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-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63697d628ab244650e33e6a340d5cd6f83a28685897d8f4da864ecfe1079d787
+size 4726137816

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:284ad95e07c55919a6684f494c7b11b14bb77b8e4021b12be4ec499fb70c9571
+size 4798510760

model.safetensors.index.json

@@ -0,0 +1,227 @@
+{
+    "metadata": {
+        "total_size": 9787813888
+    },
+    "weight_map": {
+        "encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.10.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.10.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.10.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.10.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.10.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.10.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.11.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.11.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.11.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.11.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.11.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.11.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.12.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.12.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.12.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.12.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.12.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.12.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.13.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.13.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.13.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.13.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.13.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.13.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.14.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.14.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.14.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.14.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.14.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.14.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.15.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.15.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.15.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.15.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.15.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.15.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.16.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.16.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.16.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.16.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.16.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.16.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.17.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.17.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.17.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.17.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.17.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.17.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.18.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.18.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.18.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.18.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.18.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.18.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.19.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.19.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.19.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.19.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.19.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.19.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.20.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.20.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.20.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.20.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.20.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.20.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.21.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.21.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.21.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.21.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.21.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.21.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.22.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.22.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.22.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.22.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.22.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.22.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.23.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.23.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.23.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.23.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.23.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.23.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+        "encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.7.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.8.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.8.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.8.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.8.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.8.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.8.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.9.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.9.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.9.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.9.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.9.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+        "encoder.block.9.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+        "encoder.embed_tokens.weight": "model-00001-of-00002.safetensors",
+        "encoder.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+        "shared.weight": "model-00001-of-00002.safetensors"
+    }
+}