",
+        "decoder.block.4.layer.2.layer_norm.weight": "model_00008-of-00015.safetensors",
+        "decoder.block.5.layer.0.SelfAttention.k.weight": "model_00008-of-00015.safetensors",
+        "decoder.block.5.layer.0.SelfAttention.o.weight": "model_00008-of-00015.safetensors",
+        "decoder.block.5.layer.0.SelfAttention.q.weight": "model_00008-of-00015.safetensors",
+        "decoder.block.5.layer.0.SelfAttention.v.weight": "model_00008-of-00015.safetensors",
+        "decoder.block.5.layer.0.layer_norm.weight": "model_00008-of-00015.safetensors",
+        "decoder.block.5.layer.1.EncDecAttention.k.weight": "model_00008-of-00015.safetensors",
+        "decoder.block.5.layer.1.EncDecAttention.o.weight": "model_00008-of-00015.safetensors",
+        "decoder.block.5.layer.1.EncDecAttention.q.weight": "model_00008-of-00015.safetensors",
+        "decoder.block.5.layer.1.EncDecAttention.v.weight": "model_00008-of-00015.safetensors",
+        "decoder.block.5.layer.1.layer_norm.weight": "model_00008-of-00015.safetensors",
+        "decoder.block.5.layer.2.DenseReluDense.wi.weight": "model_00009-of-00015.safetensors",
+        "decoder.block.5.layer.2.DenseReluDense.wo.weight": "model_00009-of-00015.safetensors",
+        "decoder.block.5.layer.2.layer_norm.weight": "model_00009-of-00015.safetensors",
+        "decoder.block.6.layer.0.SelfAttention.k.weight": "model_00009-of-00015.safetensors",
+        "decoder.block.6.layer.0.SelfAttention.o.weight": "model_00009-of-00015.safetensors",
+        "decoder.block.6.layer.0.SelfAttention.q.weight": "model_00009-of-00015.safetensors",
+        "decoder.block.6.layer.0.SelfAttention.v.weight": "model_00009-of-00015.safetensors",
+        "decoder.block.6.layer.0.layer_norm.weight": "model_00009-of-00015.safetensors",
+        "decoder.block.6.layer.1.EncDecAttention.k.weight": "model_00009-of-00015.safetensors",
+        "decoder.block.6.layer.1.EncDecAttention.o.weight": "model_00009-of-00015.safetensors",
+        "decoder.block.6.layer.1.EncDecAttention.q.weight": "model_00009-of-00015.safetensors",
+        "decoder.block.6.layer.1.EncDecAttention.v.weight": "model_00009-of-00015.safetensors",
+        "decoder.block.6.layer.1.layer_norm.weight": "model_00009-of-00015.safetensors",
+        "decoder.block.6.layer.2.DenseReluDense.wi.weight": "model_00009-of-00015.safetensors",
+        "decoder.block.6.layer.2.DenseReluDense.wo.weight": "model_00009-of-00015.safetensors",
+        "decoder.block.6.layer.2.layer_norm.weight": "model_00009-of-00015.safetensors",
+        "decoder.block.7.layer.0.SelfAttention.k.weight": "model_00009-of-00015.safetensors",
+        "decoder.block.7.layer.0.SelfAttention.o.weight": "model_00009-of-00015.safetensors",
+        "decoder.block.7.layer.0.SelfAttention.q.weight": "model_00009-of-00015.safetensors",
+        "decoder.block.7.layer.0.SelfAttention.v.weight": "model_00009-of-00015.safetensors",
+        "decoder.block.7.layer.0.layer_norm.weight": "model_00009-of-00015.safetensors",
+        "decoder.block.7.layer.1.EncDecAttention.k.weight": "model_00009-of-00015.safetensors",
+        "decoder.block.7.layer.1.EncDecAttention.o.weight": "model_00009-of-00015.safetensors",
+        "decoder.block.7.layer.1.EncDecAttention.q.weight": "model_00009-of-00015.safetensors",
+        "decoder.block.7.layer.1.EncDecAttention.v.weight": "model_00009-of-00015.safetensors",
+        "decoder.block.7.layer.1.layer_norm.weight": "model_00009-of-00015.safetensors",
+        "decoder.block.7.layer.2.DenseReluDense.wi.weight": "model_00009-of-00015.safetensors",
+        "decoder.block.7.layer.2.DenseReluDense.wo.weight": "model_00009-of-00015.safetensors",
+        "decoder.block.7.layer.2.layer_norm.weight": "model_00009-of-00015.safetensors",
+        "decoder.block.8.layer.0.SelfAttention.k.weight": "model_00009-of-00015.safetensors",
+        "decoder.block.8.layer.0.SelfAttention.o.weight": "model_00009-of-00015.safetensors",
+        "decoder.block.8.layer.0.SelfAttention.q.weight": "model_00009-of-00015.safetensors",
+        "decoder.block.8.layer.0.SelfAttention.v.weight": "model_00009-of-00015.safetensors",
+        "decoder.block.8.layer.0.layer_norm.weight": "model_00009-of-00015.safetensors",
+        "decoder.block.8.layer.1.EncDecAttention.k.weight": "model_00010-of-00015.safetensors",
+        "decoder.block.8.layer.1.EncDecAttention.o.weight": "model_00010-of-00015.safetensors",
+        "decoder.block.8.layer.1.EncDecAttention.q.weight": "model_00010-of-00015.safetensors",
+        "decoder.block.8.layer.1.EncDecAttention.v.weight": "model_00010-of-00015.safetensors",
+        "decoder.block.8.layer.1.layer_norm.weight": "model_00010-of-00015.safetensors",
+        "decoder.block.8.layer.2.DenseReluDense.wi.weight": "model_00010-of-00015.safetensors",
+        "decoder.block.8.layer.2.DenseReluDense.wo.weight": "model_00010-of-00015.safetensors",
+        "decoder.block.8.layer.2.layer_norm.weight": "model_00010-of-00015.safetensors",
+        "decoder.block.9.layer.0.SelfAttention.k.weight": "model_00010-of-00015.safetensors",
+        "decoder.block.9.layer.0.SelfAttention.o.weight": "model_00010-of-00015.safetensors",
+        "decoder.block.9.layer.0.SelfAttention.q.weight": "model_00010-of-00015.safetensors",
+        "decoder.block.9.layer.0.SelfAttention.v.weight": "model_00010-of-00015.safetensors",
+        "decoder.block.9.layer.0.layer_norm.weight": "model_00010-of-00015.safetensors",
+        "decoder.block.9.layer.1.EncDecAttention.k.weight": "model_00010-of-00015.safetensors",
+        "decoder.block.9.layer.1.EncDecAttention.o.weight": "model_00010-of-00015.safetensors",
+        "decoder.block.9.layer.1.EncDecAttention.q.weight": "model_00010-of-00015.safetensors",
+        "decoder.block.9.layer.1.EncDecAttention.v.weight": "model_00010-of-00015.safetensors",
+        "decoder.block.9.layer.1.layer_norm.weight": "model_00010-of-00015.safetensors",
+        "decoder.block.9.layer.2.DenseReluDense.wi.weight": "model_00010-of-00015.safetensors",
+        "decoder.block.9.layer.2.DenseReluDense.wo.weight": "model_00010-of-00015.safetensors",
+        "decoder.block.9.layer.2.layer_norm.weight": "model_00010-of-00015.safetensors",
+        "decoder.final_layer_norm.weight": "model_00015-of-00015.safetensors",
+        "encoder.block.0.layer.0.SelfAttention.k.weight": "model_00001-of-00015.safetensors",
+        "encoder.block.0.layer.0.SelfAttention.o.weight": "model_00001-of-00015.safetensors",
+        "encoder.block.0.layer.0.SelfAttention.q.weight": "model_00001-of-00015.safetensors",
+        "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model_00001-of-00015.safetensors",
+        "encoder.block.0.layer.0.SelfAttention.v.weight": "model_00001-of-00015.safetensors",
+        "encoder.block.0.layer.0.layer_norm.weight": "model_00001-of-00015.safetensors",
+        "encoder.block.0.layer.1.DenseReluDense.wi.weight": "model_00001-of-00015.safetensors",
+        "encoder.block.0.layer.1.DenseReluDense.wo.weight": "model_00001-of-00015.safetensors",
+        "encoder.block.0.layer.1.layer_norm.weight": "model_00001-of-00015.safetensors",
+        "encoder.block.1.layer.0.SelfAttention.k.weight": "model_00001-of-00015.safetensors",
+        "encoder.block.1.layer.0.SelfAttention.o.weight": "model_00001-of-00015.safetensors",
+        "encoder.block.1.layer.0.SelfAttention.q.weight": "model_00001-of-00015.safetensors",
+        "encoder.block.1.layer.0.SelfAttention.v.weight": "model_00001-of-00015.safetensors",
+        "encoder.block.1.layer.0.layer_norm.weight": "model_00001-of-00015.safetensors",
+        "encoder.block.1.layer.1.DenseReluDense.wi.weight": "model_00001-of-00015.safetensors",
+        "encoder.block.1.layer.1.DenseReluDense.wo.weight": "model_00001-of-00015.safetensors",
+        "encoder.block.1.layer.1.layer_norm.weight": "model_00001-of-00015.safetensors",
+        "encoder.block.10.layer.0.SelfAttention.k.weight": "model_00003-of-00015.safetensors",
+        "encoder.block.10.layer.0.SelfAttention.o.weight": "model_00003-of-00015.safetensors",
+        "encoder.block.10.layer.0.SelfAttention.q.weight": "model_00003-of-00015.safetensors",
+        "encoder.block.10.layer.0.SelfAttention.v.weight": "model_00003-of-00015.safetensors",
+        "encoder.block.10.layer.0.layer_norm.weight": "model_00003-of-00015.safetensors",
+        "encoder.block.10.layer.1.DenseReluDense.wi.weight": "model_00003-of-00015.safetensors",
+        "encoder.block.10.layer.1.DenseReluDense.wo.weight": "model_00003-of-00015.safetensors",
+        "encoder.block.10.layer.1.layer_norm.weight": "model_00003-of-00015.safetensors",
+        "encoder.block.11.layer.0.SelfAttention.k.weight": "model_00003-of-00015.safetensors",
+        "encoder.block.11.layer.0.SelfAttention.o.weight": "model_00003-of-00015.safetensors",
+        "encoder.block.11.layer.0.SelfAttention.q.weight": "model_00003-of-00015.safetensors",
+        "encoder.block.11.layer.0.SelfAttention.v.weight": "model_00003-of-00015.safetensors",
+        "encoder.block.11.layer.0.layer_norm.weight": "model_00003-of-00015.safetensors",
+        "encoder.block.11.layer.1.DenseReluDense.wi.weight": "model_00003-of-00015.safetensors",
+        "encoder.block.11.layer.1.DenseReluDense.wo.weight": "model_00003-of-00015.safetensors",
+        "encoder.block.11.layer.1.layer_norm.weight": "model_00003-of-00015.safetensors",
+        "encoder.block.12.layer.0.SelfAttention.k.weight": "model_00003-of-00015.safetensors",
+        "encoder.block.12.layer.0.SelfAttention.o.weight": "model_00003-of-00015.safetensors",
+        "encoder.block.12.layer.0.SelfAttention.q.weight": "model_00003-of-00015.safetensors",
+        "encoder.block.12.layer.0.SelfAttention.v.weight": "model_00003-of-00015.safetensors",
+        "encoder.block.12.layer.0.layer_norm.weight": "model_00004-of-00015.safetensors",
+        "encoder.block.12.layer.1.DenseReluDense.wi.weight": "model_00004-of-00015.safetensors",
+        "encoder.block.12.layer.1.DenseReluDense.wo.weight": "model_00004-of-00015.safetensors",
+        "encoder.block.12.layer.1.layer_norm.weight": "model_00004-of-00015.safetensors",
+        "encoder.block.13.layer.0.SelfAttention.k.weight": "model_00004-of-00015.safetensors",
+        "encoder.block.13.layer.0.SelfAttention.o.weight": "model_00004-of-00015.safetensors",
+        "encoder.block.13.layer.0.SelfAttention.q.weight": "model_00004-of-00015.safetensors",
+        "encoder.block.13.layer.0.SelfAttention.v.weight": "model_00004-of-00015.safetensors",
+        "encoder.block.13.layer.0.layer_norm.weight": "model_00004-of-00015.safetensors",
+        "encoder.block.13.layer.1.DenseReluDense.wi.weight": "model_00004-of-00015.safetensors",
+        "encoder.block.13.layer.1.DenseReluDense.wo.weight": "model_00004-of-00015.safetensors",
+        "encoder.block.13.layer.1.layer_norm.weight": "model_00004-of-00015.safetensors",
+        "encoder.block.14.layer.0.SelfAttention.k.weight": "model_00004-of-00015.safetensors",
+        "encoder.block.14.layer.0.SelfAttention.o.weight": "model_00004-of-00015.safetensors",
+        "encoder.block.14.layer.0.SelfAttention.q.weight": "model_00004-of-00015.safetensors",
+        "encoder.block.14.layer.0.SelfAttention.v.weight": "model_00004-of-00015.safetensors",
+        "encoder.block.14.layer.0.layer_norm.weight": "model_00004-of-00015.safetensors",
+        "encoder.block.14.layer.1.DenseReluDense.wi.weight": "model_00004-of-00015.safetensors",
+        "encoder.block.14.layer.1.DenseReluDense.wo.weight": "model_00004-of-00015.safetensors",
+        "encoder.block.14.layer.1.layer_norm.weight": "model_00004-of-00015.safetensors",
+        "encoder.block.15.layer.0.SelfAttention.k.weight": "model_00004-of-00015.safetensors",
+        "encoder.block.15.layer.0.SelfAttention.o.weight": "model_00004-of-00015.safetensors",
+        "encoder.block.15.layer.0.SelfAttention.q.weight": "model_00004-of-00015.safetensors",
+        "encoder.block.15.layer.0.SelfAttention.v.weight": "model_00004-of-00015.safetensors",
+        "encoder.block.15.layer.0.layer_norm.weight": "model_00004-of-00015.safetensors",
+        "encoder.block.15.layer.1.DenseReluDense.wi.weight": "model_00004-of-00015.safetensors",
+        "encoder.block.15.layer.1.DenseReluDense.wo.weight": "model_00004-of-00015.safetensors",
+        "encoder.block.15.layer.1.layer_norm.weight": "model_00004-of-00015.safetensors",
+        "encoder.block.16.layer.0.SelfAttention.k.weight": "model_00004-of-00015.safetensors",
+        "encoder.block.16.layer.0.SelfAttention.o.weight": "model_00004-of-00015.safetensors",
+        "encoder.block.16.layer.0.SelfAttention.q.weight": "model_00004-of-00015.safetensors",
+        "encoder.block.16.layer.0.SelfAttention.v.weight": "model_00004-of-00015.safetensors",
+        "encoder.block.16.layer.0.layer_norm.weight": "model_00004-of-00015.safetensors",
+        "encoder.block.16.layer.1.DenseReluDense.wi.weight": "model_00004-of-00015.safetensors",
+        "encoder.block.16.layer.1.DenseReluDense.wo.weight": "model_00005-of-00015.safetensors",
+        "encoder.block.16.layer.1.layer_norm.weight": "model_00005-of-00015.safetensors",
+        "encoder.block.17.layer.0.SelfAttention.k.weight": "model_00005-of-00015.safetensors",
+        "encoder.block.17.layer.0.SelfAttention.o.weight": "model_00005-of-00015.safetensors",
+        "encoder.block.17.layer.0.SelfAttention.q.weight": "model_00005-of-00015.safetensors",
+        "encoder.block.17.layer.0.SelfAttention.v.weight": "model_00005-of-00015.safetensors",
+        "encoder.block.17.layer.0.layer_norm.weight": "model_00005-of-00015.safetensors",
+        "encoder.block.17.layer.1.DenseReluDense.wi.weight": "model_00005-of-00015.safetensors",
+        "encoder.block.17.layer.1.DenseReluDense.wo.weight": "model_00005-of-00015.safetensors",
+        "encoder.block.17.layer.1.layer_norm.weight": "model_00005-of-00015.safetensors",
+        "encoder.block.18.layer.0.SelfAttention.k.weight": "model_00005-of-00015.safetensors",
+        "encoder.block.18.layer.0.SelfAttention.o.weight": "model_00005-of-00015.safetensors",
+        "encoder.block.18.layer.0.SelfAttention.q.weight": "model_00005-of-00015.safetensors",
+        "encoder.block.18.layer.0.SelfAttention.v.weight": "model_00005-of-00015.safetensors",
+        "encoder.block.18.layer.0.layer_norm.weight": "model_00005-of-00015.safetensors",
+        "encoder.block.18.layer.1.DenseReluDense.wi.weight": "model_00005-of-00015.safetensors",
+        "encoder.block.18.layer.1.DenseReluDense.wo.weight": "model_00005-of-00015.safetensors",
+        "encoder.block.18.layer.1.layer_norm.weight": "model_00005-of-00015.safetensors",
+        "encoder.block.19.layer.0.SelfAttention.k.weight": "model_00005-of-00015.safetensors",
+        "encoder.block.19.layer.0.SelfAttention.o.weight": "model_00005-of-00015.safetensors",
+        "encoder.block.19.layer.0.SelfAttention.q.weight": "model_00005-of-00015.safetensors",
+        "encoder.block.19.layer.0.SelfAttention.v.weight": "model_00005-of-00015.safetensors",
+        "encoder.block.19.layer.0.layer_norm.weight": "model_00005-of-00015.safetensors",
+        "encoder.block.19.layer.1.DenseReluDense.wi.weight": "model_00005-of-00015.safetensors",
+        "encoder.block.19.layer.1.DenseReluDense.wo.weight": "model_00005-of-00015.safetensors",
+        "encoder.block.19.layer.1.layer_norm.weight": "model_00005-of-00015.safetensors",
+        "encoder.block.2.layer.0.SelfAttention.k.weight": "model_00001-of-00015.safetensors",
+        "encoder.block.2.layer.0.SelfAttention.o.weight": "model_00001-of-00015.safetensors",
+        "encoder.block.2.layer.0.SelfAttention.q.weight": "model_00001-of-00015.safetensors",
+        "encoder.block.2.layer.0.SelfAttention.v.weight": "model_00001-of-00015.safetensors",
+        "encoder.block.2.layer.0.layer_norm.weight": "model_00001-of-00015.safetensors",
+        "encoder.block.2.layer.1.DenseReluDense.wi.weight": "model_00001-of-00015.safetensors",
+        "encoder.block.2.layer.1.DenseReluDense.wo.weight": "model_00001-of-00015.safetensors",
+        "encoder.block.2.layer.1.layer_norm.weight": "model_00001-of-00015.safetensors",
+        "encoder.block.20.layer.0.SelfAttention.k.weight": "model_00005-of-00015.safetensors",
+        "encoder.block.20.layer.0.SelfAttention.o.weight": "model_00005-of-00015.safetensors",
+        "encoder.block.20.layer.0.SelfAttention.q.weight": "model_00005-of-00015.safetensors",
+        "encoder.block.20.layer.0.SelfAttention.v.weight": "model_00005-of-00015.safetensors",
+        "encoder.block.20.layer.0.layer_norm.weight": "model_00005-of-00015.safetensors",
+        "encoder.block.20.layer.1.DenseReluDense.wi.weight": "model_00005-of-00015.safetensors",
+        "encoder.block.20.layer.1.DenseReluDense.wo.weight": "model_00005-of-00015.safetensors",
+        "encoder.block.20.layer.1.layer_norm.weight": "model_00005-of-00015.safetensors",
+        "encoder.block.21.layer.0.SelfAttention.k.weight": "model_00006-of-00015.safetensors",
+        "encoder.block.21.layer.0.SelfAttention.o.weight": "model_00006-of-00015.safetensors",
+        "encoder.block.21.layer.0.SelfAttention.q.weight": "model_00006-of-00015.safetensors",
+        "encoder.block.21.layer.0.SelfAttention.v.weight": "model_00006-of-00015.safetensors",
+        "encoder.block.21.layer.0.layer_norm.weight": "model_00006-of-00015.safetensors",
+        "encoder.block.21.layer.1.DenseReluDense.wi.weight": "model_00006-of-00015.safetensors",
+        "encoder.block.21.layer.1.DenseReluDense.wo.weight": "model_00006-of-00015.safetensors",
+        "encoder.block.21.layer.1.layer_norm.weight": "model_00006-of-00015.safetensors",
+        "encoder.block.22.layer.0.SelfAttention.k.weight": "model_00006-of-00015.safetensors",
+        "encoder.block.22.layer.0.SelfAttention.o.weight": "model_00006-of-00015.safetensors",
+        "encoder.block.22.layer.0.SelfAttention.q.weight": "model_00006-of-00015.safetensors",
+        "encoder.block.22.layer.0.SelfAttention.v.weight": "model_00006-of-00015.safetensors",
+        "encoder.block.22.layer.0.layer_norm.weight": "model_00006-of-00015.safetensors",
+        "encoder.block.22.layer.1.DenseReluDense.wi.weight": "model_00006-of-00015.safetensors",
+        "encoder.block.22.layer.1.DenseReluDense.wo.weight": "model_00006-of-00015.safetensors",
+        "encoder.block.22.layer.1.layer_norm.weight": "model_00006-of-00015.safetensors",
+        "encoder.block.23.layer.0.SelfAttention.k.weight": "model_00006-of-00015.safetensors",
+        "encoder.block.23.layer.0.SelfAttention.o.weight": "model_00006-of-00015.safetensors",
+        "encoder.block.23.layer.0.SelfAttention.q.weight": "model_00006-of-00015.safetensors",
+        "encoder.block.23.layer.0.SelfAttention.v.weight": "model_00006-of-00015.safetensors",
+        "encoder.block.23.layer.0.layer_norm.weight": "model_00006-of-00015.safetensors",
+        "encoder.block.23.layer.1.DenseReluDense.wi.weight": "model_00006-of-00015.safetensors",
+        "encoder.block.23.layer.1.DenseReluDense.wo.weight": "model_00006-of-00015.safetensors",
+        "encoder.block.23.layer.1.layer_norm.weight": "model_00006-of-00015.safetensors",
+        "encoder.block.3.layer.0.SelfAttention.k.weight": "model_00001-of-00015.safetensors",
+        "encoder.block.3.layer.0.SelfAttention.o.weight": "model_00001-of-00015.safetensors",
+        "encoder.block.3.layer.0.SelfAttention.q.weight": "model_00001-of-00015.safetensors",
+        "encoder.block.3.layer.0.SelfAttention.v.weight": "model_00001-of-00015.safetensors",
+        "encoder.block.3.layer.0.layer_norm.weight": "model_00001-of-00015.safetensors",
+        "encoder.block.3.layer.1.DenseReluDense.wi.weight": "model_00001-of-00015.safetensors",
+        "encoder.block.3.layer.1.DenseReluDense.wo.weight": "model_00001-of-00015.safetensors",
+        "encoder.block.3.layer.1.layer_norm.weight": "model_00001-of-00015.safetensors",
+        "encoder.block.4.layer.0.SelfAttention.k.weight": "model_00002-of-00015.safetensors",
+        "encoder.block.4.layer.0.SelfAttention.o.weight": "model_00002-of-00015.safetensors",
+        "encoder.block.4.layer.0.SelfAttention.q.weight": "model_00002-of-00015.safetensors",
+        "encoder.block.4.layer.0.SelfAttention.v.weight": "model_00002-of-00015.safetensors",
+        "encoder.block.4.layer.0.layer_norm.weight": "model_00002-of-00015.safetensors",
+        "encoder.block.4.layer.1.DenseReluDense.wi.weight": "model_00002-of-00015.safetensors",
+        "encoder.block.4.layer.1.DenseReluDense.wo.weight": "model_00002-of-00015.safetensors",
+        "encoder.block.4.layer.1.layer_norm.weight": "model_00002-of-00015.safetensors",
+        "encoder.block.5.layer.0.SelfAttention.k.weight": "model_00002-of-00015.safetensors",
+        "encoder.block.5.layer.0.SelfAttention.o.weight": "model_00002-of-00015.safetensors",
+        "encoder.block.5.layer.0.SelfAttention.q.weight": "model_00002-of-00015.safetensors",
+        "encoder.block.5.layer.0.SelfAttention.v.weight": "model_00002-of-00015.safetensors",
+        "encoder.block.5.layer.0.layer_norm.weight": "model_00002-of-00015.safetensors",
+        "encoder.block.5.layer.1.DenseReluDense.wi.weight": "model_00002-of-00015.safetensors",
+        "encoder.block.5.layer.1.DenseReluDense.wo.weight": "model_00002-of-00015.safetensors",
+        "encoder.block.5.layer.1.layer_norm.weight": "model_00002-of-00015.safetensors",
+        "encoder.block.6.layer.0.SelfAttention.k.weight": "model_00002-of-00015.safetensors",
+        "encoder.block.6.layer.0.SelfAttention.o.weight": "model_00002-of-00015.safetensors",
+        "encoder.block.6.layer.0.SelfAttention.q.weight": "model_00002-of-00015.safetensors",
+        "encoder.block.6.layer.0.SelfAttention.v.weight": "model_00002-of-00015.safetensors",
+        "encoder.block.6.layer.0.layer_norm.weight": "model_00002-of-00015.safetensors",
+        "encoder.block.6.layer.1.DenseReluDense.wi.weight": "model_00002-of-00015.safetensors",
+        "encoder.block.6.layer.1.DenseReluDense.wo.weight": "model_00002-of-00015.safetensors",
+        "encoder.block.6.layer.1.layer_norm.weight": "model_00002-of-00015.safetensors",
+        "encoder.block.7.layer.0.SelfAttention.k.weight": "model_00002-of-00015.safetensors",
+        "encoder.block.7.layer.0.SelfAttention.o.weight": "model_00002-of-00015.safetensors",
+        "encoder.block.7.layer.0.SelfAttention.q.weight": "model_00002-of-00015.safetensors",
+        "encoder.block.7.layer.0.SelfAttention.v.weight": "model_00002-of-00015.safetensors",
+        "encoder.block.7.layer.0.layer_norm.weight": "model_00002-of-00015.safetensors",
+        "encoder.block.7.layer.1.DenseReluDense.wi.weight": "model_00002-of-00015.safetensors",
+        "encoder.block.7.layer.1.DenseReluDense.wo.weight": "model_00002-of-00015.safetensors",
+        "encoder.block.7.layer.1.layer_norm.weight": "model_00002-of-00015.safetensors",
+        "encoder.block.8.layer.0.SelfAttention.k.weight": "model_00002-of-00015.safetensors",
+        "encoder.block.8.layer.0.SelfAttention.o.weight": "model_00003-of-00015.safetensors",
+        "encoder.block.8.layer.0.SelfAttention.q.weight": "model_00002-of-00015.safetensors",
+        "encoder.block.8.layer.0.SelfAttention.v.weight": "model_00003-of-00015.safetensors",
+        "encoder.block.8.layer.0.layer_norm.weight": "model_00003-of-00015.safetensors",
+        "encoder.block.8.layer.1.DenseReluDense.wi.weight": "model_00003-of-00015.safetensors",
+        "encoder.block.8.layer.1.DenseReluDense.wo.weight": "model_00003-of-00015.safetensors",
+        "encoder.block.8.layer.1.layer_norm.weight": "model_00003-of-00015.safetensors",
+        "encoder.block.9.layer.0.SelfAttention.k.weight": "model_00003-of-00015.safetensors",
+        "encoder.block.9.layer.0.SelfAttention.o.weight": "model_00003-of-00015.safetensors",
+        "encoder.block.9.layer.0.SelfAttention.q.weight": "model_00003-of-00015.safetensors",
+        "encoder.block.9.layer.0.SelfAttention.v.weight": "model_00003-of-00015.safetensors",
+        "encoder.block.9.layer.0.layer_norm.weight": "model_00003-of-00015.safetensors",
+        "encoder.block.9.layer.1.DenseReluDense.wi.weight": "model_00003-of-00015.safetensors",
+        "encoder.block.9.layer.1.DenseReluDense.wo.weight": "model_00003-of-00015.safetensors",
+        "encoder.block.9.layer.1.layer_norm.weight": "model_00003-of-00015.safetensors",
+        "encoder.final_layer_norm.weight": "model_00006-of-00015.safetensors",
+        "shared.weight": "model_00001-of-00015.safetensors"
+    }
+}

model_00001-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:857a34ca059344bd2d8ae6e9fa653a92ab57497e28e0bb59515027547bd77680
+size 1676439608

model_00002-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:227618f0cf9201716a4acd27ba436b6c570d0f31ee795675efc0d79ebcb5e87c
+size 1677742152

model_00003-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a46404bcb4e3d89527c294725ab6e4db2af1a70e020efa63084f08331404edd
+size 1677742168

model_00004-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb430264f49da120b6674a086f5fed4622dfddbe73ce718b3b012c95731a7aad
+size 1744853088

model_00005-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdb1c37542aeaee8c7fb2c39b5a4dbb4d1916e4a9e17aa0780df6d4726ab0147
+size 1744853096

model_00006-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be187f53454d3d0147160e6cc03ef52dd980d9fe07fcad7ec19216eb058a1897
+size 1442869352

model_00007-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:863a77de9e9e53443db12d226161da004a3de3f4811703cda163cf374814ce8f
+size 1442869344

model_00008-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7eb92ce0bc66e1ed0acceb36315c8cd548124d223eef1f1812b77d69498ede72
+size 1275088976

model_00009-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67ddc67b3c4b0cbbeb19fcd241b29ebd07d1f6f91655807194540681ecc6c27b
+size 1476415576

model_00010-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf4ea03c66086dfb73d2af7837f99eb88ce965641f2babf2dc6e7cfe85717e41
+size 1476415592

model_00011-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faeeeffab64337afe828bbfeb1d0cdf0ec2d55a96867e1fbd690018566a986ee
+size 1308641400

model_00012-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96c55c246d7154b2c7892dc80a73b1f78132d4b1b75b25f93afe8a9cf54e058c
+size 1476415600

model_00013-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaf6eded3561240b939b64274ea14af8aa94339b884e3137ed7cd0c2c9ba50a4
+size 1375752312

model_00014-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7acdb021a4279b3b09efcc22e7b4479d292376fe10febd17aca6d2f538a7fe1
+size 1375752304

model_00015-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1abbaeffb942b183db4093af2b88d6bee9f142ac7ecec1820bb3969c27294519
+size 1442863200