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:b7ed9e5fb39fb6135eb4c8694795b61aab72e4f63b1952a7fa640b203aea2698
+size 9998231416

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7d9dccba9d95ccf7a79d90034d814c83c68b34e23b084889f130f96ac4e644e
+size 2175058952

model.safetensors.index.json

@@ -0,0 +1,444 @@
+{
+    "metadata": {
+        "total_size": 12173244416
+    },
+    "weight_map": {
+        "lm_head.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.0.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.0.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.0.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.0.attn.c_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.ln_2.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.0.ln_2.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.0.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.0.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.0.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.0.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.1.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.1.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.1.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.1.attn.c_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.ln_2.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.1.ln_2.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.1.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.1.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.1.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.1.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.10.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.10.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.10.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.10.attn.c_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.ln_2.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.10.ln_2.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.10.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.10.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.10.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.10.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.11.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.11.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.11.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.11.attn.c_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.ln_2.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.11.ln_2.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.11.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.11.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.11.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.11.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.12.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.12.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.12.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.12.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.12.ln_1.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.12.ln_1.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.12.ln_2.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.12.ln_2.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.12.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.12.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.12.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.12.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.13.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.13.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.13.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.13.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.13.ln_1.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.13.ln_1.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.13.ln_2.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.13.ln_2.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.13.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.13.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.13.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.13.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.14.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.14.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.14.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.14.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.14.ln_1.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.14.ln_1.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.14.ln_2.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.14.ln_2.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.14.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.14.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.14.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.14.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.15.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.15.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.15.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.15.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.15.ln_1.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.15.ln_1.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.15.ln_2.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.15.ln_2.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.15.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.15.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.15.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.15.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.16.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.16.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.16.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.16.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.16.ln_1.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.16.ln_1.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.16.ln_2.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.16.ln_2.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.16.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.16.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.16.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.16.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.17.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.17.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.17.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.17.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.17.ln_1.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.17.ln_1.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.17.ln_2.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.17.ln_2.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.17.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.17.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.17.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.17.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.18.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.18.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.18.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.18.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.18.ln_1.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.18.ln_1.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.18.ln_2.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.18.ln_2.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.18.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.18.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.18.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.18.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.19.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.19.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.19.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.19.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.19.ln_1.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.19.ln_1.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.19.ln_2.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.19.ln_2.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.19.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.19.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.19.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.19.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.2.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.2.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.2.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.2.attn.c_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.ln_2.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.2.ln_2.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.2.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.2.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.2.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.2.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.20.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.20.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.20.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.20.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.20.ln_1.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.20.ln_1.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.20.ln_2.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.20.ln_2.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.20.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.20.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.20.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.20.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.21.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.21.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.21.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.21.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.21.ln_1.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.21.ln_1.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.21.ln_2.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.21.ln_2.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.21.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.21.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.21.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.21.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.22.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.22.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.22.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.22.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.22.ln_1.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.22.ln_1.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.22.ln_2.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.22.ln_2.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.22.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.22.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.22.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.22.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.23.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.23.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.23.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.23.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.23.ln_1.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.23.ln_1.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.23.ln_2.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.23.ln_2.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.23.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.23.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.23.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.23.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.24.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.24.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.24.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.24.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.24.ln_1.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.24.ln_1.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.24.ln_2.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.24.ln_2.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.24.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.24.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.24.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.24.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.25.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.25.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.25.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.25.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.25.ln_1.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.25.ln_1.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.25.ln_2.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.25.ln_2.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.25.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.25.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.25.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.25.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.26.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.26.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.26.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.26.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.26.ln_1.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.26.ln_1.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.26.ln_2.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.26.ln_2.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.26.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.26.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.26.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.26.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.27.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.27.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.27.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.27.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.27.ln_1.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.27.ln_1.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.27.ln_2.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.27.ln_2.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.27.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.27.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.27.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.27.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.28.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.28.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.28.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.28.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.28.ln_1.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.28.ln_1.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.28.ln_2.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.28.ln_2.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.28.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.28.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.28.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.28.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.29.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.29.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.29.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.29.attn.c_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.29.ln_1.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.29.ln_1.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.29.ln_2.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.29.ln_2.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.29.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.29.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.29.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.29.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.3.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.3.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.3.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.3.attn.c_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.ln_2.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.3.ln_2.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.3.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.3.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.3.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.3.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.30.attn.c_attn.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.30.attn.c_attn.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.30.attn.c_proj.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.30.attn.c_proj.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.30.ln_1.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.30.ln_1.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.30.ln_2.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.30.ln_2.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.30.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.30.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.30.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.30.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.31.attn.c_attn.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.31.attn.c_attn.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.31.attn.c_proj.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.31.attn.c_proj.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.31.ln_1.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.31.ln_1.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.31.ln_2.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.31.ln_2.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.31.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.31.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.31.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.31.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.32.attn.c_attn.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.32.attn.c_attn.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.32.attn.c_proj.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.32.attn.c_proj.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.32.ln_1.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.32.ln_1.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.32.ln_2.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.32.ln_2.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.32.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.32.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.32.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.32.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.33.attn.c_attn.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.33.attn.c_attn.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.33.attn.c_proj.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.33.attn.c_proj.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.33.ln_1.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.33.ln_1.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.33.ln_2.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.33.ln_2.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.33.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.33.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.33.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.33.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.34.attn.c_attn.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.34.attn.c_attn.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.34.attn.c_proj.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.34.attn.c_proj.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.34.ln_1.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.34.ln_1.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.34.ln_2.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.34.ln_2.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.34.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.34.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.34.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.34.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.35.attn.c_attn.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.35.attn.c_attn.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.35.attn.c_proj.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.35.attn.c_proj.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.35.ln_1.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.35.ln_1.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.35.ln_2.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.35.ln_2.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.35.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.35.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.35.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+        "transformer.h.35.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+        "transformer.h.4.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.4.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.4.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.4.attn.c_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.ln_2.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.4.ln_2.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.4.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.4.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.4.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.4.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.5.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.5.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.5.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.5.attn.c_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.ln_2.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.5.ln_2.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.5.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.5.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.5.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.5.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.6.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.6.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.6.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.6.attn.c_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.ln_2.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.6.ln_2.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.6.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.6.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.6.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.6.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.7.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.7.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.7.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.7.attn.c_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.ln_2.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.7.ln_2.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.7.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.7.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.7.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.7.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.8.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.8.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.8.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.8.attn.c_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.ln_2.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.8.ln_2.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.8.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.8.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.8.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.8.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.9.attn.c_attn.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.9.attn.c_attn.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.9.attn.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.9.attn.c_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.ln_2.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.9.ln_2.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.9.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.9.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+        "transformer.h.9.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+        "transformer.h.9.mlp.c_proj.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.wpe.weight": "model-00001-of-00002.safetensors",
+        "transformer.wte.weight": "model-00001-of-00002.safetensors"
+    }
+}