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:a61563768b6459a77e2d3d439206c63dcec935d96941433afe1b5e995213334d
+size 4977967584

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e54f4d55e4edcf495e7f2f6d71b0d25b661824e4869c1697ddc84e1ba78ab6a5
+size 268576780

model.safetensors.index.json

@@ -0,0 +1,300 @@
+{
+    "metadata": {
+        "total_size": 5246509060
+    },
+    "weight_map": {
+        "lm_backbone.embed_in.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+        "lm_backbone.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+        "lm_backbone.layers.0.attention.dense.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.0.attention.dense.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.0.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.0.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.0.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.0.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.0.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.1.attention.dense.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.1.attention.dense.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.1.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.1.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.1.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.1.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.1.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.10.attention.dense.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.10.attention.dense.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.10.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.10.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.10.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.10.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.10.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.10.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.10.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.11.attention.dense.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.11.attention.dense.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.11.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.11.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.11.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.11.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.11.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.11.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.11.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.12.attention.dense.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.12.attention.dense.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.12.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.12.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.12.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.12.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.12.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.12.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.12.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.13.attention.dense.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.13.attention.dense.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.13.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.13.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.13.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.13.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.13.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.13.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.13.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.14.attention.dense.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.14.attention.dense.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.14.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.14.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.14.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.14.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.14.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.14.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.14.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.15.attention.dense.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.15.attention.dense.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.15.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.15.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.15.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.15.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.15.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.15.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.15.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.16.attention.dense.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.16.attention.dense.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.16.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.16.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.16.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.16.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.16.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.16.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.16.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.16.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.17.attention.dense.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.17.attention.dense.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.17.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.17.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.17.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.17.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.17.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.17.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.17.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.17.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.18.attention.dense.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.18.attention.dense.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.18.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.18.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.18.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.18.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.18.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.18.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.18.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.18.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.19.attention.dense.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.19.attention.dense.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.19.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.19.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.19.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.19.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.19.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.19.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.19.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.19.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.2.attention.dense.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.2.attention.dense.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.2.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.2.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.2.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.2.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.2.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.20.attention.dense.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.20.attention.dense.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.20.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.20.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.20.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.20.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.20.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.20.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.20.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.20.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.21.attention.dense.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.21.attention.dense.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.21.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.21.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.21.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.21.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.21.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.21.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.21.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.21.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.22.attention.dense.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.22.attention.dense.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.22.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.22.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.22.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.22.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
+        "lm_backbone.layers.22.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+        "lm_backbone.layers.22.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.22.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.22.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.23.attention.dense.bias": "model-00002-of-00002.safetensors",
+        "lm_backbone.layers.23.attention.dense.weight": "model-00002-of-00002.safetensors",
+        "lm_backbone.layers.23.attention.query_key_value.bias": "model-00002-of-00002.safetensors",
+        "lm_backbone.layers.23.attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+        "lm_backbone.layers.23.input_layernorm.bias": "model-00002-of-00002.safetensors",
+        "lm_backbone.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "lm_backbone.layers.23.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
+        "lm_backbone.layers.23.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+        "lm_backbone.layers.23.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
+        "lm_backbone.layers.23.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+        "lm_backbone.layers.23.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
+        "lm_backbone.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "lm_backbone.layers.3.attention.dense.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.3.attention.dense.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.3.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.3.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.3.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.3.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.3.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.3.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.3.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.4.attention.dense.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.4.attention.dense.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.4.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.4.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.4.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.4.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.4.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.4.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.4.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.5.attention.dense.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.5.attention.dense.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.5.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.5.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.5.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.5.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.5.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.5.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.5.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.6.attention.dense.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.6.attention.dense.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.6.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.6.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.6.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.6.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.6.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.6.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.6.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.7.attention.dense.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.7.attention.dense.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.7.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.7.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.7.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.7.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.7.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.7.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.7.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.8.attention.dense.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.8.attention.dense.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.8.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.8.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.8.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.8.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.8.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.8.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.8.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.9.attention.dense.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.9.attention.dense.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.9.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.9.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.9.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.9.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.9.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.9.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.9.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "lm_backbone.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "scalar_head.bias": "model-00002-of-00002.safetensors",
+        "scalar_head.weight": "model-00002-of-00002.safetensors"
+    }
+}