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-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a1b0e2f43597841818d7f19ebf3d23ab2c39587becb621024d2c2dd2d1b12dc
+size 2979477136

model-00002-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57f4708fad1a0c19cd9b787c7386c3653709cc4fb3e74d091636371f05ef105b
+size 2731002408

model-00003-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c58ce344b840a5797dca5a695649851aff0938592b9e56f37a7f8cd1ca30300
+size 2730990328

model-00004-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1de36390e87bf8a8caf7c416510afb0a49dfa06827d1a49eb1c7fb40affef622
+size 2957494888

model-00005-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f8ce33bec32dcd500b2823d11005fe9fb00e85f97623ded68603a86fa20f4d5
+size 2954373408

model-00006-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b3b247277eba5a6d6d3693506245c1dc2b32ddedc985b48f47d1a2df9a0626d
+size 2731002456

model-00007-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f56726cec26762960a18723089e3fa54d0055634d5e7547ece9d352a1105092f
+size 2730990384

model-00008-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9275096f213e905960ebdd5287aff13aaa344f9cee51064dc18b11c68cd5079c
+size 2957494888

model-00009-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d1269a70c6419a0f4216662a547e275e5cd5f9e585b2e59a92220b54211d36d
+size 2954373408

model-00010-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9d8358a3680b8a8ffcf53d9ef69b4390d0576baf30a1b5c7017b65549cbb9a1
+size 2731002456

model-00011-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:956d223a77534d474f387129592cf0072b2d723b14bbb427b8fb90ad78784795
+size 2576799400

model.safetensors.index.json

@@ -0,0 +1,492 @@
+{
+    "metadata": {
+        "total_size": 31034949632
+    },
+    "weight_map": {
+        "lm_head.weight": "model-00001-of-00011.safetensors",
+        "transformer.h.0.attn.c_attn.bias": "model-00001-of-00011.safetensors",
+        "transformer.h.0.attn.c_attn.weight": "model-00001-of-00011.safetensors",
+        "transformer.h.0.attn.c_proj.bias": "model-00001-of-00011.safetensors",
+        "transformer.h.0.attn.c_proj.weight": "model-00001-of-00011.safetensors",
+        "transformer.h.0.ln_1.bias": "model-00001-of-00011.safetensors",
+        "transformer.h.0.ln_1.weight": "model-00001-of-00011.safetensors",
+        "transformer.h.0.ln_2.bias": "model-00001-of-00011.safetensors",
+        "transformer.h.0.ln_2.weight": "model-00001-of-00011.safetensors",
+        "transformer.h.0.mlp.c_fc.bias": "model-00001-of-00011.safetensors",
+        "transformer.h.0.mlp.c_fc.weight": "model-00001-of-00011.safetensors",
+        "transformer.h.0.mlp.c_proj.bias": "model-00001-of-00011.safetensors",
+        "transformer.h.0.mlp.c_proj.weight": "model-00001-of-00011.safetensors",
+        "transformer.h.1.attn.c_attn.bias": "model-00001-of-00011.safetensors",
+        "transformer.h.1.attn.c_attn.weight": "model-00001-of-00011.safetensors",
+        "transformer.h.1.attn.c_proj.bias": "model-00001-of-00011.safetensors",
+        "transformer.h.1.attn.c_proj.weight": "model-00001-of-00011.safetensors",
+        "transformer.h.1.ln_1.bias": "model-00001-of-00011.safetensors",
+        "transformer.h.1.ln_1.weight": "model-00001-of-00011.safetensors",
+        "transformer.h.1.ln_2.bias": "model-00001-of-00011.safetensors",
+        "transformer.h.1.ln_2.weight": "model-00001-of-00011.safetensors",
+        "transformer.h.1.mlp.c_fc.bias": "model-00001-of-00011.safetensors",
+        "transformer.h.1.mlp.c_fc.weight": "model-00001-of-00011.safetensors",
+        "transformer.h.1.mlp.c_proj.bias": "model-00001-of-00011.safetensors",
+        "transformer.h.1.mlp.c_proj.weight": "model-00001-of-00011.safetensors",
+        "transformer.h.10.attn.c_attn.bias": "model-00003-of-00011.safetensors",
+        "transformer.h.10.attn.c_attn.weight": "model-00003-of-00011.safetensors",
+        "transformer.h.10.attn.c_proj.bias": "model-00003-of-00011.safetensors",
+        "transformer.h.10.attn.c_proj.weight": "model-00003-of-00011.safetensors",
+        "transformer.h.10.ln_1.bias": "model-00003-of-00011.safetensors",
+        "transformer.h.10.ln_1.weight": "model-00003-of-00011.safetensors",
+        "transformer.h.10.ln_2.bias": "model-00003-of-00011.safetensors",
+        "transformer.h.10.ln_2.weight": "model-00003-of-00011.safetensors",
+        "transformer.h.10.mlp.c_fc.bias": "model-00004-of-00011.safetensors",
+        "transformer.h.10.mlp.c_fc.weight": "model-00004-of-00011.safetensors",
+        "transformer.h.10.mlp.c_proj.bias": "model-00004-of-00011.safetensors",
+        "transformer.h.10.mlp.c_proj.weight": "model-00004-of-00011.safetensors",
+        "transformer.h.11.attn.c_attn.bias": "model-00004-of-00011.safetensors",
+        "transformer.h.11.attn.c_attn.weight": "model-00004-of-00011.safetensors",
+        "transformer.h.11.attn.c_proj.bias": "model-00004-of-00011.safetensors",
+        "transformer.h.11.attn.c_proj.weight": "model-00004-of-00011.safetensors",
+        "transformer.h.11.ln_1.bias": "model-00004-of-00011.safetensors",
+        "transformer.h.11.ln_1.weight": "model-00004-of-00011.safetensors",
+        "transformer.h.11.ln_2.bias": "model-00004-of-00011.safetensors",
+        "transformer.h.11.ln_2.weight": "model-00004-of-00011.safetensors",
+        "transformer.h.11.mlp.c_fc.bias": "model-00004-of-00011.safetensors",
+        "transformer.h.11.mlp.c_fc.weight": "model-00004-of-00011.safetensors",
+        "transformer.h.11.mlp.c_proj.bias": "model-00004-of-00011.safetensors",
+        "transformer.h.11.mlp.c_proj.weight": "model-00004-of-00011.safetensors",
+        "transformer.h.12.attn.c_attn.bias": "model-00004-of-00011.safetensors",
+        "transformer.h.12.attn.c_attn.weight": "model-00004-of-00011.safetensors",
+        "transformer.h.12.attn.c_proj.bias": "model-00004-of-00011.safetensors",
+        "transformer.h.12.attn.c_proj.weight": "model-00004-of-00011.safetensors",
+        "transformer.h.12.ln_1.bias": "model-00004-of-00011.safetensors",
+        "transformer.h.12.ln_1.weight": "model-00004-of-00011.safetensors",
+        "transformer.h.12.ln_2.bias": "model-00004-of-00011.safetensors",
+        "transformer.h.12.ln_2.weight": "model-00004-of-00011.safetensors",
+        "transformer.h.12.mlp.c_fc.bias": "model-00004-of-00011.safetensors",
+        "transformer.h.12.mlp.c_fc.weight": "model-00004-of-00011.safetensors",
+        "transformer.h.12.mlp.c_proj.bias": "model-00004-of-00011.safetensors",
+        "transformer.h.12.mlp.c_proj.weight": "model-00004-of-00011.safetensors",
+        "transformer.h.13.attn.c_attn.bias": "model-00004-of-00011.safetensors",
+        "transformer.h.13.attn.c_attn.weight": "model-00004-of-00011.safetensors",
+        "transformer.h.13.attn.c_proj.bias": "model-00004-of-00011.safetensors",
+        "transformer.h.13.attn.c_proj.weight": "model-00004-of-00011.safetensors",
+        "transformer.h.13.ln_1.bias": "model-00004-of-00011.safetensors",
+        "transformer.h.13.ln_1.weight": "model-00004-of-00011.safetensors",
+        "transformer.h.13.ln_2.bias": "model-00004-of-00011.safetensors",
+        "transformer.h.13.ln_2.weight": "model-00004-of-00011.safetensors",
+        "transformer.h.13.mlp.c_fc.bias": "model-00004-of-00011.safetensors",
+        "transformer.h.13.mlp.c_fc.weight": "model-00004-of-00011.safetensors",
+        "transformer.h.13.mlp.c_proj.bias": "model-00004-of-00011.safetensors",
+        "transformer.h.13.mlp.c_proj.weight": "model-00004-of-00011.safetensors",
+        "transformer.h.14.attn.c_attn.bias": "model-00004-of-00011.safetensors",
+        "transformer.h.14.attn.c_attn.weight": "model-00004-of-00011.safetensors",
+        "transformer.h.14.attn.c_proj.bias": "model-00005-of-00011.safetensors",
+        "transformer.h.14.attn.c_proj.weight": "model-00005-of-00011.safetensors",
+        "transformer.h.14.ln_1.bias": "model-00004-of-00011.safetensors",
+        "transformer.h.14.ln_1.weight": "model-00004-of-00011.safetensors",
+        "transformer.h.14.ln_2.bias": "model-00005-of-00011.safetensors",
+        "transformer.h.14.ln_2.weight": "model-00005-of-00011.safetensors",
+        "transformer.h.14.mlp.c_fc.bias": "model-00005-of-00011.safetensors",
+        "transformer.h.14.mlp.c_fc.weight": "model-00005-of-00011.safetensors",
+        "transformer.h.14.mlp.c_proj.bias": "model-00005-of-00011.safetensors",
+        "transformer.h.14.mlp.c_proj.weight": "model-00005-of-00011.safetensors",
+        "transformer.h.15.attn.c_attn.bias": "model-00005-of-00011.safetensors",
+        "transformer.h.15.attn.c_attn.weight": "model-00005-of-00011.safetensors",
+        "transformer.h.15.attn.c_proj.bias": "model-00005-of-00011.safetensors",
+        "transformer.h.15.attn.c_proj.weight": "model-00005-of-00011.safetensors",
+        "transformer.h.15.ln_1.bias": "model-00005-of-00011.safetensors",
+        "transformer.h.15.ln_1.weight": "model-00005-of-00011.safetensors",
+        "transformer.h.15.ln_2.bias": "model-00005-of-00011.safetensors",
+        "transformer.h.15.ln_2.weight": "model-00005-of-00011.safetensors",
+        "transformer.h.15.mlp.c_fc.bias": "model-00005-of-00011.safetensors",
+        "transformer.h.15.mlp.c_fc.weight": "model-00005-of-00011.safetensors",
+        "transformer.h.15.mlp.c_proj.bias": "model-00005-of-00011.safetensors",
+        "transformer.h.15.mlp.c_proj.weight": "model-00005-of-00011.safetensors",
+        "transformer.h.16.attn.c_attn.bias": "model-00005-of-00011.safetensors",
+        "transformer.h.16.attn.c_attn.weight": "model-00005-of-00011.safetensors",
+        "transformer.h.16.attn.c_proj.bias": "model-00005-of-00011.safetensors",
+        "transformer.h.16.attn.c_proj.weight": "model-00005-of-00011.safetensors",
+        "transformer.h.16.ln_1.bias": "model-00005-of-00011.safetensors",
+        "transformer.h.16.ln_1.weight": "model-00005-of-00011.safetensors",
+        "transformer.h.16.ln_2.bias": "model-00005-of-00011.safetensors",
+        "transformer.h.16.ln_2.weight": "model-00005-of-00011.safetensors",
+        "transformer.h.16.mlp.c_fc.bias": "model-00005-of-00011.safetensors",
+        "transformer.h.16.mlp.c_fc.weight": "model-00005-of-00011.safetensors",
+        "transformer.h.16.mlp.c_proj.bias": "model-00005-of-00011.safetensors",
+        "transformer.h.16.mlp.c_proj.weight": "model-00005-of-00011.safetensors",
+        "transformer.h.17.attn.c_attn.bias": "model-00005-of-00011.safetensors",
+        "transformer.h.17.attn.c_attn.weight": "model-00005-of-00011.safetensors",
+        "transformer.h.17.attn.c_proj.bias": "model-00005-of-00011.safetensors",
+        "transformer.h.17.attn.c_proj.weight": "model-00005-of-00011.safetensors",
+        "transformer.h.17.ln_1.bias": "model-00005-of-00011.safetensors",
+        "transformer.h.17.ln_1.weight": "model-00005-of-00011.safetensors",
+        "transformer.h.17.ln_2.bias": "model-00005-of-00011.safetensors",
+        "transformer.h.17.ln_2.weight": "model-00005-of-00011.safetensors",
+        "transformer.h.17.mlp.c_fc.bias": "model-00005-of-00011.safetensors",
+        "transformer.h.17.mlp.c_fc.weight": "model-00005-of-00011.safetensors",
+        "transformer.h.17.mlp.c_proj.bias": "model-00005-of-00011.safetensors",
+        "transformer.h.17.mlp.c_proj.weight": "model-00005-of-00011.safetensors",
+        "transformer.h.18.attn.c_attn.bias": "model-00006-of-00011.safetensors",
+        "transformer.h.18.attn.c_attn.weight": "model-00006-of-00011.safetensors",
+        "transformer.h.18.attn.c_proj.bias": "model-00006-of-00011.safetensors",
+        "transformer.h.18.attn.c_proj.weight": "model-00006-of-00011.safetensors",
+        "transformer.h.18.ln_1.bias": "model-00005-of-00011.safetensors",
+        "transformer.h.18.ln_1.weight": "model-00005-of-00011.safetensors",
+        "transformer.h.18.ln_2.bias": "model-00006-of-00011.safetensors",
+        "transformer.h.18.ln_2.weight": "model-00006-of-00011.safetensors",
+        "transformer.h.18.mlp.c_fc.bias": "model-00006-of-00011.safetensors",
+        "transformer.h.18.mlp.c_fc.weight": "model-00006-of-00011.safetensors",
+        "transformer.h.18.mlp.c_proj.bias": "model-00006-of-00011.safetensors",
+        "transformer.h.18.mlp.c_proj.weight": "model-00006-of-00011.safetensors",
+        "transformer.h.19.attn.c_attn.bias": "model-00006-of-00011.safetensors",
+        "transformer.h.19.attn.c_attn.weight": "model-00006-of-00011.safetensors",
+        "transformer.h.19.attn.c_proj.bias": "model-00006-of-00011.safetensors",
+        "transformer.h.19.attn.c_proj.weight": "model-00006-of-00011.safetensors",
+        "transformer.h.19.ln_1.bias": "model-00006-of-00011.safetensors",
+        "transformer.h.19.ln_1.weight": "model-00006-of-00011.safetensors",
+        "transformer.h.19.ln_2.bias": "model-00006-of-00011.safetensors",
+        "transformer.h.19.ln_2.weight": "model-00006-of-00011.safetensors",
+        "transformer.h.19.mlp.c_fc.bias": "model-00006-of-00011.safetensors",
+        "transformer.h.19.mlp.c_fc.weight": "model-00006-of-00011.safetensors",
+        "transformer.h.19.mlp.c_proj.bias": "model-00006-of-00011.safetensors",
+        "transformer.h.19.mlp.c_proj.weight": "model-00006-of-00011.safetensors",
+        "transformer.h.2.attn.c_attn.bias": "model-00001-of-00011.safetensors",
+        "transformer.h.2.attn.c_attn.weight": "model-00001-of-00011.safetensors",
+        "transformer.h.2.attn.c_proj.bias": "model-00001-of-00011.safetensors",
+        "transformer.h.2.attn.c_proj.weight": "model-00001-of-00011.safetensors",
+        "transformer.h.2.ln_1.bias": "model-00001-of-00011.safetensors",
+        "transformer.h.2.ln_1.weight": "model-00001-of-00011.safetensors",
+        "transformer.h.2.ln_2.bias": "model-00001-of-00011.safetensors",
+        "transformer.h.2.ln_2.weight": "model-00001-of-00011.safetensors",
+        "transformer.h.2.mlp.c_fc.bias": "model-00001-of-00011.safetensors",
+        "transformer.h.2.mlp.c_fc.weight": "model-00001-of-00011.safetensors",
+        "transformer.h.2.mlp.c_proj.bias": "model-00001-of-00011.safetensors",
+        "transformer.h.2.mlp.c_proj.weight": "model-00001-of-00011.safetensors",
+        "transformer.h.20.attn.c_attn.bias": "model-00006-of-00011.safetensors",
+        "transformer.h.20.attn.c_attn.weight": "model-00006-of-00011.safetensors",
+        "transformer.h.20.attn.c_proj.bias": "model-00006-of-00011.safetensors",
+        "transformer.h.20.attn.c_proj.weight": "model-00006-of-00011.safetensors",
+        "transformer.h.20.ln_1.bias": "model-00006-of-00011.safetensors",
+        "transformer.h.20.ln_1.weight": "model-00006-of-00011.safetensors",
+        "transformer.h.20.ln_2.bias": "model-00006-of-00011.safetensors",
+        "transformer.h.20.ln_2.weight": "model-00006-of-00011.safetensors",
+        "transformer.h.20.mlp.c_fc.bias": "model-00006-of-00011.safetensors",
+        "transformer.h.20.mlp.c_fc.weight": "model-00006-of-00011.safetensors",
+        "transformer.h.20.mlp.c_proj.bias": "model-00006-of-00011.safetensors",
+        "transformer.h.20.mlp.c_proj.weight": "model-00006-of-00011.safetensors",
+        "transformer.h.21.attn.c_attn.bias": "model-00006-of-00011.safetensors",
+        "transformer.h.21.attn.c_attn.weight": "model-00006-of-00011.safetensors",
+        "transformer.h.21.attn.c_proj.bias": "model-00006-of-00011.safetensors",
+        "transformer.h.21.attn.c_proj.weight": "model-00006-of-00011.safetensors",
+        "transformer.h.21.ln_1.bias": "model-00006-of-00011.safetensors",
+        "transformer.h.21.ln_1.weight": "model-00006-of-00011.safetensors",
+        "transformer.h.21.ln_2.bias": "model-00006-of-00011.safetensors",
+        "transformer.h.21.ln_2.weight": "model-00006-of-00011.safetensors",
+        "transformer.h.21.mlp.c_fc.bias": "model-00006-of-00011.safetensors",
+        "transformer.h.21.mlp.c_fc.weight": "model-00006-of-00011.safetensors",
+        "transformer.h.21.mlp.c_proj.bias": "model-00007-of-00011.safetensors",
+        "transformer.h.21.mlp.c_proj.weight": "model-00007-of-00011.safetensors",
+        "transformer.h.22.attn.c_attn.bias": "model-00007-of-00011.safetensors",
+        "transformer.h.22.attn.c_attn.weight": "model-00007-of-00011.safetensors",
+        "transformer.h.22.attn.c_proj.bias": "model-00007-of-00011.safetensors",
+        "transformer.h.22.attn.c_proj.weight": "model-00007-of-00011.safetensors",
+        "transformer.h.22.ln_1.bias": "model-00007-of-00011.safetensors",
+        "transformer.h.22.ln_1.weight": "model-00007-of-00011.safetensors",
+        "transformer.h.22.ln_2.bias": "model-00007-of-00011.safetensors",
+        "transformer.h.22.ln_2.weight": "model-00007-of-00011.safetensors",
+        "transformer.h.22.mlp.c_fc.bias": "model-00007-of-00011.safetensors",
+        "transformer.h.22.mlp.c_fc.weight": "model-00007-of-00011.safetensors",
+        "transformer.h.22.mlp.c_proj.bias": "model-00007-of-00011.safetensors",
+        "transformer.h.22.mlp.c_proj.weight": "model-00007-of-00011.safetensors",
+        "transformer.h.23.attn.c_attn.bias": "model-00007-of-00011.safetensors",
+        "transformer.h.23.attn.c_attn.weight": "model-00007-of-00011.safetensors",
+        "transformer.h.23.attn.c_proj.bias": "model-00007-of-00011.safetensors",
+        "transformer.h.23.attn.c_proj.weight": "model-00007-of-00011.safetensors",
+        "transformer.h.23.ln_1.bias": "model-00007-of-00011.safetensors",
+        "transformer.h.23.ln_1.weight": "model-00007-of-00011.safetensors",
+        "transformer.h.23.ln_2.bias": "model-00007-of-00011.safetensors",
+        "transformer.h.23.ln_2.weight": "model-00007-of-00011.safetensors",
+        "transformer.h.23.mlp.c_fc.bias": "model-00007-of-00011.safetensors",
+        "transformer.h.23.mlp.c_fc.weight": "model-00007-of-00011.safetensors",
+        "transformer.h.23.mlp.c_proj.bias": "model-00007-of-00011.safetensors",
+        "transformer.h.23.mlp.c_proj.weight": "model-00007-of-00011.safetensors",
+        "transformer.h.24.attn.c_attn.bias": "model-00007-of-00011.safetensors",
+        "transformer.h.24.attn.c_attn.weight": "model-00007-of-00011.safetensors",
+        "transformer.h.24.attn.c_proj.bias": "model-00007-of-00011.safetensors",
+        "transformer.h.24.attn.c_proj.weight": "model-00007-of-00011.safetensors",
+        "transformer.h.24.ln_1.bias": "model-00007-of-00011.safetensors",
+        "transformer.h.24.ln_1.weight": "model-00007-of-00011.safetensors",
+        "transformer.h.24.ln_2.bias": "model-00007-of-00011.safetensors",
+        "transformer.h.24.ln_2.weight": "model-00007-of-00011.safetensors",
+        "transformer.h.24.mlp.c_fc.bias": "model-00007-of-00011.safetensors",
+        "transformer.h.24.mlp.c_fc.weight": "model-00007-of-00011.safetensors",
+        "transformer.h.24.mlp.c_proj.bias": "model-00007-of-00011.safetensors",
+        "transformer.h.24.mlp.c_proj.weight": "model-00007-of-00011.safetensors",
+        "transformer.h.25.attn.c_attn.bias": "model-00007-of-00011.safetensors",
+        "transformer.h.25.attn.c_attn.weight": "model-00007-of-00011.safetensors",
+        "transformer.h.25.attn.c_proj.bias": "model-00007-of-00011.safetensors",
+        "transformer.h.25.attn.c_proj.weight": "model-00007-of-00011.safetensors",
+        "transformer.h.25.ln_1.bias": "model-00007-of-00011.safetensors",
+        "transformer.h.25.ln_1.weight": "model-00007-of-00011.safetensors",
+        "transformer.h.25.ln_2.bias": "model-00007-of-00011.safetensors",
+        "transformer.h.25.ln_2.weight": "model-00007-of-00011.safetensors",
+        "transformer.h.25.mlp.c_fc.bias": "model-00008-of-00011.safetensors",
+        "transformer.h.25.mlp.c_fc.weight": "model-00008-of-00011.safetensors",
+        "transformer.h.25.mlp.c_proj.bias": "model-00008-of-00011.safetensors",
+        "transformer.h.25.mlp.c_proj.weight": "model-00008-of-00011.safetensors",
+        "transformer.h.26.attn.c_attn.bias": "model-00008-of-00011.safetensors",
+        "transformer.h.26.attn.c_attn.weight": "model-00008-of-00011.safetensors",
+        "transformer.h.26.attn.c_proj.bias": "model-00008-of-00011.safetensors",
+        "transformer.h.26.attn.c_proj.weight": "model-00008-of-00011.safetensors",
+        "transformer.h.26.ln_1.bias": "model-00008-of-00011.safetensors",
+        "transformer.h.26.ln_1.weight": "model-00008-of-00011.safetensors",
+        "transformer.h.26.ln_2.bias": "model-00008-of-00011.safetensors",
+        "transformer.h.26.ln_2.weight": "model-00008-of-00011.safetensors",
+        "transformer.h.26.mlp.c_fc.bias": "model-00008-of-00011.safetensors",
+        "transformer.h.26.mlp.c_fc.weight": "model-00008-of-00011.safetensors",
+        "transformer.h.26.mlp.c_proj.bias": "model-00008-of-00011.safetensors",
+        "transformer.h.26.mlp.c_proj.weight": "model-00008-of-00011.safetensors",
+        "transformer.h.27.attn.c_attn.bias": "model-00008-of-00011.safetensors",
+        "transformer.h.27.attn.c_attn.weight": "model-00008-of-00011.safetensors",
+        "transformer.h.27.attn.c_proj.bias": "model-00008-of-00011.safetensors",
+        "transformer.h.27.attn.c_proj.weight": "model-00008-of-00011.safetensors",
+        "transformer.h.27.ln_1.bias": "model-00008-of-00011.safetensors",
+        "transformer.h.27.ln_1.weight": "model-00008-of-00011.safetensors",
+        "transformer.h.27.ln_2.bias": "model-00008-of-00011.safetensors",
+        "transformer.h.27.ln_2.weight": "model-00008-of-00011.safetensors",
+        "transformer.h.27.mlp.c_fc.bias": "model-00008-of-00011.safetensors",
+        "transformer.h.27.mlp.c_fc.weight": "model-00008-of-00011.safetensors",
+        "transformer.h.27.mlp.c_proj.bias": "model-00008-of-00011.safetensors",
+        "transformer.h.27.mlp.c_proj.weight": "model-00008-of-00011.safetensors",
+        "transformer.h.28.attn.c_attn.bias": "model-00008-of-00011.safetensors",
+        "transformer.h.28.attn.c_attn.weight": "model-00008-of-00011.safetensors",
+        "transformer.h.28.attn.c_proj.bias": "model-00008-of-00011.safetensors",
+        "transformer.h.28.attn.c_proj.weight": "model-00008-of-00011.safetensors",
+        "transformer.h.28.ln_1.bias": "model-00008-of-00011.safetensors",
+        "transformer.h.28.ln_1.weight": "model-00008-of-00011.safetensors",
+        "transformer.h.28.ln_2.bias": "model-00008-of-00011.safetensors",
+        "transformer.h.28.ln_2.weight": "model-00008-of-00011.safetensors",
+        "transformer.h.28.mlp.c_fc.bias": "model-00008-of-00011.safetensors",
+        "transformer.h.28.mlp.c_fc.weight": "model-00008-of-00011.safetensors",
+        "transformer.h.28.mlp.c_proj.bias": "model-00008-of-00011.safetensors",
+        "transformer.h.28.mlp.c_proj.weight": "model-00008-of-00011.safetensors",
+        "transformer.h.29.attn.c_attn.bias": "model-00008-of-00011.safetensors",
+        "transformer.h.29.attn.c_attn.weight": "model-00008-of-00011.safetensors",
+        "transformer.h.29.attn.c_proj.bias": "model-00009-of-00011.safetensors",
+        "transformer.h.29.attn.c_proj.weight": "model-00009-of-00011.safetensors",
+        "transformer.h.29.ln_1.bias": "model-00008-of-00011.safetensors",
+        "transformer.h.29.ln_1.weight": "model-00008-of-00011.safetensors",
+        "transformer.h.29.ln_2.bias": "model-00009-of-00011.safetensors",
+        "transformer.h.29.ln_2.weight": "model-00009-of-00011.safetensors",
+        "transformer.h.29.mlp.c_fc.bias": "model-00009-of-00011.safetensors",
+        "transformer.h.29.mlp.c_fc.weight": "model-00009-of-00011.safetensors",
+        "transformer.h.29.mlp.c_proj.bias": "model-00009-of-00011.safetensors",
+        "transformer.h.29.mlp.c_proj.weight": "model-00009-of-00011.safetensors",
+        "transformer.h.3.attn.c_attn.bias": "model-00002-of-00011.safetensors",
+        "transformer.h.3.attn.c_attn.weight": "model-00002-of-00011.safetensors",
+        "transformer.h.3.attn.c_proj.bias": "model-00002-of-00011.safetensors",
+        "transformer.h.3.attn.c_proj.weight": "model-00002-of-00011.safetensors",
+        "transformer.h.3.ln_1.bias": "model-00001-of-00011.safetensors",
+        "transformer.h.3.ln_1.weight": "model-00001-of-00011.safetensors",
+        "transformer.h.3.ln_2.bias": "model-00002-of-00011.safetensors",
+        "transformer.h.3.ln_2.weight": "model-00002-of-00011.safetensors",
+        "transformer.h.3.mlp.c_fc.bias": "model-00002-of-00011.safetensors",
+        "transformer.h.3.mlp.c_fc.weight": "model-00002-of-00011.safetensors",
+        "transformer.h.3.mlp.c_proj.bias": "model-00002-of-00011.safetensors",
+        "transformer.h.3.mlp.c_proj.weight": "model-00002-of-00011.safetensors",
+        "transformer.h.30.attn.c_attn.bias": "model-00009-of-00011.safetensors",
+        "transformer.h.30.attn.c_attn.weight": "model-00009-of-00011.safetensors",
+        "transformer.h.30.attn.c_proj.bias": "model-00009-of-00011.safetensors",
+        "transformer.h.30.attn.c_proj.weight": "model-00009-of-00011.safetensors",
+        "transformer.h.30.ln_1.bias": "model-00009-of-00011.safetensors",
+        "transformer.h.30.ln_1.weight": "model-00009-of-00011.safetensors",
+        "transformer.h.30.ln_2.bias": "model-00009-of-00011.safetensors",
+        "transformer.h.30.ln_2.weight": "model-00009-of-00011.safetensors",
+        "transformer.h.30.mlp.c_fc.bias": "model-00009-of-00011.safetensors",
+        "transformer.h.30.mlp.c_fc.weight": "model-00009-of-00011.safetensors",
+        "transformer.h.30.mlp.c_proj.bias": "model-00009-of-00011.safetensors",
+        "transformer.h.30.mlp.c_proj.weight": "model-00009-of-00011.safetensors",
+        "transformer.h.31.attn.c_attn.bias": "model-00009-of-00011.safetensors",
+        "transformer.h.31.attn.c_attn.weight": "model-00009-of-00011.safetensors",
+        "transformer.h.31.attn.c_proj.bias": "model-00009-of-00011.safetensors",
+        "transformer.h.31.attn.c_proj.weight": "model-00009-of-00011.safetensors",
+        "transformer.h.31.ln_1.bias": "model-00009-of-00011.safetensors",
+        "transformer.h.31.ln_1.weight": "model-00009-of-00011.safetensors",
+        "transformer.h.31.ln_2.bias": "model-00009-of-00011.safetensors",
+        "transformer.h.31.ln_2.weight": "model-00009-of-00011.safetensors",
+        "transformer.h.31.mlp.c_fc.bias": "model-00009-of-00011.safetensors",
+        "transformer.h.31.mlp.c_fc.weight": "model-00009-of-00011.safetensors",
+        "transformer.h.31.mlp.c_proj.bias": "model-00009-of-00011.safetensors",
+        "transformer.h.31.mlp.c_proj.weight": "model-00009-of-00011.safetensors",
+        "transformer.h.32.attn.c_attn.bias": "model-00009-of-00011.safetensors",
+        "transformer.h.32.attn.c_attn.weight": "model-00009-of-00011.safetensors",
+        "transformer.h.32.attn.c_proj.bias": "model-00009-of-00011.safetensors",
+        "transformer.h.32.attn.c_proj.weight": "model-00009-of-00011.safetensors",
+        "transformer.h.32.ln_1.bias": "model-00009-of-00011.safetensors",
+        "transformer.h.32.ln_1.weight": "model-00009-of-00011.safetensors",
+        "transformer.h.32.ln_2.bias": "model-00009-of-00011.safetensors",
+        "transformer.h.32.ln_2.weight": "model-00009-of-00011.safetensors",
+        "transformer.h.32.mlp.c_fc.bias": "model-00009-of-00011.safetensors",
+        "transformer.h.32.mlp.c_fc.weight": "model-00009-of-00011.safetensors",
+        "transformer.h.32.mlp.c_proj.bias": "model-00009-of-00011.safetensors",
+        "transformer.h.32.mlp.c_proj.weight": "model-00009-of-00011.safetensors",
+        "transformer.h.33.attn.c_attn.bias": "model-00010-of-00011.safetensors",
+        "transformer.h.33.attn.c_attn.weight": "model-00010-of-00011.safetensors",
+        "transformer.h.33.attn.c_proj.bias": "model-00010-of-00011.safetensors",
+        "transformer.h.33.attn.c_proj.weight": "model-00010-of-00011.safetensors",
+        "transformer.h.33.ln_1.bias": "model-00009-of-00011.safetensors",
+        "transformer.h.33.ln_1.weight": "model-00009-of-00011.safetensors",
+        "transformer.h.33.ln_2.bias": "model-00010-of-00011.safetensors",
+        "transformer.h.33.ln_2.weight": "model-00010-of-00011.safetensors",
+        "transformer.h.33.mlp.c_fc.bias": "model-00010-of-00011.safetensors",
+        "transformer.h.33.mlp.c_fc.weight": "model-00010-of-00011.safetensors",
+        "transformer.h.33.mlp.c_proj.bias": "model-00010-of-00011.safetensors",
+        "transformer.h.33.mlp.c_proj.weight": "model-00010-of-00011.safetensors",
+        "transformer.h.34.attn.c_attn.bias": "model-00010-of-00011.safetensors",
+        "transformer.h.34.attn.c_attn.weight": "model-00010-of-00011.safetensors",
+        "transformer.h.34.attn.c_proj.bias": "model-00010-of-00011.safetensors",
+        "transformer.h.34.attn.c_proj.weight": "model-00010-of-00011.safetensors",
+        "transformer.h.34.ln_1.bias": "model-00010-of-00011.safetensors",
+        "transformer.h.34.ln_1.weight": "model-00010-of-00011.safetensors",
+        "transformer.h.34.ln_2.bias": "model-00010-of-00011.safetensors",
+        "transformer.h.34.ln_2.weight": "model-00010-of-00011.safetensors",
+        "transformer.h.34.mlp.c_fc.bias": "model-00010-of-00011.safetensors",
+        "transformer.h.34.mlp.c_fc.weight": "model-00010-of-00011.safetensors",
+        "transformer.h.34.mlp.c_proj.bias": "model-00010-of-00011.safetensors",
+        "transformer.h.34.mlp.c_proj.weight": "model-00010-of-00011.safetensors",
+        "transformer.h.35.attn.c_attn.bias": "model-00010-of-00011.safetensors",
+        "transformer.h.35.attn.c_attn.weight": "model-00010-of-00011.safetensors",
+        "transformer.h.35.attn.c_proj.bias": "model-00010-of-00011.safetensors",
+        "transformer.h.35.attn.c_proj.weight": "model-00010-of-00011.safetensors",
+        "transformer.h.35.ln_1.bias": "model-00010-of-00011.safetensors",
+        "transformer.h.35.ln_1.weight": "model-00010-of-00011.safetensors",
+        "transformer.h.35.ln_2.bias": "model-00010-of-00011.safetensors",
+        "transformer.h.35.ln_2.weight": "model-00010-of-00011.safetensors",
+        "transformer.h.35.mlp.c_fc.bias": "model-00010-of-00011.safetensors",
+        "transformer.h.35.mlp.c_fc.weight": "model-00010-of-00011.safetensors",
+        "transformer.h.35.mlp.c_proj.bias": "model-00010-of-00011.safetensors",
+        "transformer.h.35.mlp.c_proj.weight": "model-00010-of-00011.safetensors",
+        "transformer.h.36.attn.c_attn.bias": "model-00010-of-00011.safetensors",
+        "transformer.h.36.attn.c_attn.weight": "model-00010-of-00011.safetensors",
+        "transformer.h.36.attn.c_proj.bias": "model-00010-of-00011.safetensors",
+        "transformer.h.36.attn.c_proj.weight": "model-00010-of-00011.safetensors",
+        "transformer.h.36.ln_1.bias": "model-00010-of-00011.safetensors",
+        "transformer.h.36.ln_1.weight": "model-00010-of-00011.safetensors",
+        "transformer.h.36.ln_2.bias": "model-00010-of-00011.safetensors",
+        "transformer.h.36.ln_2.weight": "model-00010-of-00011.safetensors",
+        "transformer.h.36.mlp.c_fc.bias": "model-00010-of-00011.safetensors",
+        "transformer.h.36.mlp.c_fc.weight": "model-00010-of-00011.safetensors",
+        "transformer.h.36.mlp.c_proj.bias": "model-00011-of-00011.safetensors",
+        "transformer.h.36.mlp.c_proj.weight": "model-00011-of-00011.safetensors",
+        "transformer.h.37.attn.c_attn.bias": "model-00011-of-00011.safetensors",
+        "transformer.h.37.attn.c_attn.weight": "model-00011-of-00011.safetensors",
+        "transformer.h.37.attn.c_proj.bias": "model-00011-of-00011.safetensors",
+        "transformer.h.37.attn.c_proj.weight": "model-00011-of-00011.safetensors",
+        "transformer.h.37.ln_1.bias": "model-00011-of-00011.safetensors",
+        "transformer.h.37.ln_1.weight": "model-00011-of-00011.safetensors",
+        "transformer.h.37.ln_2.bias": "model-00011-of-00011.safetensors",
+        "transformer.h.37.ln_2.weight": "model-00011-of-00011.safetensors",
+        "transformer.h.37.mlp.c_fc.bias": "model-00011-of-00011.safetensors",
+        "transformer.h.37.mlp.c_fc.weight": "model-00011-of-00011.safetensors",
+        "transformer.h.37.mlp.c_proj.bias": "model-00011-of-00011.safetensors",
+        "transformer.h.37.mlp.c_proj.weight": "model-00011-of-00011.safetensors",
+        "transformer.h.38.attn.c_attn.bias": "model-00011-of-00011.safetensors",
+        "transformer.h.38.attn.c_attn.weight": "model-00011-of-00011.safetensors",
+        "transformer.h.38.attn.c_proj.bias": "model-00011-of-00011.safetensors",
+        "transformer.h.38.attn.c_proj.weight": "model-00011-of-00011.safetensors",
+        "transformer.h.38.ln_1.bias": "model-00011-of-00011.safetensors",
+        "transformer.h.38.ln_1.weight": "model-00011-of-00011.safetensors",
+        "transformer.h.38.ln_2.bias": "model-00011-of-00011.safetensors",
+        "transformer.h.38.ln_2.weight": "model-00011-of-00011.safetensors",
+        "transformer.h.38.mlp.c_fc.bias": "model-00011-of-00011.safetensors",
+        "transformer.h.38.mlp.c_fc.weight": "model-00011-of-00011.safetensors",
+        "transformer.h.38.mlp.c_proj.bias": "model-00011-of-00011.safetensors",
+        "transformer.h.38.mlp.c_proj.weight": "model-00011-of-00011.safetensors",
+        "transformer.h.39.attn.c_attn.bias": "model-00011-of-00011.safetensors",
+        "transformer.h.39.attn.c_attn.weight": "model-00011-of-00011.safetensors",
+        "transformer.h.39.attn.c_proj.bias": "model-00011-of-00011.safetensors",
+        "transformer.h.39.attn.c_proj.weight": "model-00011-of-00011.safetensors",
+        "transformer.h.39.ln_1.bias": "model-00011-of-00011.safetensors",
+        "transformer.h.39.ln_1.weight": "model-00011-of-00011.safetensors",
+        "transformer.h.39.ln_2.bias": "model-00011-of-00011.safetensors",
+        "transformer.h.39.ln_2.weight": "model-00011-of-00011.safetensors",
+        "transformer.h.39.mlp.c_fc.bias": "model-00011-of-00011.safetensors",
+        "transformer.h.39.mlp.c_fc.weight": "model-00011-of-00011.safetensors",
+        "transformer.h.39.mlp.c_proj.bias": "model-00011-of-00011.safetensors",
+        "transformer.h.39.mlp.c_proj.weight": "model-00011-of-00011.safetensors",
+        "transformer.h.4.attn.c_attn.bias": "model-00002-of-00011.safetensors",
+        "transformer.h.4.attn.c_attn.weight": "model-00002-of-00011.safetensors",
+        "transformer.h.4.attn.c_proj.bias": "model-00002-of-00011.safetensors",
+        "transformer.h.4.attn.c_proj.weight": "model-00002-of-00011.safetensors",
+        "transformer.h.4.ln_1.bias": "model-00002-of-00011.safetensors",
+        "transformer.h.4.ln_1.weight": "model-00002-of-00011.safetensors",
+        "transformer.h.4.ln_2.bias": "model-00002-of-00011.safetensors",
+        "transformer.h.4.ln_2.weight": "model-00002-of-00011.safetensors",
+        "transformer.h.4.mlp.c_fc.bias": "model-00002-of-00011.safetensors",
+        "transformer.h.4.mlp.c_fc.weight": "model-00002-of-00011.safetensors",
+        "transformer.h.4.mlp.c_proj.bias": "model-00002-of-00011.safetensors",
+        "transformer.h.4.mlp.c_proj.weight": "model-00002-of-00011.safetensors",
+        "transformer.h.5.attn.c_attn.bias": "model-00002-of-00011.safetensors",
+        "transformer.h.5.attn.c_attn.weight": "model-00002-of-00011.safetensors",
+        "transformer.h.5.attn.c_proj.bias": "model-00002-of-00011.safetensors",
+        "transformer.h.5.attn.c_proj.weight": "model-00002-of-00011.safetensors",
+        "transformer.h.5.ln_1.bias": "model-00002-of-00011.safetensors",
+        "transformer.h.5.ln_1.weight": "model-00002-of-00011.safetensors",
+        "transformer.h.5.ln_2.bias": "model-00002-of-00011.safetensors",
+        "transformer.h.5.ln_2.weight": "model-00002-of-00011.safetensors",
+        "transformer.h.5.mlp.c_fc.bias": "model-00002-of-00011.safetensors",
+        "transformer.h.5.mlp.c_fc.weight": "model-00002-of-00011.safetensors",
+        "transformer.h.5.mlp.c_proj.bias": "model-00002-of-00011.safetensors",
+        "transformer.h.5.mlp.c_proj.weight": "model-00002-of-00011.safetensors",
+        "transformer.h.6.attn.c_attn.bias": "model-00002-of-00011.safetensors",
+        "transformer.h.6.attn.c_attn.weight": "model-00002-of-00011.safetensors",
+        "transformer.h.6.attn.c_proj.bias": "model-00002-of-00011.safetensors",
+        "transformer.h.6.attn.c_proj.weight": "model-00002-of-00011.safetensors",
+        "transformer.h.6.ln_1.bias": "model-00002-of-00011.safetensors",
+        "transformer.h.6.ln_1.weight": "model-00002-of-00011.safetensors",
+        "transformer.h.6.ln_2.bias": "model-00002-of-00011.safetensors",
+        "transformer.h.6.ln_2.weight": "model-00002-of-00011.safetensors",
+        "transformer.h.6.mlp.c_fc.bias": "model-00002-of-00011.safetensors",
+        "transformer.h.6.mlp.c_fc.weight": "model-00002-of-00011.safetensors",
+        "transformer.h.6.mlp.c_proj.bias": "model-00003-of-00011.safetensors",
+        "transformer.h.6.mlp.c_proj.weight": "model-00003-of-00011.safetensors",
+        "transformer.h.7.attn.c_attn.bias": "model-00003-of-00011.safetensors",
+        "transformer.h.7.attn.c_attn.weight": "model-00003-of-00011.safetensors",
+        "transformer.h.7.attn.c_proj.bias": "model-00003-of-00011.safetensors",
+        "transformer.h.7.attn.c_proj.weight": "model-00003-of-00011.safetensors",
+        "transformer.h.7.ln_1.bias": "model-00003-of-00011.safetensors",
+        "transformer.h.7.ln_1.weight": "model-00003-of-00011.safetensors",
+        "transformer.h.7.ln_2.bias": "model-00003-of-00011.safetensors",
+        "transformer.h.7.ln_2.weight": "model-00003-of-00011.safetensors",
+        "transformer.h.7.mlp.c_fc.bias": "model-00003-of-00011.safetensors",
+        "transformer.h.7.mlp.c_fc.weight": "model-00003-of-00011.safetensors",
+        "transformer.h.7.mlp.c_proj.bias": "model-00003-of-00011.safetensors",
+        "transformer.h.7.mlp.c_proj.weight": "model-00003-of-00011.safetensors",
+        "transformer.h.8.attn.c_attn.bias": "model-00003-of-00011.safetensors",
+        "transformer.h.8.attn.c_attn.weight": "model-00003-of-00011.safetensors",
+        "transformer.h.8.attn.c_proj.bias": "model-00003-of-00011.safetensors",
+        "transformer.h.8.attn.c_proj.weight": "model-00003-of-00011.safetensors",
+        "transformer.h.8.ln_1.bias": "model-00003-of-00011.safetensors",
+        "transformer.h.8.ln_1.weight": "model-00003-of-00011.safetensors",
+        "transformer.h.8.ln_2.bias": "model-00003-of-00011.safetensors",
+        "transformer.h.8.ln_2.weight": "model-00003-of-00011.safetensors",
+        "transformer.h.8.mlp.c_fc.bias": "model-00003-of-00011.safetensors",
+        "transformer.h.8.mlp.c_fc.weight": "model-00003-of-00011.safetensors",
+        "transformer.h.8.mlp.c_proj.bias": "model-00003-of-00011.safetensors",
+        "transformer.h.8.mlp.c_proj.weight": "model-00003-of-00011.safetensors",
+        "transformer.h.9.attn.c_attn.bias": "model-00003-of-00011.safetensors",
+        "transformer.h.9.attn.c_attn.weight": "model-00003-of-00011.safetensors",
+        "transformer.h.9.attn.c_proj.bias": "model-00003-of-00011.safetensors",
+        "transformer.h.9.attn.c_proj.weight": "model-00003-of-00011.safetensors",
+        "transformer.h.9.ln_1.bias": "model-00003-of-00011.safetensors",
+        "transformer.h.9.ln_1.weight": "model-00003-of-00011.safetensors",
+        "transformer.h.9.ln_2.bias": "model-00003-of-00011.safetensors",
+        "transformer.h.9.ln_2.weight": "model-00003-of-00011.safetensors",
+        "transformer.h.9.mlp.c_fc.bias": "model-00003-of-00011.safetensors",
+        "transformer.h.9.mlp.c_fc.weight": "model-00003-of-00011.safetensors",
+        "transformer.h.9.mlp.c_proj.bias": "model-00003-of-00011.safetensors",
+        "transformer.h.9.mlp.c_proj.weight": "model-00003-of-00011.safetensors",
+        "transformer.ln_f.bias": "model-00011-of-00011.safetensors",
+        "transformer.ln_f.weight": "model-00011-of-00011.safetensors",
+        "transformer.wpe.weight": "model-00001-of-00011.safetensors",
+        "transformer.wte.weight": "model-00001-of-00011.safetensors"
+    }
+}