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-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2209fe278c9739e972ef421f22083072a059d555f16a49a4e65fe48d02312b5
+size 1974522792

model-00002-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f7b16c7fdda0127752095596df8281aebe28c61b11ab0f40b9b5d47fb04dbea
+size 1912663824

model-00003-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ea70638dfd0c8bf6384c0ac71303ad7255419a897a4741567ed7b46db88e626
+size 1879117936

model-00004-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2162ccdaca85e949d38f58128bbd0154db30c70110dc590058615119a3b2bd4b
+size 1879100992

model-00005-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c59a90e9d5638ee441f92bb52c5625b48e08ab376ec1c39e751338ede109b76
+size 1879117976

model-00006-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a55836e7056080b72616c1189bdb22a9e8db15a7a54b4c82ded9b739c7e561a7
+size 1879100992

model-00007-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:322ba58ab5293e0d26631174c0018bde034c093657479977ea3bc18bd280692d
+size 1879117976

model-00008-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:585c0eeac0b8b45b12c5bd1805f493fe5caaf1da4628468e0a2be33499d4d9af
+size 1879100992

model-00009-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e9d00116ac05fbbd8e287e25415f5256e816c789e350b59c2a5b6ba0532b9fa
+size 1879117976

model-00010-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49bb3c7372775edb158534a4ae3b75f05851cb571aa85af698bd5fad546b2cd9
+size 402670208

model.safetensors.index.json

@@ -0,0 +1,299 @@
+{
+    "metadata": {
+        "total_size": 17443595264
+    },
+    "weight_map": {
+        "encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00010.safetensors",
+        "encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00010.safetensors",
+        "encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00010.safetensors",
+        "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00010.safetensors",
+        "encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00010.safetensors",
+        "encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00010.safetensors",
+        "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00010.safetensors",
+        "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00010.safetensors",
+        "encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00010.safetensors",
+        "encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00010.safetensors",
+        "encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00010.safetensors",
+        "encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00010.safetensors",
+        "encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00010.safetensors",
+        "encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00010.safetensors",
+        "encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00010.safetensors",
+        "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00010.safetensors",
+        "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00010.safetensors",
+        "encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00010.safetensors",
+        "encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00010.safetensors",
+        "encoder.block.10.layer.0.SelfAttention.k.weight": "model-00003-of-00010.safetensors",
+        "encoder.block.10.layer.0.SelfAttention.o.weight": "model-00003-of-00010.safetensors",
+        "encoder.block.10.layer.0.SelfAttention.q.weight": "model-00003-of-00010.safetensors",
+        "encoder.block.10.layer.0.SelfAttention.v.weight": "model-00003-of-00010.safetensors",
+        "encoder.block.10.layer.0.layer_norm.weight": "model-00003-of-00010.safetensors",
+        "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00010.safetensors",
+        "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00010.safetensors",
+        "encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00004-of-00010.safetensors",
+        "encoder.block.10.layer.1.layer_norm.weight": "model-00004-of-00010.safetensors",
+        "encoder.block.11.layer.0.SelfAttention.k.weight": "model-00004-of-00010.safetensors",
+        "encoder.block.11.layer.0.SelfAttention.o.weight": "model-00004-of-00010.safetensors",
+        "encoder.block.11.layer.0.SelfAttention.q.weight": "model-00004-of-00010.safetensors",
+        "encoder.block.11.layer.0.SelfAttention.v.weight": "model-00004-of-00010.safetensors",
+        "encoder.block.11.layer.0.layer_norm.weight": "model-00004-of-00010.safetensors",
+        "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00010.safetensors",
+        "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00010.safetensors",
+        "encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00004-of-00010.safetensors",
+        "encoder.block.11.layer.1.layer_norm.weight": "model-00004-of-00010.safetensors",
+        "encoder.block.12.layer.0.SelfAttention.k.weight": "model-00004-of-00010.safetensors",
+        "encoder.block.12.layer.0.SelfAttention.o.weight": "model-00004-of-00010.safetensors",
+        "encoder.block.12.layer.0.SelfAttention.q.weight": "model-00004-of-00010.safetensors",
+        "encoder.block.12.layer.0.SelfAttention.v.weight": "model-00004-of-00010.safetensors",
+        "encoder.block.12.layer.0.layer_norm.weight": "model-00004-of-00010.safetensors",
+        "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00010.safetensors",
+        "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00010.safetensors",
+        "encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00004-of-00010.safetensors",
+        "encoder.block.12.layer.1.layer_norm.weight": "model-00004-of-00010.safetensors",
+        "encoder.block.13.layer.0.SelfAttention.k.weight": "model-00004-of-00010.safetensors",
+        "encoder.block.13.layer.0.SelfAttention.o.weight": "model-00004-of-00010.safetensors",
+        "encoder.block.13.layer.0.SelfAttention.q.weight": "model-00004-of-00010.safetensors",
+        "encoder.block.13.layer.0.SelfAttention.v.weight": "model-00004-of-00010.safetensors",
+        "encoder.block.13.layer.0.layer_norm.weight": "model-00004-of-00010.safetensors",
+        "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00010.safetensors",
+        "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00010.safetensors",
+        "encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00005-of-00010.safetensors",
+        "encoder.block.13.layer.1.layer_norm.weight": "model-00005-of-00010.safetensors",
+        "encoder.block.14.layer.0.SelfAttention.k.weight": "model-00005-of-00010.safetensors",
+        "encoder.block.14.layer.0.SelfAttention.o.weight": "model-00005-of-00010.safetensors",
+        "encoder.block.14.layer.0.SelfAttention.q.weight": "model-00005-of-00010.safetensors",
+        "encoder.block.14.layer.0.SelfAttention.v.weight": "model-00005-of-00010.safetensors",
+        "encoder.block.14.layer.0.layer_norm.weight": "model-00005-of-00010.safetensors",
+        "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00005-of-00010.safetensors",
+        "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00005-of-00010.safetensors",
+        "encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00005-of-00010.safetensors",
+        "encoder.block.14.layer.1.layer_norm.weight": "model-00005-of-00010.safetensors",
+        "encoder.block.15.layer.0.SelfAttention.k.weight": "model-00005-of-00010.safetensors",
+        "encoder.block.15.layer.0.SelfAttention.o.weight": "model-00005-of-00010.safetensors",
+        "encoder.block.15.layer.0.SelfAttention.q.weight": "model-00005-of-00010.safetensors",
+        "encoder.block.15.layer.0.SelfAttention.v.weight": "model-00005-of-00010.safetensors",
+        "encoder.block.15.layer.0.layer_norm.weight": "model-00005-of-00010.safetensors",
+        "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00005-of-00010.safetensors",
+        "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00005-of-00010.safetensors",
+        "encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00005-of-00010.safetensors",
+        "encoder.block.15.layer.1.layer_norm.weight": "model-00005-of-00010.safetensors",
+        "encoder.block.16.layer.0.SelfAttention.k.weight": "model-00005-of-00010.safetensors",
+        "encoder.block.16.layer.0.SelfAttention.o.weight": "model-00005-of-00010.safetensors",
+        "encoder.block.16.layer.0.SelfAttention.q.weight": "model-00005-of-00010.safetensors",
+        "encoder.block.16.layer.0.SelfAttention.v.weight": "model-00005-of-00010.safetensors",
+        "encoder.block.16.layer.0.layer_norm.weight": "model-00005-of-00010.safetensors",
+        "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00005-of-00010.safetensors",
+        "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00005-of-00010.safetensors",
+        "encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00005-of-00010.safetensors",
+        "encoder.block.16.layer.1.layer_norm.weight": "model-00005-of-00010.safetensors",
+        "encoder.block.17.layer.0.SelfAttention.k.weight": "model-00005-of-00010.safetensors",
+        "encoder.block.17.layer.0.SelfAttention.o.weight": "model-00005-of-00010.safetensors",
+        "encoder.block.17.layer.0.SelfAttention.q.weight": "model-00005-of-00010.safetensors",
+        "encoder.block.17.layer.0.SelfAttention.v.weight": "model-00005-of-00010.safetensors",
+        "encoder.block.17.layer.0.layer_norm.weight": "model-00005-of-00010.safetensors",
+        "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00006-of-00010.safetensors",
+        "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00006-of-00010.safetensors",
+        "encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00006-of-00010.safetensors",
+        "encoder.block.17.layer.1.layer_norm.weight": "model-00006-of-00010.safetensors",
+        "encoder.block.18.layer.0.SelfAttention.k.weight": "model-00006-of-00010.safetensors",
+        "encoder.block.18.layer.0.SelfAttention.o.weight": "model-00006-of-00010.safetensors",
+        "encoder.block.18.layer.0.SelfAttention.q.weight": "model-00006-of-00010.safetensors",
+        "encoder.block.18.layer.0.SelfAttention.v.weight": "model-00006-of-00010.safetensors",
+        "encoder.block.18.layer.0.layer_norm.weight": "model-00006-of-00010.safetensors",
+        "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00006-of-00010.safetensors",
+        "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00006-of-00010.safetensors",
+        "encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00006-of-00010.safetensors",
+        "encoder.block.18.layer.1.layer_norm.weight": "model-00006-of-00010.safetensors",
+        "encoder.block.19.layer.0.SelfAttention.k.weight": "model-00006-of-00010.safetensors",
+        "encoder.block.19.layer.0.SelfAttention.o.weight": "model-00006-of-00010.safetensors",
+        "encoder.block.19.layer.0.SelfAttention.q.weight": "model-00006-of-00010.safetensors",
+        "encoder.block.19.layer.0.SelfAttention.v.weight": "model-00006-of-00010.safetensors",
+        "encoder.block.19.layer.0.layer_norm.weight": "model-00006-of-00010.safetensors",
+        "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00006-of-00010.safetensors",
+        "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00006-of-00010.safetensors",
+        "encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00006-of-00010.safetensors",
+        "encoder.block.19.layer.1.layer_norm.weight": "model-00006-of-00010.safetensors",
+        "encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00010.safetensors",
+        "encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00010.safetensors",
+        "encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00010.safetensors",
+        "encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00010.safetensors",
+        "encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00010.safetensors",
+        "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00010.safetensors",
+        "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00010.safetensors",
+        "encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00010.safetensors",
+        "encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00010.safetensors",
+        "encoder.block.20.layer.0.SelfAttention.k.weight": "model-00006-of-00010.safetensors",
+        "encoder.block.20.layer.0.SelfAttention.o.weight": "model-00006-of-00010.safetensors",
+        "encoder.block.20.layer.0.SelfAttention.q.weight": "model-00006-of-00010.safetensors",
+        "encoder.block.20.layer.0.SelfAttention.v.weight": "model-00006-of-00010.safetensors",
+        "encoder.block.20.layer.0.layer_norm.weight": "model-00006-of-00010.safetensors",
+        "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00006-of-00010.safetensors",
+        "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00006-of-00010.safetensors",
+        "encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00007-of-00010.safetensors",
+        "encoder.block.20.layer.1.layer_norm.weight": "model-00007-of-00010.safetensors",
+        "encoder.block.21.layer.0.SelfAttention.k.weight": "model-00007-of-00010.safetensors",
+        "encoder.block.21.layer.0.SelfAttention.o.weight": "model-00007-of-00010.safetensors",
+        "encoder.block.21.layer.0.SelfAttention.q.weight": "model-00007-of-00010.safetensors",
+        "encoder.block.21.layer.0.SelfAttention.v.weight": "model-00007-of-00010.safetensors",
+        "encoder.block.21.layer.0.layer_norm.weight": "model-00007-of-00010.safetensors",
+        "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00007-of-00010.safetensors",
+        "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00007-of-00010.safetensors",
+        "encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00007-of-00010.safetensors",
+        "encoder.block.21.layer.1.layer_norm.weight": "model-00007-of-00010.safetensors",
+        "encoder.block.22.layer.0.SelfAttention.k.weight": "model-00007-of-00010.safetensors",
+        "encoder.block.22.layer.0.SelfAttention.o.weight": "model-00007-of-00010.safetensors",
+        "encoder.block.22.layer.0.SelfAttention.q.weight": "model-00007-of-00010.safetensors",
+        "encoder.block.22.layer.0.SelfAttention.v.weight": "model-00007-of-00010.safetensors",
+        "encoder.block.22.layer.0.layer_norm.weight": "model-00007-of-00010.safetensors",
+        "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00007-of-00010.safetensors",
+        "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00007-of-00010.safetensors",
+        "encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00007-of-00010.safetensors",
+        "encoder.block.22.layer.1.layer_norm.weight": "model-00007-of-00010.safetensors",
+        "encoder.block.23.layer.0.SelfAttention.k.weight": "model-00007-of-00010.safetensors",
+        "encoder.block.23.layer.0.SelfAttention.o.weight": "model-00007-of-00010.safetensors",
+        "encoder.block.23.layer.0.SelfAttention.q.weight": "model-00007-of-00010.safetensors",
+        "encoder.block.23.layer.0.SelfAttention.v.weight": "model-00007-of-00010.safetensors",
+        "encoder.block.23.layer.0.layer_norm.weight": "model-00007-of-00010.safetensors",
+        "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00007-of-00010.safetensors",
+        "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00007-of-00010.safetensors",
+        "encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00007-of-00010.safetensors",
+        "encoder.block.23.layer.1.layer_norm.weight": "model-00007-of-00010.safetensors",
+        "encoder.block.24.layer.0.SelfAttention.k.weight": "model-00007-of-00010.safetensors",
+        "encoder.block.24.layer.0.SelfAttention.o.weight": "model-00007-of-00010.safetensors",
+        "encoder.block.24.layer.0.SelfAttention.q.weight": "model-00007-of-00010.safetensors",
+        "encoder.block.24.layer.0.SelfAttention.v.weight": "model-00007-of-00010.safetensors",
+        "encoder.block.24.layer.0.layer_norm.weight": "model-00007-of-00010.safetensors",
+        "encoder.block.24.layer.1.DenseReluDense.wi_0.weight": "model-00008-of-00010.safetensors",
+        "encoder.block.24.layer.1.DenseReluDense.wi_1.weight": "model-00008-of-00010.safetensors",
+        "encoder.block.24.layer.1.DenseReluDense.wo.weight": "model-00008-of-00010.safetensors",
+        "encoder.block.24.layer.1.layer_norm.weight": "model-00008-of-00010.safetensors",
+        "encoder.block.25.layer.0.SelfAttention.k.weight": "model-00008-of-00010.safetensors",
+        "encoder.block.25.layer.0.SelfAttention.o.weight": "model-00008-of-00010.safetensors",
+        "encoder.block.25.layer.0.SelfAttention.q.weight": "model-00008-of-00010.safetensors",
+        "encoder.block.25.layer.0.SelfAttention.v.weight": "model-00008-of-00010.safetensors",
+        "encoder.block.25.layer.0.layer_norm.weight": "model-00008-of-00010.safetensors",
+        "encoder.block.25.layer.1.DenseReluDense.wi_0.weight": "model-00008-of-00010.safetensors",
+        "encoder.block.25.layer.1.DenseReluDense.wi_1.weight": "model-00008-of-00010.safetensors",
+        "encoder.block.25.layer.1.DenseReluDense.wo.weight": "model-00008-of-00010.safetensors",
+        "encoder.block.25.layer.1.layer_norm.weight": "model-00008-of-00010.safetensors",
+        "encoder.block.26.layer.0.SelfAttention.k.weight": "model-00008-of-00010.safetensors",
+        "encoder.block.26.layer.0.SelfAttention.o.weight": "model-00008-of-00010.safetensors",
+        "encoder.block.26.layer.0.SelfAttention.q.weight": "model-00008-of-00010.safetensors",
+        "encoder.block.26.layer.0.SelfAttention.v.weight": "model-00008-of-00010.safetensors",
+        "encoder.block.26.layer.0.layer_norm.weight": "model-00008-of-00010.safetensors",
+        "encoder.block.26.layer.1.DenseReluDense.wi_0.weight": "model-00008-of-00010.safetensors",
+        "encoder.block.26.layer.1.DenseReluDense.wi_1.weight": "model-00008-of-00010.safetensors",
+        "encoder.block.26.layer.1.DenseReluDense.wo.weight": "model-00008-of-00010.safetensors",
+        "encoder.block.26.layer.1.layer_norm.weight": "model-00008-of-00010.safetensors",
+        "encoder.block.27.layer.0.SelfAttention.k.weight": "model-00008-of-00010.safetensors",
+        "encoder.block.27.layer.0.SelfAttention.o.weight": "model-00008-of-00010.safetensors",
+        "encoder.block.27.layer.0.SelfAttention.q.weight": "model-00008-of-00010.safetensors",
+        "encoder.block.27.layer.0.SelfAttention.v.weight": "model-00008-of-00010.safetensors",
+        "encoder.block.27.layer.0.layer_norm.weight": "model-00008-of-00010.safetensors",
+        "encoder.block.27.layer.1.DenseReluDense.wi_0.weight": "model-00008-of-00010.safetensors",
+        "encoder.block.27.layer.1.DenseReluDense.wi_1.weight": "model-00008-of-00010.safetensors",
+        "encoder.block.27.layer.1.DenseReluDense.wo.weight": "model-00009-of-00010.safetensors",
+        "encoder.block.27.layer.1.layer_norm.weight": "model-00009-of-00010.safetensors",
+        "encoder.block.28.layer.0.SelfAttention.k.weight": "model-00009-of-00010.safetensors",
+        "encoder.block.28.layer.0.SelfAttention.o.weight": "model-00009-of-00010.safetensors",
+        "encoder.block.28.layer.0.SelfAttention.q.weight": "model-00009-of-00010.safetensors",
+        "encoder.block.28.layer.0.SelfAttention.v.weight": "model-00009-of-00010.safetensors",
+        "encoder.block.28.layer.0.layer_norm.weight": "model-00009-of-00010.safetensors",
+        "encoder.block.28.layer.1.DenseReluDense.wi_0.weight": "model-00009-of-00010.safetensors",
+        "encoder.block.28.layer.1.DenseReluDense.wi_1.weight": "model-00009-of-00010.safetensors",
+        "encoder.block.28.layer.1.DenseReluDense.wo.weight": "model-00009-of-00010.safetensors",
+        "encoder.block.28.layer.1.layer_norm.weight": "model-00009-of-00010.safetensors",
+        "encoder.block.29.layer.0.SelfAttention.k.weight": "model-00009-of-00010.safetensors",
+        "encoder.block.29.layer.0.SelfAttention.o.weight": "model-00009-of-00010.safetensors",
+        "encoder.block.29.layer.0.SelfAttention.q.weight": "model-00009-of-00010.safetensors",
+        "encoder.block.29.layer.0.SelfAttention.v.weight": "model-00009-of-00010.safetensors",
+        "encoder.block.29.layer.0.layer_norm.weight": "model-00009-of-00010.safetensors",
+        "encoder.block.29.layer.1.DenseReluDense.wi_0.weight": "model-00009-of-00010.safetensors",
+        "encoder.block.29.layer.1.DenseReluDense.wi_1.weight": "model-00009-of-00010.safetensors",
+        "encoder.block.29.layer.1.DenseReluDense.wo.weight": "model-00009-of-00010.safetensors",
+        "encoder.block.29.layer.1.layer_norm.weight": "model-00009-of-00010.safetensors",
+        "encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00010.safetensors",
+        "encoder.block.3.layer.0.SelfAttention.o.weight": "model-00002-of-00010.safetensors",
+        "encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00010.safetensors",
+        "encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00010.safetensors",
+        "encoder.block.3.layer.0.layer_norm.weight": "model-00002-of-00010.safetensors",
+        "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00010.safetensors",
+        "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00010.safetensors",
+        "encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00002-of-00010.safetensors",
+        "encoder.block.3.layer.1.layer_norm.weight": "model-00002-of-00010.safetensors",
+        "encoder.block.30.layer.0.SelfAttention.k.weight": "model-00009-of-00010.safetensors",
+        "encoder.block.30.layer.0.SelfAttention.o.weight": "model-00009-of-00010.safetensors",
+        "encoder.block.30.layer.0.SelfAttention.q.weight": "model-00009-of-00010.safetensors",
+        "encoder.block.30.layer.0.SelfAttention.v.weight": "model-00009-of-00010.safetensors",
+        "encoder.block.30.layer.0.layer_norm.weight": "model-00009-of-00010.safetensors",
+        "encoder.block.30.layer.1.DenseReluDense.wi_0.weight": "model-00009-of-00010.safetensors",
+        "encoder.block.30.layer.1.DenseReluDense.wi_1.weight": "model-00009-of-00010.safetensors",
+        "encoder.block.30.layer.1.DenseReluDense.wo.weight": "model-00009-of-00010.safetensors",
+        "encoder.block.30.layer.1.layer_norm.weight": "model-00009-of-00010.safetensors",
+        "encoder.block.31.layer.0.SelfAttention.k.weight": "model-00009-of-00010.safetensors",
+        "encoder.block.31.layer.0.SelfAttention.o.weight": "model-00009-of-00010.safetensors",
+        "encoder.block.31.layer.0.SelfAttention.q.weight": "model-00009-of-00010.safetensors",
+        "encoder.block.31.layer.0.SelfAttention.v.weight": "model-00009-of-00010.safetensors",
+        "encoder.block.31.layer.0.layer_norm.weight": "model-00009-of-00010.safetensors",
+        "encoder.block.31.layer.1.DenseReluDense.wi_0.weight": "model-00010-of-00010.safetensors",
+        "encoder.block.31.layer.1.DenseReluDense.wi_1.weight": "model-00010-of-00010.safetensors",
+        "encoder.block.31.layer.1.DenseReluDense.wo.weight": "model-00010-of-00010.safetensors",
+        "encoder.block.31.layer.1.layer_norm.weight": "model-00010-of-00010.safetensors",
+        "encoder.block.4.layer.0.SelfAttention.k.weight": "model-00002-of-00010.safetensors",
+        "encoder.block.4.layer.0.SelfAttention.o.weight": "model-00002-of-00010.safetensors",
+        "encoder.block.4.layer.0.SelfAttention.q.weight": "model-00002-of-00010.safetensors",
+        "encoder.block.4.layer.0.SelfAttention.v.weight": "model-00002-of-00010.safetensors",
+        "encoder.block.4.layer.0.layer_norm.weight": "model-00002-of-00010.safetensors",
+        "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00010.safetensors",
+        "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00010.safetensors",
+        "encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00002-of-00010.safetensors",
+        "encoder.block.4.layer.1.layer_norm.weight": "model-00002-of-00010.safetensors",
+        "encoder.block.5.layer.0.SelfAttention.k.weight": "model-00002-of-00010.safetensors",
+        "encoder.block.5.layer.0.SelfAttention.o.weight": "model-00002-of-00010.safetensors",
+        "encoder.block.5.layer.0.SelfAttention.q.weight": "model-00002-of-00010.safetensors",
+        "encoder.block.5.layer.0.SelfAttention.v.weight": "model-00002-of-00010.safetensors",
+        "encoder.block.5.layer.0.layer_norm.weight": "model-00002-of-00010.safetensors",
+        "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00010.safetensors",
+        "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00010.safetensors",
+        "encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00002-of-00010.safetensors",
+        "encoder.block.5.layer.1.layer_norm.weight": "model-00002-of-00010.safetensors",
+        "encoder.block.6.layer.0.SelfAttention.k.weight": "model-00002-of-00010.safetensors",
+        "encoder.block.6.layer.0.SelfAttention.o.weight": "model-00002-of-00010.safetensors",
+        "encoder.block.6.layer.0.SelfAttention.q.weight": "model-00002-of-00010.safetensors",
+        "encoder.block.6.layer.0.SelfAttention.v.weight": "model-00002-of-00010.safetensors",
+        "encoder.block.6.layer.0.layer_norm.weight": "model-00002-of-00010.safetensors",
+        "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00010.safetensors",
+        "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00010.safetensors",
+        "encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00003-of-00010.safetensors",
+        "encoder.block.6.layer.1.layer_norm.weight": "model-00003-of-00010.safetensors",
+        "encoder.block.7.layer.0.SelfAttention.k.weight": "model-00003-of-00010.safetensors",
+        "encoder.block.7.layer.0.SelfAttention.o.weight": "model-00003-of-00010.safetensors",
+        "encoder.block.7.layer.0.SelfAttention.q.weight": "model-00003-of-00010.safetensors",
+        "encoder.block.7.layer.0.SelfAttention.v.weight": "model-00003-of-00010.safetensors",
+        "encoder.block.7.layer.0.layer_norm.weight": "model-00003-of-00010.safetensors",
+        "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00010.safetensors",
+        "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00010.safetensors",
+        "encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00003-of-00010.safetensors",
+        "encoder.block.7.layer.1.layer_norm.weight": "model-00003-of-00010.safetensors",
+        "encoder.block.8.layer.0.SelfAttention.k.weight": "model-00003-of-00010.safetensors",
+        "encoder.block.8.layer.0.SelfAttention.o.weight": "model-00003-of-00010.safetensors",
+        "encoder.block.8.layer.0.SelfAttention.q.weight": "model-00003-of-00010.safetensors",
+        "encoder.block.8.layer.0.SelfAttention.v.weight": "model-00003-of-00010.safetensors",
+        "encoder.block.8.layer.0.layer_norm.weight": "model-00003-of-00010.safetensors",
+        "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00010.safetensors",
+        "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00010.safetensors",
+        "encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00003-of-00010.safetensors",
+        "encoder.block.8.layer.1.layer_norm.weight": "model-00003-of-00010.safetensors",
+        "encoder.block.9.layer.0.SelfAttention.k.weight": "model-00003-of-00010.safetensors",
+        "encoder.block.9.layer.0.SelfAttention.o.weight": "model-00003-of-00010.safetensors",
+        "encoder.block.9.layer.0.SelfAttention.q.weight": "model-00003-of-00010.safetensors",
+        "encoder.block.9.layer.0.SelfAttention.v.weight": "model-00003-of-00010.safetensors",
+        "encoder.block.9.layer.0.layer_norm.weight": "model-00003-of-00010.safetensors",
+        "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00010.safetensors",
+        "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00010.safetensors",
+        "encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00003-of-00010.safetensors",
+        "encoder.block.9.layer.1.layer_norm.weight": "model-00003-of-00010.safetensors",
+        "encoder.embed_tokens.weight": "model-00001-of-00010.safetensors",
+        "encoder.final_layer_norm.weight": "model-00010-of-00010.safetensors",
+        "shared.weight": "model-00001-of-00010.safetensors"
+    }
+}