Adding `safetensors` variant of this model

This is an automated PR created with https://huggingface.co/spaces/safetensors/convert

This new file is equivalent to `pytorch_model.bin` but safe in the sense that
no arbitrary code can be put into it.

These files also happen to load much faster than their pytorch counterpart:
https://colab.research.google.com/github/huggingface/notebooks/blob/main/safetensors_doc/en/speed.ipynb

The widgets on your model page will run using this model even if this is not merged
making sure the file actually works.

If you find any issues: please report here: https://huggingface.co/spaces/safetensors/convert/discussions

Feel free to ignore this PR.

.gitattributes

@@ -26,3 +26,8 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+model-00005-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00003-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00001-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00004-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00002-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:013a00cdffa843c6984ff2dc9f5636d9657162f3c6cdf675f735a1ed436e790a
+size 97753352

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9a526a334ea9467209904161181fbcb887eb7414771c1be4e0809f116a4b430
+size 96878448

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ae7ecbe54929f09df0a00139db0fd7d6fe9fdafe9440fa02652de2583a51236
+size 99231784

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd294e754be34aa0320f64195a0a59ab4e587df4ace54ae9f0597780c5ad4158
+size 99241040

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65dbfd703a738abaf69df0a9fb823852d793c2e82c9df41a1e45bb2b85efda54
+size 40162648

model.safetensors.index.json

@@ -0,0 +1,207 @@
+{
+    "metadata": {
+        "total_size": 433245184
+    },
+    "weight_map": {
+        "embeddings.LayerNorm.bias": "model-00001-of-00005.safetensors",
+        "embeddings.LayerNorm.weight": "model-00001-of-00005.safetensors",
+        "embeddings.position_embeddings.weight": "model-00001-of-00005.safetensors",
+        "embeddings.position_ids": "model-00001-of-00005.safetensors",
+        "embeddings.token_type_embeddings.weight": "model-00001-of-00005.safetensors",
+        "embeddings.word_embeddings.weight": "model-00001-of-00005.safetensors",
+        "encoder.layer.0.attention.output.LayerNorm.bias": "model-00002-of-00005.safetensors",
+        "encoder.layer.0.attention.output.LayerNorm.weight": "model-00002-of-00005.safetensors",
+        "encoder.layer.0.attention.output.dense.bias": "model-00002-of-00005.safetensors",
+        "encoder.layer.0.attention.output.dense.weight": "model-00002-of-00005.safetensors",
+        "encoder.layer.0.attention.self.key.bias": "model-00001-of-00005.safetensors",
+        "encoder.layer.0.attention.self.key.weight": "model-00001-of-00005.safetensors",
+        "encoder.layer.0.attention.self.query.bias": "model-00001-of-00005.safetensors",
+        "encoder.layer.0.attention.self.query.weight": "model-00001-of-00005.safetensors",
+        "encoder.layer.0.attention.self.value.bias": "model-00001-of-00005.safetensors",
+        "encoder.layer.0.attention.self.value.weight": "model-00001-of-00005.safetensors",
+        "encoder.layer.0.intermediate.dense.bias": "model-00002-of-00005.safetensors",
+        "encoder.layer.0.intermediate.dense.weight": "model-00002-of-00005.safetensors",
+        "encoder.layer.0.output.LayerNorm.bias": "model-00002-of-00005.safetensors",
+        "encoder.layer.0.output.LayerNorm.weight": "model-00002-of-00005.safetensors",
+        "encoder.layer.0.output.dense.bias": "model-00002-of-00005.safetensors",
+        "encoder.layer.0.output.dense.weight": "model-00002-of-00005.safetensors",
+        "encoder.layer.1.attention.output.LayerNorm.bias": "model-00002-of-00005.safetensors",
+        "encoder.layer.1.attention.output.LayerNorm.weight": "model-00002-of-00005.safetensors",
+        "encoder.layer.1.attention.output.dense.bias": "model-00002-of-00005.safetensors",
+        "encoder.layer.1.attention.output.dense.weight": "model-00002-of-00005.safetensors",
+        "encoder.layer.1.attention.self.key.bias": "model-00002-of-00005.safetensors",
+        "encoder.layer.1.attention.self.key.weight": "model-00002-of-00005.safetensors",
+        "encoder.layer.1.attention.self.query.bias": "model-00002-of-00005.safetensors",
+        "encoder.layer.1.attention.self.query.weight": "model-00002-of-00005.safetensors",
+        "encoder.layer.1.attention.self.value.bias": "model-00002-of-00005.safetensors",
+        "encoder.layer.1.attention.self.value.weight": "model-00002-of-00005.safetensors",
+        "encoder.layer.1.intermediate.dense.bias": "model-00002-of-00005.safetensors",
+        "encoder.layer.1.intermediate.dense.weight": "model-00002-of-00005.safetensors",
+        "encoder.layer.1.output.LayerNorm.bias": "model-00002-of-00005.safetensors",
+        "encoder.layer.1.output.LayerNorm.weight": "model-00002-of-00005.safetensors",
+        "encoder.layer.1.output.dense.bias": "model-00002-of-00005.safetensors",
+        "encoder.layer.1.output.dense.weight": "model-00002-of-00005.safetensors",
+        "encoder.layer.10.attention.output.LayerNorm.bias": "model-00004-of-00005.safetensors",
+        "encoder.layer.10.attention.output.LayerNorm.weight": "model-00004-of-00005.safetensors",
+        "encoder.layer.10.attention.output.dense.bias": "model-00004-of-00005.safetensors",
+        "encoder.layer.10.attention.output.dense.weight": "model-00004-of-00005.safetensors",
+        "encoder.layer.10.attention.self.key.bias": "model-00004-of-00005.safetensors",
+        "encoder.layer.10.attention.self.key.weight": "model-00004-of-00005.safetensors",
+        "encoder.layer.10.attention.self.query.bias": "model-00004-of-00005.safetensors",
+        "encoder.layer.10.attention.self.query.weight": "model-00004-of-00005.safetensors",
+        "encoder.layer.10.attention.self.value.bias": "model-00004-of-00005.safetensors",
+        "encoder.layer.10.attention.self.value.weight": "model-00004-of-00005.safetensors",
+        "encoder.layer.10.intermediate.dense.bias": "model-00004-of-00005.safetensors",
+        "encoder.layer.10.intermediate.dense.weight": "model-00004-of-00005.safetensors",
+        "encoder.layer.10.output.LayerNorm.bias": "model-00005-of-00005.safetensors",
+        "encoder.layer.10.output.LayerNorm.weight": "model-00005-of-00005.safetensors",
+        "encoder.layer.10.output.dense.bias": "model-00005-of-00005.safetensors",
+        "encoder.layer.10.output.dense.weight": "model-00005-of-00005.safetensors",
+        "encoder.layer.11.attention.output.LayerNorm.bias": "model-00005-of-00005.safetensors",
+        "encoder.layer.11.attention.output.LayerNorm.weight": "model-00005-of-00005.safetensors",
+        "encoder.layer.11.attention.output.dense.bias": "model-00005-of-00005.safetensors",
+        "encoder.layer.11.attention.output.dense.weight": "model-00005-of-00005.safetensors",
+        "encoder.layer.11.attention.self.key.bias": "model-00005-of-00005.safetensors",
+        "encoder.layer.11.attention.self.key.weight": "model-00005-of-00005.safetensors",
+        "encoder.layer.11.attention.self.query.bias": "model-00005-of-00005.safetensors",
+        "encoder.layer.11.attention.self.query.weight": "model-00005-of-00005.safetensors",
+        "encoder.layer.11.attention.self.value.bias": "model-00005-of-00005.safetensors",
+        "encoder.layer.11.attention.self.value.weight": "model-00005-of-00005.safetensors",
+        "encoder.layer.11.intermediate.dense.bias": "model-00005-of-00005.safetensors",
+        "encoder.layer.11.intermediate.dense.weight": "model-00005-of-00005.safetensors",
+        "encoder.layer.11.output.LayerNorm.bias": "model-00005-of-00005.safetensors",
+        "encoder.layer.11.output.LayerNorm.weight": "model-00005-of-00005.safetensors",
+        "encoder.layer.11.output.dense.bias": "model-00005-of-00005.safetensors",
+        "encoder.layer.11.output.dense.weight": "model-00005-of-00005.safetensors",
+        "encoder.layer.2.attention.output.LayerNorm.bias": "model-00002-of-00005.safetensors",
+        "encoder.layer.2.attention.output.LayerNorm.weight": "model-00002-of-00005.safetensors",
+        "encoder.layer.2.attention.output.dense.bias": "model-00002-of-00005.safetensors",
+        "encoder.layer.2.attention.output.dense.weight": "model-00002-of-00005.safetensors",
+        "encoder.layer.2.attention.self.key.bias": "model-00002-of-00005.safetensors",
+        "encoder.layer.2.attention.self.key.weight": "model-00002-of-00005.safetensors",
+        "encoder.layer.2.attention.self.query.bias": "model-00002-of-00005.safetensors",
+        "encoder.layer.2.attention.self.query.weight": "model-00002-of-00005.safetensors",
+        "encoder.layer.2.attention.self.value.bias": "model-00002-of-00005.safetensors",
+        "encoder.layer.2.attention.self.value.weight": "model-00002-of-00005.safetensors",
+        "encoder.layer.2.intermediate.dense.bias": "model-00002-of-00005.safetensors",
+        "encoder.layer.2.intermediate.dense.weight": "model-00002-of-00005.safetensors",
+        "encoder.layer.2.output.LayerNorm.bias": "model-00002-of-00005.safetensors",
+        "encoder.layer.2.output.LayerNorm.weight": "model-00002-of-00005.safetensors",
+        "encoder.layer.2.output.dense.bias": "model-00002-of-00005.safetensors",
+        "encoder.layer.2.output.dense.weight": "model-00002-of-00005.safetensors",
+        "encoder.layer.3.attention.output.LayerNorm.bias": "model-00002-of-00005.safetensors",
+        "encoder.layer.3.attention.output.LayerNorm.weight": "model-00002-of-00005.safetensors",
+        "encoder.layer.3.attention.output.dense.bias": "model-00002-of-00005.safetensors",
+        "encoder.layer.3.attention.output.dense.weight": "model-00002-of-00005.safetensors",
+        "encoder.layer.3.attention.self.key.bias": "model-00002-of-00005.safetensors",
+        "encoder.layer.3.attention.self.key.weight": "model-00002-of-00005.safetensors",
+        "encoder.layer.3.attention.self.query.bias": "model-00002-of-00005.safetensors",
+        "encoder.layer.3.attention.self.query.weight": "model-00002-of-00005.safetensors",
+        "encoder.layer.3.attention.self.value.bias": "model-00002-of-00005.safetensors",
+        "encoder.layer.3.attention.self.value.weight": "model-00002-of-00005.safetensors",
+        "encoder.layer.3.intermediate.dense.bias": "model-00002-of-00005.safetensors",
+        "encoder.layer.3.intermediate.dense.weight": "model-00002-of-00005.safetensors",
+        "encoder.layer.3.output.LayerNorm.bias": "model-00003-of-00005.safetensors",
+        "encoder.layer.3.output.LayerNorm.weight": "model-00003-of-00005.safetensors",
+        "encoder.layer.3.output.dense.bias": "model-00003-of-00005.safetensors",
+        "encoder.layer.3.output.dense.weight": "model-00003-of-00005.safetensors",
+        "encoder.layer.4.attention.output.LayerNorm.bias": "model-00003-of-00005.safetensors",
+        "encoder.layer.4.attention.output.LayerNorm.weight": "model-00003-of-00005.safetensors",
+        "encoder.layer.4.attention.output.dense.bias": "model-00003-of-00005.safetensors",
+        "encoder.layer.4.attention.output.dense.weight": "model-00003-of-00005.safetensors",
+        "encoder.layer.4.attention.self.key.bias": "model-00003-of-00005.safetensors",
+        "encoder.layer.4.attention.self.key.weight": "model-00003-of-00005.safetensors",
+        "encoder.layer.4.attention.self.query.bias": "model-00003-of-00005.safetensors",
+        "encoder.layer.4.attention.self.query.weight": "model-00003-of-00005.safetensors",
+        "encoder.layer.4.attention.self.value.bias": "model-00003-of-00005.safetensors",
+        "encoder.layer.4.attention.self.value.weight": "model-00003-of-00005.safetensors",
+        "encoder.layer.4.intermediate.dense.bias": "model-00003-of-00005.safetensors",
+        "encoder.layer.4.intermediate.dense.weight": "model-00003-of-00005.safetensors",
+        "encoder.layer.4.output.LayerNorm.bias": "model-00003-of-00005.safetensors",
+        "encoder.layer.4.output.LayerNorm.weight": "model-00003-of-00005.safetensors",
+        "encoder.layer.4.output.dense.bias": "model-00003-of-00005.safetensors",
+        "encoder.layer.4.output.dense.weight": "model-00003-of-00005.safetensors",
+        "encoder.layer.5.attention.output.LayerNorm.bias": "model-00003-of-00005.safetensors",
+        "encoder.layer.5.attention.output.LayerNorm.weight": "model-00003-of-00005.safetensors",
+        "encoder.layer.5.attention.output.dense.bias": "model-00003-of-00005.safetensors",
+        "encoder.layer.5.attention.output.dense.weight": "model-00003-of-00005.safetensors",
+        "encoder.layer.5.attention.self.key.bias": "model-00003-of-00005.safetensors",
+        "encoder.layer.5.attention.self.key.weight": "model-00003-of-00005.safetensors",
+        "encoder.layer.5.attention.self.query.bias": "model-00003-of-00005.safetensors",
+        "encoder.layer.5.attention.self.query.weight": "model-00003-of-00005.safetensors",
+        "encoder.layer.5.attention.self.value.bias": "model-00003-of-00005.safetensors",
+        "encoder.layer.5.attention.self.value.weight": "model-00003-of-00005.safetensors",
+        "encoder.layer.5.intermediate.dense.bias": "model-00003-of-00005.safetensors",
+        "encoder.layer.5.intermediate.dense.weight": "model-00003-of-00005.safetensors",
+        "encoder.layer.5.output.LayerNorm.bias": "model-00003-of-00005.safetensors",
+        "encoder.layer.5.output.LayerNorm.weight": "model-00003-of-00005.safetensors",
+        "encoder.layer.5.output.dense.bias": "model-00003-of-00005.safetensors",
+        "encoder.layer.5.output.dense.weight": "model-00003-of-00005.safetensors",
+        "encoder.layer.6.attention.output.LayerNorm.bias": "model-00003-of-00005.safetensors",
+        "encoder.layer.6.attention.output.LayerNorm.weight": "model-00003-of-00005.safetensors",
+        "encoder.layer.6.attention.output.dense.bias": "model-00003-of-00005.safetensors",
+        "encoder.layer.6.attention.output.dense.weight": "model-00003-of-00005.safetensors",
+        "encoder.layer.6.attention.self.key.bias": "model-00003-of-00005.safetensors",
+        "encoder.layer.6.attention.self.key.weight": "model-00003-of-00005.safetensors",
+        "encoder.layer.6.attention.self.query.bias": "model-00003-of-00005.safetensors",
+        "encoder.layer.6.attention.self.query.weight": "model-00003-of-00005.safetensors",
+        "encoder.layer.6.attention.self.value.bias": "model-00003-of-00005.safetensors",
+        "encoder.layer.6.attention.self.value.weight": "model-00003-of-00005.safetensors",
+        "encoder.layer.6.intermediate.dense.bias": "model-00003-of-00005.safetensors",
+        "encoder.layer.6.intermediate.dense.weight": "model-00003-of-00005.safetensors",
+        "encoder.layer.6.output.LayerNorm.bias": "model-00003-of-00005.safetensors",
+        "encoder.layer.6.output.LayerNorm.weight": "model-00003-of-00005.safetensors",
+        "encoder.layer.6.output.dense.bias": "model-00003-of-00005.safetensors",
+        "encoder.layer.6.output.dense.weight": "model-00003-of-00005.safetensors",
+        "encoder.layer.7.attention.output.LayerNorm.bias": "model-00004-of-00005.safetensors",
+        "encoder.layer.7.attention.output.LayerNorm.weight": "model-00004-of-00005.safetensors",
+        "encoder.layer.7.attention.output.dense.bias": "model-00004-of-00005.safetensors",
+        "encoder.layer.7.attention.output.dense.weight": "model-00004-of-00005.safetensors",
+        "encoder.layer.7.attention.self.key.bias": "model-00003-of-00005.safetensors",
+        "encoder.layer.7.attention.self.key.weight": "model-00003-of-00005.safetensors",
+        "encoder.layer.7.attention.self.query.bias": "model-00003-of-00005.safetensors",
+        "encoder.layer.7.attention.self.query.weight": "model-00003-of-00005.safetensors",
+        "encoder.layer.7.attention.self.value.bias": "model-00004-of-00005.safetensors",
+        "encoder.layer.7.attention.self.value.weight": "model-00004-of-00005.safetensors",
+        "encoder.layer.7.intermediate.dense.bias": "model-00004-of-00005.safetensors",
+        "encoder.layer.7.intermediate.dense.weight": "model-00004-of-00005.safetensors",
+        "encoder.layer.7.output.LayerNorm.bias": "model-00004-of-00005.safetensors",
+        "encoder.layer.7.output.LayerNorm.weight": "model-00004-of-00005.safetensors",
+        "encoder.layer.7.output.dense.bias": "model-00004-of-00005.safetensors",
+        "encoder.layer.7.output.dense.weight": "model-00004-of-00005.safetensors",
+        "encoder.layer.8.attention.output.LayerNorm.bias": "model-00004-of-00005.safetensors",
+        "encoder.layer.8.attention.output.LayerNorm.weight": "model-00004-of-00005.safetensors",
+        "encoder.layer.8.attention.output.dense.bias": "model-00004-of-00005.safetensors",
+        "encoder.layer.8.attention.output.dense.weight": "model-00004-of-00005.safetensors",
+        "encoder.layer.8.attention.self.key.bias": "model-00004-of-00005.safetensors",
+        "encoder.layer.8.attention.self.key.weight": "model-00004-of-00005.safetensors",
+        "encoder.layer.8.attention.self.query.bias": "model-00004-of-00005.safetensors",
+        "encoder.layer.8.attention.self.query.weight": "model-00004-of-00005.safetensors",
+        "encoder.layer.8.attention.self.value.bias": "model-00004-of-00005.safetensors",
+        "encoder.layer.8.attention.self.value.weight": "model-00004-of-00005.safetensors",
+        "encoder.layer.8.intermediate.dense.bias": "model-00004-of-00005.safetensors",
+        "encoder.layer.8.intermediate.dense.weight": "model-00004-of-00005.safetensors",
+        "encoder.layer.8.output.LayerNorm.bias": "model-00004-of-00005.safetensors",
+        "encoder.layer.8.output.LayerNorm.weight": "model-00004-of-00005.safetensors",
+        "encoder.layer.8.output.dense.bias": "model-00004-of-00005.safetensors",
+        "encoder.layer.8.output.dense.weight": "model-00004-of-00005.safetensors",
+        "encoder.layer.9.attention.output.LayerNorm.bias": "model-00004-of-00005.safetensors",
+        "encoder.layer.9.attention.output.LayerNorm.weight": "model-00004-of-00005.safetensors",
+        "encoder.layer.9.attention.output.dense.bias": "model-00004-of-00005.safetensors",
+        "encoder.layer.9.attention.output.dense.weight": "model-00004-of-00005.safetensors",
+        "encoder.layer.9.attention.self.key.bias": "model-00004-of-00005.safetensors",
+        "encoder.layer.9.attention.self.key.weight": "model-00004-of-00005.safetensors",
+        "encoder.layer.9.attention.self.query.bias": "model-00004-of-00005.safetensors",
+        "encoder.layer.9.attention.self.query.weight": "model-00004-of-00005.safetensors",
+        "encoder.layer.9.attention.self.value.bias": "model-00004-of-00005.safetensors",
+        "encoder.layer.9.attention.self.value.weight": "model-00004-of-00005.safetensors",
+        "encoder.layer.9.intermediate.dense.bias": "model-00004-of-00005.safetensors",
+        "encoder.layer.9.intermediate.dense.weight": "model-00004-of-00005.safetensors",
+        "encoder.layer.9.output.LayerNorm.bias": "model-00004-of-00005.safetensors",
+        "encoder.layer.9.output.LayerNorm.weight": "model-00004-of-00005.safetensors",
+        "encoder.layer.9.output.dense.bias": "model-00004-of-00005.safetensors",
+        "encoder.layer.9.output.dense.weight": "model-00004-of-00005.safetensors",
+        "pooler.dense.bias": "model-00005-of-00005.safetensors",
+        "pooler.dense.weight": "model-00005-of-00005.safetensors"
+    }
+}