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-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b7a4146cc1ca7b150ff962ef19635881108bcc80bef42460553dbdf4549bdc1
+size 4692527680

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbf05cc13b56e1f4b491b092aff69b59fa15a1f42b02ae2406fbf053d41e8707
+size 4966213648

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7c6b2fd9b7ecd9e47a0c440846bf2a6a052da1043244e828bd9440d0d21b222
+size 4966213664

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb651e737dd4c1b91f294c06329e9d3030a1e8fcf1ea71b907e10dfe467ed87c
+size 4960989112

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99b92872a61807a741a519bf2a4f0ba00363382ad8ffbb0403aa41ece611a58e
+size 4999811952

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0b1fb8ec9af3c9d739c52e3a57b3ee2b01dd83a7c4e8e0536ad4dd26b5375f8
+size 4932694640

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77652aadc9beeaa9d76dfea3e14ec0f12c311d7bd6b69d4ab00d048b1cc25b6d
+size 4999803376

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb40bda405bbbd342dbfd6b0e8f483fd36ca3972dd2d78deaa9435290581c538
+size 4927451192

model.safetensors.index.json

@@ -0,0 +1,751 @@
+{
+    "metadata": {
+        "total_size": 39708805120
+    },
+    "weight_map": {
+        "decoder.block.0.layer.0.SelfAttention.k.weight": "model-00004-of-00008.safetensors",
+        "decoder.block.0.layer.0.SelfAttention.o.weight": "model-00004-of-00008.safetensors",
+        "decoder.block.0.layer.0.SelfAttention.q.weight": "model-00004-of-00008.safetensors",
+        "decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00004-of-00008.safetensors",
+        "decoder.block.0.layer.0.SelfAttention.v.weight": "model-00004-of-00008.safetensors",
+        "decoder.block.0.layer.0.layer_norm.weight": "model-00004-of-00008.safetensors",
+        "decoder.block.0.layer.1.EncDecAttention.k.weight": "model-00004-of-00008.safetensors",
+        "decoder.block.0.layer.1.EncDecAttention.o.weight": "model-00004-of-00008.safetensors",
+        "decoder.block.0.layer.1.EncDecAttention.q.weight": "model-00004-of-00008.safetensors",
+        "decoder.block.0.layer.1.EncDecAttention.v.weight": "model-00004-of-00008.safetensors",
+        "decoder.block.0.layer.1.layer_norm.weight": "model-00004-of-00008.safetensors",
+        "decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "model-00004-of-00008.safetensors",
+        "decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "model-00004-of-00008.safetensors",
+        "decoder.block.0.layer.2.DenseReluDense.wo.weight": "model-00004-of-00008.safetensors",
+        "decoder.block.0.layer.2.layer_norm.weight": "model-00004-of-00008.safetensors",
+        "decoder.block.1.layer.0.SelfAttention.k.weight": "model-00004-of-00008.safetensors",
+        "decoder.block.1.layer.0.SelfAttention.o.weight": "model-00004-of-00008.safetensors",
+        "decoder.block.1.layer.0.SelfAttention.q.weight": "model-00004-of-00008.safetensors",
+        "decoder.block.1.layer.0.SelfAttention.v.weight": "model-00004-of-00008.safetensors",
+        "decoder.block.1.layer.0.layer_norm.weight": "model-00004-of-00008.safetensors",
+        "decoder.block.1.layer.1.EncDecAttention.k.weight": "model-00004-of-00008.safetensors",
+        "decoder.block.1.layer.1.EncDecAttention.o.weight": "model-00004-of-00008.safetensors",
+        "decoder.block.1.layer.1.EncDecAttention.q.weight": "model-00004-of-00008.safetensors",
+        "decoder.block.1.layer.1.EncDecAttention.v.weight": "model-00004-of-00008.safetensors",
+        "decoder.block.1.layer.1.layer_norm.weight": "model-00004-of-00008.safetensors",
+        "decoder.block.1.layer.2.DenseReluDense.wi_0.weight": "model-00004-of-00008.safetensors",
+        "decoder.block.1.layer.2.DenseReluDense.wi_1.weight": "model-00004-of-00008.safetensors",
+        "decoder.block.1.layer.2.DenseReluDense.wo.weight": "model-00004-of-00008.safetensors",
+        "decoder.block.1.layer.2.layer_norm.weight": "model-00004-of-00008.safetensors",
+        "decoder.block.10.layer.0.SelfAttention.k.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.10.layer.0.SelfAttention.o.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.10.layer.0.SelfAttention.q.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.10.layer.0.SelfAttention.v.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.10.layer.0.layer_norm.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.10.layer.1.EncDecAttention.k.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.10.layer.1.EncDecAttention.o.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.10.layer.1.EncDecAttention.q.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.10.layer.1.EncDecAttention.v.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.10.layer.1.layer_norm.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.10.layer.2.DenseReluDense.wi_0.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.10.layer.2.DenseReluDense.wi_1.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.10.layer.2.DenseReluDense.wo.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.10.layer.2.layer_norm.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.11.layer.0.SelfAttention.k.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.11.layer.0.SelfAttention.o.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.11.layer.0.SelfAttention.q.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.11.layer.0.SelfAttention.v.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.11.layer.0.layer_norm.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.11.layer.1.EncDecAttention.k.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.11.layer.1.EncDecAttention.o.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.11.layer.1.EncDecAttention.q.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.11.layer.1.EncDecAttention.v.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.11.layer.1.layer_norm.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.11.layer.2.DenseReluDense.wi_0.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.11.layer.2.DenseReluDense.wi_1.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.11.layer.2.DenseReluDense.wo.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.11.layer.2.layer_norm.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.12.layer.0.SelfAttention.k.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.12.layer.0.SelfAttention.o.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.12.layer.0.SelfAttention.q.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.12.layer.0.SelfAttention.v.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.12.layer.0.layer_norm.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.12.layer.1.EncDecAttention.k.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.12.layer.1.EncDecAttention.o.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.12.layer.1.EncDecAttention.q.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.12.layer.1.EncDecAttention.v.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.12.layer.1.layer_norm.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.12.layer.2.DenseReluDense.wi_0.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.12.layer.2.DenseReluDense.wi_1.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.12.layer.2.DenseReluDense.wo.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.12.layer.2.layer_norm.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.13.layer.0.SelfAttention.k.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.13.layer.0.SelfAttention.o.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.13.layer.0.SelfAttention.q.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.13.layer.0.SelfAttention.v.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.13.layer.0.layer_norm.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.13.layer.1.EncDecAttention.k.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.13.layer.1.EncDecAttention.o.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.13.layer.1.EncDecAttention.q.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.13.layer.1.EncDecAttention.v.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.13.layer.1.layer_norm.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.13.layer.2.DenseReluDense.wi_0.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.13.layer.2.DenseReluDense.wi_1.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.13.layer.2.DenseReluDense.wo.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.13.layer.2.layer_norm.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.14.layer.0.SelfAttention.k.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.14.layer.0.SelfAttention.o.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.14.layer.0.SelfAttention.q.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.14.layer.0.SelfAttention.v.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.14.layer.0.layer_norm.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.14.layer.1.EncDecAttention.k.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.14.layer.1.EncDecAttention.o.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.14.layer.1.EncDecAttention.q.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.14.layer.1.EncDecAttention.v.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.14.layer.1.layer_norm.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.14.layer.2.DenseReluDense.wi_0.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.14.layer.2.DenseReluDense.wi_1.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.14.layer.2.DenseReluDense.wo.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.14.layer.2.layer_norm.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.15.layer.0.SelfAttention.k.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.15.layer.0.SelfAttention.o.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.15.layer.0.SelfAttention.q.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.15.layer.0.SelfAttention.v.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.15.layer.0.layer_norm.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.15.layer.1.EncDecAttention.k.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.15.layer.1.EncDecAttention.o.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.15.layer.1.EncDecAttention.q.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.15.layer.1.EncDecAttention.v.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.15.layer.1.layer_norm.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.15.layer.2.DenseReluDense.wi_0.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.15.layer.2.DenseReluDense.wi_1.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.15.layer.2.DenseReluDense.wo.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.15.layer.2.layer_norm.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.16.layer.0.SelfAttention.k.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.16.layer.0.SelfAttention.o.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.16.layer.0.SelfAttention.q.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.16.layer.0.SelfAttention.v.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.16.layer.0.layer_norm.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.16.layer.1.EncDecAttention.k.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.16.layer.1.EncDecAttention.o.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.16.layer.1.EncDecAttention.q.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.16.layer.1.EncDecAttention.v.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.16.layer.1.layer_norm.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.16.layer.2.DenseReluDense.wi_0.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.16.layer.2.DenseReluDense.wi_1.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.16.layer.2.DenseReluDense.wo.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.16.layer.2.layer_norm.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.17.layer.0.SelfAttention.k.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.17.layer.0.SelfAttention.o.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.17.layer.0.SelfAttention.q.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.17.layer.0.SelfAttention.v.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.17.layer.0.layer_norm.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.17.layer.1.EncDecAttention.k.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.17.layer.1.EncDecAttention.o.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.17.layer.1.EncDecAttention.q.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.17.layer.1.EncDecAttention.v.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.17.layer.1.layer_norm.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.17.layer.2.DenseReluDense.wi_0.weight": "model-00006-of-00008.safetensors",
+        "decoder.block.17.layer.2.DenseReluDense.wi_1.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.17.layer.2.DenseReluDense.wo.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.17.layer.2.layer_norm.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.18.layer.0.SelfAttention.k.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.18.layer.0.SelfAttention.o.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.18.layer.0.SelfAttention.q.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.18.layer.0.SelfAttention.v.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.18.layer.0.layer_norm.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.18.layer.1.EncDecAttention.k.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.18.layer.1.EncDecAttention.o.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.18.layer.1.EncDecAttention.q.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.18.layer.1.EncDecAttention.v.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.18.layer.1.layer_norm.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.18.layer.2.DenseReluDense.wi_0.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.18.layer.2.DenseReluDense.wi_1.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.18.layer.2.DenseReluDense.wo.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.18.layer.2.layer_norm.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.19.layer.0.SelfAttention.k.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.19.layer.0.SelfAttention.o.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.19.layer.0.SelfAttention.q.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.19.layer.0.SelfAttention.v.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.19.layer.0.layer_norm.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.19.layer.1.EncDecAttention.k.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.19.layer.1.EncDecAttention.o.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.19.layer.1.EncDecAttention.q.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.19.layer.1.EncDecAttention.v.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.19.layer.1.layer_norm.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.19.layer.2.DenseReluDense.wi_0.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.19.layer.2.DenseReluDense.wi_1.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.19.layer.2.DenseReluDense.wo.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.19.layer.2.layer_norm.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.2.layer.0.SelfAttention.k.weight": "model-00004-of-00008.safetensors",
+        "decoder.block.2.layer.0.SelfAttention.o.weight": "model-00004-of-00008.safetensors",
+        "decoder.block.2.layer.0.SelfAttention.q.weight": "model-00004-of-00008.safetensors",
+        "decoder.block.2.layer.0.SelfAttention.v.weight": "model-00004-of-00008.safetensors",
+        "decoder.block.2.layer.0.layer_norm.weight": "model-00004-of-00008.safetensors",
+        "decoder.block.2.layer.1.EncDecAttention.k.weight": "model-00004-of-00008.safetensors",
+        "decoder.block.2.layer.1.EncDecAttention.o.weight": "model-00004-of-00008.safetensors",
+        "decoder.block.2.layer.1.EncDecAttention.q.weight": "model-00004-of-00008.safetensors",
+        "decoder.block.2.layer.1.EncDecAttention.v.weight": "model-00004-of-00008.safetensors",
+        "decoder.block.2.layer.1.layer_norm.weight": "model-00004-of-00008.safetensors",
+        "decoder.block.2.layer.2.DenseReluDense.wi_0.weight": "model-00004-of-00008.safetensors",
+        "decoder.block.2.layer.2.DenseReluDense.wi_1.weight": "model-00004-of-00008.safetensors",
+        "decoder.block.2.layer.2.DenseReluDense.wo.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.2.layer.2.layer_norm.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.20.layer.0.SelfAttention.k.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.20.layer.0.SelfAttention.o.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.20.layer.0.SelfAttention.q.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.20.layer.0.SelfAttention.v.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.20.layer.0.layer_norm.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.20.layer.1.EncDecAttention.k.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.20.layer.1.EncDecAttention.o.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.20.layer.1.EncDecAttention.q.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.20.layer.1.EncDecAttention.v.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.20.layer.1.layer_norm.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.20.layer.2.DenseReluDense.wi_0.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.20.layer.2.DenseReluDense.wi_1.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.20.layer.2.DenseReluDense.wo.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.20.layer.2.layer_norm.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.21.layer.0.SelfAttention.k.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.21.layer.0.SelfAttention.o.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.21.layer.0.SelfAttention.q.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.21.layer.0.SelfAttention.v.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.21.layer.0.layer_norm.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.21.layer.1.EncDecAttention.k.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.21.layer.1.EncDecAttention.o.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.21.layer.1.EncDecAttention.q.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.21.layer.1.EncDecAttention.v.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.21.layer.1.layer_norm.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.21.layer.2.DenseReluDense.wi_0.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.21.layer.2.DenseReluDense.wi_1.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.21.layer.2.DenseReluDense.wo.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.21.layer.2.layer_norm.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.22.layer.0.SelfAttention.k.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.22.layer.0.SelfAttention.o.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.22.layer.0.SelfAttention.q.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.22.layer.0.SelfAttention.v.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.22.layer.0.layer_norm.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.22.layer.1.EncDecAttention.k.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.22.layer.1.EncDecAttention.o.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.22.layer.1.EncDecAttention.q.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.22.layer.1.EncDecAttention.v.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.22.layer.1.layer_norm.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.22.layer.2.DenseReluDense.wi_0.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.22.layer.2.DenseReluDense.wi_1.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.22.layer.2.DenseReluDense.wo.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.22.layer.2.layer_norm.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.23.layer.0.SelfAttention.k.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.23.layer.0.SelfAttention.o.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.23.layer.0.SelfAttention.q.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.23.layer.0.SelfAttention.v.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.23.layer.0.layer_norm.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.23.layer.1.EncDecAttention.k.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.23.layer.1.EncDecAttention.o.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.23.layer.1.EncDecAttention.q.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.23.layer.1.EncDecAttention.v.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.23.layer.1.layer_norm.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.23.layer.2.DenseReluDense.wi_0.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.23.layer.2.DenseReluDense.wi_1.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.23.layer.2.DenseReluDense.wo.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.23.layer.2.layer_norm.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.24.layer.0.SelfAttention.k.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.24.layer.0.SelfAttention.o.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.24.layer.0.SelfAttention.q.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.24.layer.0.SelfAttention.v.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.24.layer.0.layer_norm.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.24.layer.1.EncDecAttention.k.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.24.layer.1.EncDecAttention.o.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.24.layer.1.EncDecAttention.q.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.24.layer.1.EncDecAttention.v.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.24.layer.1.layer_norm.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.24.layer.2.DenseReluDense.wi_0.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.24.layer.2.DenseReluDense.wi_1.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.24.layer.2.DenseReluDense.wo.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.24.layer.2.layer_norm.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.25.layer.0.SelfAttention.k.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.25.layer.0.SelfAttention.o.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.25.layer.0.SelfAttention.q.weight": "model-00007-of-00008.safetensors",
+        "decoder.block.25.layer.0.SelfAttention.v.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.25.layer.0.layer_norm.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.25.layer.1.EncDecAttention.k.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.25.layer.1.EncDecAttention.o.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.25.layer.1.EncDecAttention.q.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.25.layer.1.EncDecAttention.v.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.25.layer.1.layer_norm.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.25.layer.2.DenseReluDense.wi_0.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.25.layer.2.DenseReluDense.wi_1.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.25.layer.2.DenseReluDense.wo.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.25.layer.2.layer_norm.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.26.layer.0.SelfAttention.k.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.26.layer.0.SelfAttention.o.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.26.layer.0.SelfAttention.q.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.26.layer.0.SelfAttention.v.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.26.layer.0.layer_norm.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.26.layer.1.EncDecAttention.k.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.26.layer.1.EncDecAttention.o.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.26.layer.1.EncDecAttention.q.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.26.layer.1.EncDecAttention.v.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.26.layer.1.layer_norm.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.26.layer.2.DenseReluDense.wi_0.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.26.layer.2.DenseReluDense.wi_1.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.26.layer.2.DenseReluDense.wo.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.26.layer.2.layer_norm.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.27.layer.0.SelfAttention.k.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.27.layer.0.SelfAttention.o.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.27.layer.0.SelfAttention.q.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.27.layer.0.SelfAttention.v.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.27.layer.0.layer_norm.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.27.layer.1.EncDecAttention.k.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.27.layer.1.EncDecAttention.o.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.27.layer.1.EncDecAttention.q.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.27.layer.1.EncDecAttention.v.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.27.layer.1.layer_norm.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.27.layer.2.DenseReluDense.wi_0.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.27.layer.2.DenseReluDense.wi_1.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.27.layer.2.DenseReluDense.wo.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.27.layer.2.layer_norm.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.28.layer.0.SelfAttention.k.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.28.layer.0.SelfAttention.o.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.28.layer.0.SelfAttention.q.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.28.layer.0.SelfAttention.v.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.28.layer.0.layer_norm.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.28.layer.1.EncDecAttention.k.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.28.layer.1.EncDecAttention.o.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.28.layer.1.EncDecAttention.q.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.28.layer.1.EncDecAttention.v.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.28.layer.1.layer_norm.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.28.layer.2.DenseReluDense.wi_0.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.28.layer.2.DenseReluDense.wi_1.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.28.layer.2.DenseReluDense.wo.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.28.layer.2.layer_norm.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.29.layer.0.SelfAttention.k.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.29.layer.0.SelfAttention.o.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.29.layer.0.SelfAttention.q.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.29.layer.0.SelfAttention.v.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.29.layer.0.layer_norm.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.29.layer.1.EncDecAttention.k.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.29.layer.1.EncDecAttention.o.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.29.layer.1.EncDecAttention.q.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.29.layer.1.EncDecAttention.v.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.29.layer.1.layer_norm.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.29.layer.2.DenseReluDense.wi_0.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.29.layer.2.DenseReluDense.wi_1.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.29.layer.2.DenseReluDense.wo.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.29.layer.2.layer_norm.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.3.layer.0.SelfAttention.k.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.3.layer.0.SelfAttention.o.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.3.layer.0.SelfAttention.q.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.3.layer.0.SelfAttention.v.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.3.layer.0.layer_norm.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.3.layer.1.EncDecAttention.k.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.3.layer.1.EncDecAttention.o.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.3.layer.1.EncDecAttention.q.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.3.layer.1.EncDecAttention.v.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.3.layer.1.layer_norm.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.3.layer.2.DenseReluDense.wi_0.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.3.layer.2.DenseReluDense.wi_1.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.3.layer.2.DenseReluDense.wo.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.3.layer.2.layer_norm.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.30.layer.0.SelfAttention.k.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.30.layer.0.SelfAttention.o.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.30.layer.0.SelfAttention.q.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.30.layer.0.SelfAttention.v.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.30.layer.0.layer_norm.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.30.layer.1.EncDecAttention.k.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.30.layer.1.EncDecAttention.o.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.30.layer.1.EncDecAttention.q.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.30.layer.1.EncDecAttention.v.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.30.layer.1.layer_norm.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.30.layer.2.DenseReluDense.wi_0.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.30.layer.2.DenseReluDense.wi_1.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.30.layer.2.DenseReluDense.wo.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.30.layer.2.layer_norm.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.31.layer.0.SelfAttention.k.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.31.layer.0.SelfAttention.o.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.31.layer.0.SelfAttention.q.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.31.layer.0.SelfAttention.v.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.31.layer.0.layer_norm.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.31.layer.1.EncDecAttention.k.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.31.layer.1.EncDecAttention.o.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.31.layer.1.EncDecAttention.q.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.31.layer.1.EncDecAttention.v.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.31.layer.1.layer_norm.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.31.layer.2.DenseReluDense.wi_0.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.31.layer.2.DenseReluDense.wi_1.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.31.layer.2.DenseReluDense.wo.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.31.layer.2.layer_norm.weight": "model-00008-of-00008.safetensors",
+        "decoder.block.4.layer.0.SelfAttention.k.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.4.layer.0.SelfAttention.o.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.4.layer.0.SelfAttention.q.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.4.layer.0.SelfAttention.v.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.4.layer.0.layer_norm.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.4.layer.1.EncDecAttention.k.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.4.layer.1.EncDecAttention.o.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.4.layer.1.EncDecAttention.q.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.4.layer.1.EncDecAttention.v.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.4.layer.1.layer_norm.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.4.layer.2.DenseReluDense.wi_0.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.4.layer.2.DenseReluDense.wi_1.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.4.layer.2.DenseReluDense.wo.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.4.layer.2.layer_norm.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.5.layer.0.SelfAttention.k.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.5.layer.0.SelfAttention.o.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.5.layer.0.SelfAttention.q.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.5.layer.0.SelfAttention.v.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.5.layer.0.layer_norm.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.5.layer.1.EncDecAttention.k.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.5.layer.1.EncDecAttention.o.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.5.layer.1.EncDecAttention.q.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.5.layer.1.EncDecAttention.v.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.5.layer.1.layer_norm.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.5.layer.2.DenseReluDense.wi_0.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.5.layer.2.DenseReluDense.wi_1.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.5.layer.2.DenseReluDense.wo.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.5.layer.2.layer_norm.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.6.layer.0.SelfAttention.k.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.6.layer.0.SelfAttention.o.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.6.layer.0.SelfAttention.q.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.6.layer.0.SelfAttention.v.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.6.layer.0.layer_norm.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.6.layer.1.EncDecAttention.k.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.6.layer.1.EncDecAttention.o.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.6.layer.1.EncDecAttention.q.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.6.layer.1.EncDecAttention.v.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.6.layer.1.layer_norm.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.6.layer.2.DenseReluDense.wi_0.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.6.layer.2.DenseReluDense.wi_1.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.6.layer.2.DenseReluDense.wo.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.6.layer.2.layer_norm.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.7.layer.0.SelfAttention.k.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.7.layer.0.SelfAttention.o.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.7.layer.0.SelfAttention.q.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.7.layer.0.SelfAttention.v.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.7.layer.0.layer_norm.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.7.layer.1.EncDecAttention.k.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.7.layer.1.EncDecAttention.o.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.7.layer.1.EncDecAttention.q.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.7.layer.1.EncDecAttention.v.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.7.layer.1.layer_norm.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.7.layer.2.DenseReluDense.wi_0.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.7.layer.2.DenseReluDense.wi_1.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.7.layer.2.DenseReluDense.wo.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.7.layer.2.layer_norm.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.8.layer.0.SelfAttention.k.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.8.layer.0.SelfAttention.o.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.8.layer.0.SelfAttention.q.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.8.layer.0.SelfAttention.v.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.8.layer.0.layer_norm.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.8.layer.1.EncDecAttention.k.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.8.layer.1.EncDecAttention.o.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.8.layer.1.EncDecAttention.q.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.8.layer.1.EncDecAttention.v.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.8.layer.1.layer_norm.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.8.layer.2.DenseReluDense.wi_0.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.8.layer.2.DenseReluDense.wi_1.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.8.layer.2.DenseReluDense.wo.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.8.layer.2.layer_norm.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.9.layer.0.SelfAttention.k.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.9.layer.0.SelfAttention.o.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.9.layer.0.SelfAttention.q.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.9.layer.0.SelfAttention.v.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.9.layer.0.layer_norm.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.9.layer.1.EncDecAttention.k.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.9.layer.1.EncDecAttention.o.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.9.layer.1.EncDecAttention.q.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.9.layer.1.EncDecAttention.v.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.9.layer.1.layer_norm.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.9.layer.2.DenseReluDense.wi_0.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.9.layer.2.DenseReluDense.wi_1.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.9.layer.2.DenseReluDense.wo.weight": "model-00005-of-00008.safetensors",
+        "decoder.block.9.layer.2.layer_norm.weight": "model-00005-of-00008.safetensors",
+        "decoder.embed_tokens.weight": "model-00004-of-00008.safetensors",
+        "decoder.final_layer_norm.weight": "model-00008-of-00008.safetensors",
+        "encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.10.layer.0.SelfAttention.k.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.10.layer.0.SelfAttention.o.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.10.layer.0.SelfAttention.q.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.10.layer.0.SelfAttention.v.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.10.layer.0.layer_norm.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.10.layer.1.layer_norm.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.11.layer.0.SelfAttention.k.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.11.layer.0.SelfAttention.o.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.11.layer.0.SelfAttention.q.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.11.layer.0.SelfAttention.v.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.11.layer.0.layer_norm.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.11.layer.1.layer_norm.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.12.layer.0.SelfAttention.k.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.12.layer.0.SelfAttention.o.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.12.layer.0.SelfAttention.q.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.12.layer.0.SelfAttention.v.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.12.layer.0.layer_norm.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.12.layer.1.layer_norm.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.13.layer.0.SelfAttention.k.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.13.layer.0.SelfAttention.o.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.13.layer.0.SelfAttention.q.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.13.layer.0.SelfAttention.v.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.13.layer.0.layer_norm.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.13.layer.1.layer_norm.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.14.layer.0.SelfAttention.k.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.14.layer.0.SelfAttention.o.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.14.layer.0.SelfAttention.q.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.14.layer.0.SelfAttention.v.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.14.layer.0.layer_norm.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.14.layer.1.layer_norm.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.15.layer.0.SelfAttention.k.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.15.layer.0.SelfAttention.o.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.15.layer.0.SelfAttention.q.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.15.layer.0.SelfAttention.v.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.15.layer.0.layer_norm.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.15.layer.1.layer_norm.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.16.layer.0.SelfAttention.k.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.16.layer.0.SelfAttention.o.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.16.layer.0.SelfAttention.q.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.16.layer.0.SelfAttention.v.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.16.layer.0.layer_norm.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.16.layer.1.layer_norm.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.17.layer.0.SelfAttention.k.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.17.layer.0.SelfAttention.o.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.17.layer.0.SelfAttention.q.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.17.layer.0.SelfAttention.v.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.17.layer.0.layer_norm.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.17.layer.1.layer_norm.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.18.layer.0.SelfAttention.k.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.18.layer.0.SelfAttention.o.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.18.layer.0.SelfAttention.q.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.18.layer.0.SelfAttention.v.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.18.layer.0.layer_norm.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.18.layer.1.layer_norm.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.19.layer.0.SelfAttention.k.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.19.layer.0.SelfAttention.o.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.19.layer.0.SelfAttention.q.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.19.layer.0.SelfAttention.v.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.19.layer.0.layer_norm.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.19.layer.1.layer_norm.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.20.layer.0.SelfAttention.k.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.20.layer.0.SelfAttention.o.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.20.layer.0.SelfAttention.q.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.20.layer.0.SelfAttention.v.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.20.layer.0.layer_norm.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.20.layer.1.layer_norm.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.21.layer.0.SelfAttention.k.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.21.layer.0.SelfAttention.o.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.21.layer.0.SelfAttention.q.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.21.layer.0.SelfAttention.v.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.21.layer.0.layer_norm.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.21.layer.1.layer_norm.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.22.layer.0.SelfAttention.k.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.22.layer.0.SelfAttention.o.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.22.layer.0.SelfAttention.q.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.22.layer.0.SelfAttention.v.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.22.layer.0.layer_norm.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.22.layer.1.layer_norm.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.23.layer.0.SelfAttention.k.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.23.layer.0.SelfAttention.o.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.23.layer.0.SelfAttention.q.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.23.layer.0.SelfAttention.v.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.23.layer.0.layer_norm.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.23.layer.1.layer_norm.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.24.layer.0.SelfAttention.k.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.24.layer.0.SelfAttention.o.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.24.layer.0.SelfAttention.q.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.24.layer.0.SelfAttention.v.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.24.layer.0.layer_norm.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.24.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.24.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.24.layer.1.DenseReluDense.wo.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.24.layer.1.layer_norm.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.25.layer.0.SelfAttention.k.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.25.layer.0.SelfAttention.o.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.25.layer.0.SelfAttention.q.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.25.layer.0.SelfAttention.v.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.25.layer.0.layer_norm.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.25.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.25.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.25.layer.1.DenseReluDense.wo.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.25.layer.1.layer_norm.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.26.layer.0.SelfAttention.k.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.26.layer.0.SelfAttention.o.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.26.layer.0.SelfAttention.q.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.26.layer.0.SelfAttention.v.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.26.layer.0.layer_norm.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.26.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.26.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00008.safetensors",
+        "encoder.block.26.layer.1.DenseReluDense.wo.weight": "model-00004-of-00008.safetensors",
+        "encoder.block.26.layer.1.layer_norm.weight": "model-00004-of-00008.safetensors",
+        "encoder.block.27.layer.0.SelfAttention.k.weight": "model-00004-of-00008.safetensors",
+        "encoder.block.27.layer.0.SelfAttention.o.weight": "model-00004-of-00008.safetensors",
+        "encoder.block.27.layer.0.SelfAttention.q.weight": "model-00004-of-00008.safetensors",
+        "encoder.block.27.layer.0.SelfAttention.v.weight": "model-00004-of-00008.safetensors",
+        "encoder.block.27.layer.0.layer_norm.weight": "model-00004-of-00008.safetensors",
+        "encoder.block.27.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00008.safetensors",
+        "encoder.block.27.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00008.safetensors",
+        "encoder.block.27.layer.1.DenseReluDense.wo.weight": "model-00004-of-00008.safetensors",
+        "encoder.block.27.layer.1.layer_norm.weight": "model-00004-of-00008.safetensors",
+        "encoder.block.28.layer.0.SelfAttention.k.weight": "model-00004-of-00008.safetensors",
+        "encoder.block.28.layer.0.SelfAttention.o.weight": "model-00004-of-00008.safetensors",
+        "encoder.block.28.layer.0.SelfAttention.q.weight": "model-00004-of-00008.safetensors",
+        "encoder.block.28.layer.0.SelfAttention.v.weight": "model-00004-of-00008.safetensors",
+        "encoder.block.28.layer.0.layer_norm.weight": "model-00004-of-00008.safetensors",
+        "encoder.block.28.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00008.safetensors",
+        "encoder.block.28.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00008.safetensors",
+        "encoder.block.28.layer.1.DenseReluDense.wo.weight": "model-00004-of-00008.safetensors",
+        "encoder.block.28.layer.1.layer_norm.weight": "model-00004-of-00008.safetensors",
+        "encoder.block.29.layer.0.SelfAttention.k.weight": "model-00004-of-00008.safetensors",
+        "encoder.block.29.layer.0.SelfAttention.o.weight": "model-00004-of-00008.safetensors",
+        "encoder.block.29.layer.0.SelfAttention.q.weight": "model-00004-of-00008.safetensors",
+        "encoder.block.29.layer.0.SelfAttention.v.weight": "model-00004-of-00008.safetensors",
+        "encoder.block.29.layer.0.layer_norm.weight": "model-00004-of-00008.safetensors",
+        "encoder.block.29.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00008.safetensors",
+        "encoder.block.29.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00008.safetensors",
+        "encoder.block.29.layer.1.DenseReluDense.wo.weight": "model-00004-of-00008.safetensors",
+        "encoder.block.29.layer.1.layer_norm.weight": "model-00004-of-00008.safetensors",
+        "encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.30.layer.0.SelfAttention.k.weight": "model-00004-of-00008.safetensors",
+        "encoder.block.30.layer.0.SelfAttention.o.weight": "model-00004-of-00008.safetensors",
+        "encoder.block.30.layer.0.SelfAttention.q.weight": "model-00004-of-00008.safetensors",
+        "encoder.block.30.layer.0.SelfAttention.v.weight": "model-00004-of-00008.safetensors",
+        "encoder.block.30.layer.0.layer_norm.weight": "model-00004-of-00008.safetensors",
+        "encoder.block.30.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00008.safetensors",
+        "encoder.block.30.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00008.safetensors",
+        "encoder.block.30.layer.1.DenseReluDense.wo.weight": "model-00004-of-00008.safetensors",
+        "encoder.block.30.layer.1.layer_norm.weight": "model-00004-of-00008.safetensors",
+        "encoder.block.31.layer.0.SelfAttention.k.weight": "model-00004-of-00008.safetensors",
+        "encoder.block.31.layer.0.SelfAttention.o.weight": "model-00004-of-00008.safetensors",
+        "encoder.block.31.layer.0.SelfAttention.q.weight": "model-00004-of-00008.safetensors",
+        "encoder.block.31.layer.0.SelfAttention.v.weight": "model-00004-of-00008.safetensors",
+        "encoder.block.31.layer.0.layer_norm.weight": "model-00004-of-00008.safetensors",
+        "encoder.block.31.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00008.safetensors",
+        "encoder.block.31.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00008.safetensors",
+        "encoder.block.31.layer.1.DenseReluDense.wo.weight": "model-00004-of-00008.safetensors",
+        "encoder.block.31.layer.1.layer_norm.weight": "model-00004-of-00008.safetensors",
+        "encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.7.layer.1.layer_norm.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.8.layer.0.SelfAttention.k.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.8.layer.0.SelfAttention.o.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.8.layer.0.SelfAttention.q.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.8.layer.0.SelfAttention.v.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.8.layer.0.layer_norm.weight": "model-00001-of-00008.safetensors",
+        "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.8.layer.1.layer_norm.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.9.layer.0.SelfAttention.k.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.9.layer.0.SelfAttention.o.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.9.layer.0.SelfAttention.q.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.9.layer.0.SelfAttention.v.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.9.layer.0.layer_norm.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00002-of-00008.safetensors",
+        "encoder.block.9.layer.1.layer_norm.weight": "model-00002-of-00008.safetensors",
+        "encoder.embed_tokens.weight": "model-00001-of-00008.safetensors",
+        "encoder.final_layer_norm.weight": "model-00004-of-00008.safetensors",
+        "lm_head.weight": "model-00008-of-00008.safetensors",
+        "shared.weight": "model-00001-of-00008.safetensors"
+    }
+}