Adding `safetensors` variant of this model

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

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

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

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

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

Feel free to ignore this PR.

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:688553672794bd5c6da365c22ae06660230198dacadff19654f9b6098cd2b08f
+size 9950976480

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d359631efbb71d5fda51d39643a29fc3d7d69504e2129ed5739ff8209e49209c
+size 3892488296

model.safetensors.index.json

@@ -0,0 +1,203 @@
+{
+    "metadata": {
+        "total_size": 13843441408
+    },
+    "weight_map": {
+        "lm_head.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.0.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.0.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.0.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.0.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.1.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.1.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.1.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.1.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.10.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.10.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.10.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.10.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.11.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.11.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.11.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.11.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.12.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.12.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.12.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.12.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.13.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.13.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.13.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.13.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.14.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.14.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.14.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.14.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.15.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.15.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.15.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.15.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.16.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.16.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.16.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.16.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.16.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.17.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.17.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.17.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.17.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.17.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.18.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.18.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.18.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.18.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.18.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.19.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.19.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.19.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.19.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.19.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.2.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.2.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.2.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.2.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.20.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.20.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.20.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.20.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.20.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.21.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.21.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.21.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.21.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.21.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.22.input_layernorm.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.22.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.22.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.22.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.22.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.23.input_layernorm.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.23.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.23.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.23.self_attention.dense.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.23.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.24.input_layernorm.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.24.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.24.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.24.self_attention.dense.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.24.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.25.input_layernorm.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.25.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.25.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.25.self_attention.dense.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.25.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.26.input_layernorm.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.26.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.26.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.26.self_attention.dense.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.26.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.27.input_layernorm.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.27.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.27.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.27.self_attention.dense.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.27.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.28.input_layernorm.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.28.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.28.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.28.self_attention.dense.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.28.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.29.input_layernorm.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.29.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.29.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.29.self_attention.dense.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.29.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.3.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.3.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.3.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.3.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.30.input_layernorm.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.30.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.30.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.30.self_attention.dense.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.30.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.31.input_layernorm.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.31.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.31.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.31.self_attention.dense.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.31.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.4.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.4.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.4.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.4.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.5.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.5.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.5.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.5.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.6.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.6.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.6.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.6.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.7.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.7.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.7.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.7.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.8.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.8.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.8.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.8.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.9.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.9.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.9.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.9.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "transformer.ln_f.bias": "model-00002-of-00002.safetensors",
+        "transformer.ln_f.weight": "model-00002-of-00002.safetensors",
+        "transformer.word_embeddings.weight": "model-00001-of-00002.safetensors"
+    }
+}