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:aee3de38660cdc62e4dacdd24c7f8a0c61b746208243cd0772ac1bb9ae237d74
+size 9950194656

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c102019b70ea2b5f8bf360090a7ebffcf0cf22d93534cdb91217971d5c0daafa
+size 4681626360

model.safetensors.index.json

@@ -0,0 +1,156 @@
+{
+    "metadata": {
+        "total_size": 14631804928
+    },
+    "weight_map": {
+        "lm_head.bias": "model-00002-of-00002.safetensors",
+        "lm_head.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.0.attn.causal_mask": "model-00001-of-00002.safetensors",
+        "transformer.h.0.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.0.attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.0.ln_1.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.0.ln_1.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.0.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.0.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.0.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.0.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.1.attn.causal_mask": "model-00001-of-00002.safetensors",
+        "transformer.h.1.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.1.attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.1.ln_1.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.1.ln_1.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.1.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.1.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.1.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.1.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.10.attn.causal_mask": "model-00001-of-00002.safetensors",
+        "transformer.h.10.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.10.attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.10.ln_1.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.10.ln_1.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.10.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.10.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.10.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.10.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.11.attn.causal_mask": "model-00001-of-00002.safetensors",
+        "transformer.h.11.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.11.attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.11.ln_1.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.11.ln_1.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.11.mlp.fc_in.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.11.mlp.fc_in.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.11.mlp.fc_out.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.11.mlp.fc_out.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.12.attn.causal_mask": "model-00002-of-00002.safetensors",
+        "transformer.h.12.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.12.attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.12.ln_1.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.12.ln_1.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.12.mlp.fc_in.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.12.mlp.fc_in.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.12.mlp.fc_out.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.12.mlp.fc_out.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.13.attn.causal_mask": "model-00002-of-00002.safetensors",
+        "transformer.h.13.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.13.attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.13.ln_1.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.13.ln_1.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.13.mlp.fc_in.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.13.mlp.fc_in.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.13.mlp.fc_out.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.13.mlp.fc_out.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.14.attn.causal_mask": "model-00002-of-00002.safetensors",
+        "transformer.h.14.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.14.attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.14.ln_1.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.14.ln_1.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.14.mlp.fc_in.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.14.mlp.fc_in.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.14.mlp.fc_out.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.14.mlp.fc_out.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.15.attn.causal_mask": "model-00002-of-00002.safetensors",
+        "transformer.h.15.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.15.attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.15.ln_1.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.15.ln_1.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.15.mlp.fc_in.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.15.mlp.fc_in.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.15.mlp.fc_out.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.15.mlp.fc_out.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.2.attn.causal_mask": "model-00001-of-00002.safetensors",
+        "transformer.h.2.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.2.attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.2.ln_1.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.2.ln_1.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.2.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.2.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.2.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.2.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.3.attn.causal_mask": "model-00001-of-00002.safetensors",
+        "transformer.h.3.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.3.attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.3.ln_1.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.3.ln_1.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.3.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.3.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.3.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.3.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.4.attn.causal_mask": "model-00001-of-00002.safetensors",
+        "transformer.h.4.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.4.attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.4.ln_1.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.4.ln_1.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.4.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.4.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.4.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.4.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.5.attn.causal_mask": "model-00001-of-00002.safetensors",
+        "transformer.h.5.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.5.attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.5.ln_1.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.5.ln_1.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.5.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.5.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.5.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.5.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.6.attn.causal_mask": "model-00001-of-00002.safetensors",
+        "transformer.h.6.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.6.attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.6.ln_1.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.6.ln_1.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.6.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.6.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.6.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.6.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.7.attn.causal_mask": "model-00001-of-00002.safetensors",
+        "transformer.h.7.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.7.attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.7.ln_1.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.7.ln_1.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.7.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.7.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.7.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.7.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.8.attn.causal_mask": "model-00001-of-00002.safetensors",
+        "transformer.h.8.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.8.attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.8.ln_1.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.8.ln_1.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.8.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.8.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.8.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.8.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.9.attn.causal_mask": "model-00001-of-00002.safetensors",
+        "transformer.h.9.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.9.attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.9.ln_1.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.9.ln_1.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.9.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.9.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.9.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.9.mlp.fc_out.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.wte.weight": "model-00001-of-00002.safetensors"
+    }
+}