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-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a9ac5dfa2e28bd80edce39525cb483150b7a20651a862e1afa6c6e2a0a02a16
+size 1740647416

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ff6b1e4cfc6ae19d736819f70fd083378625ab3ae314520d3efdf087f997305
+size 1879719496

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2297356b8896dccd05d0be130461985b48da442055768edf5e46265a45ca711
+size 1980374384

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63d996e707af3a9a1ff42d0a51100b1a073f0c649b92bea3d09ecba48dccd8e2
+size 1913282160

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e3b6b61f07e7023cc1ed4ce04edb6971e11a8a36f93e10244c7038a163f7079
+size 1879710960

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff8a3d86d570c34080b8e047e4b0a4f062a0215ef2ef576cfa223a22cdcc9ef3
+size 1879719560

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:697492727810fb4fbc27d70e68bfb00010793fc1f4c3ce81560763bc3fe8efca
+size 1074097968

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e29ce4595da4a1b8f80f87a2e16d7c635d84a2fd8a110271e4fff6a26f02e36a
+size 1069285504

model.safetensors.index.json

@@ -0,0 +1,375 @@
+{
+    "metadata": {
+        "total_size": 13744473856
+    },
+    "weight_map": {
+        "lm_head.weight": "model-00008-of-00008.safetensors",
+        "transformer.final_layernorm.bias": "model-00007-of-00008.safetensors",
+        "transformer.final_layernorm.weight": "model-00007-of-00008.safetensors",
+        "transformer.layers.0.attention.dense.bias": "model-00001-of-00008.safetensors",
+        "transformer.layers.0.attention.dense.weight": "model-00001-of-00008.safetensors",
+        "transformer.layers.0.attention.query_key_value.bias": "model-00001-of-00008.safetensors",
+        "transformer.layers.0.attention.query_key_value.weight": "model-00001-of-00008.safetensors",
+        "transformer.layers.0.attention.rotary_emb.inv_freq": "model-00001-of-00008.safetensors",
+        "transformer.layers.0.input_layernorm.bias": "model-00001-of-00008.safetensors",
+        "transformer.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors",
+        "transformer.layers.0.mlp.dense_4h_to_h.bias": "model-00001-of-00008.safetensors",
+        "transformer.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00008.safetensors",
+        "transformer.layers.0.mlp.dense_h_to_4h.bias": "model-00001-of-00008.safetensors",
+        "transformer.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00008.safetensors",
+        "transformer.layers.0.post_attention_layernorm.bias": "model-00001-of-00008.safetensors",
+        "transformer.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+        "transformer.layers.1.attention.dense.bias": "model-00001-of-00008.safetensors",
+        "transformer.layers.1.attention.dense.weight": "model-00001-of-00008.safetensors",
+        "transformer.layers.1.attention.query_key_value.bias": "model-00001-of-00008.safetensors",
+        "transformer.layers.1.attention.query_key_value.weight": "model-00001-of-00008.safetensors",
+        "transformer.layers.1.attention.rotary_emb.inv_freq": "model-00001-of-00008.safetensors",
+        "transformer.layers.1.input_layernorm.bias": "model-00001-of-00008.safetensors",
+        "transformer.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors",
+        "transformer.layers.1.mlp.dense_4h_to_h.bias": "model-00002-of-00008.safetensors",
+        "transformer.layers.1.mlp.dense_4h_to_h.weight": "model-00002-of-00008.safetensors",
+        "transformer.layers.1.mlp.dense_h_to_4h.bias": "model-00001-of-00008.safetensors",
+        "transformer.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00008.safetensors",
+        "transformer.layers.1.post_attention_layernorm.bias": "model-00001-of-00008.safetensors",
+        "transformer.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+        "transformer.layers.10.attention.dense.bias": "model-00003-of-00008.safetensors",
+        "transformer.layers.10.attention.dense.weight": "model-00003-of-00008.safetensors",
+        "transformer.layers.10.attention.query_key_value.bias": "model-00003-of-00008.safetensors",
+        "transformer.layers.10.attention.query_key_value.weight": "model-00003-of-00008.safetensors",
+        "transformer.layers.10.attention.rotary_emb.inv_freq": "model-00003-of-00008.safetensors",
+        "transformer.layers.10.input_layernorm.bias": "model-00003-of-00008.safetensors",
+        "transformer.layers.10.input_layernorm.weight": "model-00003-of-00008.safetensors",
+        "transformer.layers.10.mlp.dense_4h_to_h.bias": "model-00003-of-00008.safetensors",
+        "transformer.layers.10.mlp.dense_4h_to_h.weight": "model-00003-of-00008.safetensors",
+        "transformer.layers.10.mlp.dense_h_to_4h.bias": "model-00003-of-00008.safetensors",
+        "transformer.layers.10.mlp.dense_h_to_4h.weight": "model-00003-of-00008.safetensors",
+        "transformer.layers.10.post_attention_layernorm.bias": "model-00003-of-00008.safetensors",
+        "transformer.layers.10.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+        "transformer.layers.11.attention.dense.bias": "model-00004-of-00008.safetensors",
+        "transformer.layers.11.attention.dense.weight": "model-00004-of-00008.safetensors",
+        "transformer.layers.11.attention.query_key_value.bias": "model-00003-of-00008.safetensors",
+        "transformer.layers.11.attention.query_key_value.weight": "model-00003-of-00008.safetensors",
+        "transformer.layers.11.attention.rotary_emb.inv_freq": "model-00003-of-00008.safetensors",
+        "transformer.layers.11.input_layernorm.bias": "model-00003-of-00008.safetensors",
+        "transformer.layers.11.input_layernorm.weight": "model-00003-of-00008.safetensors",
+        "transformer.layers.11.mlp.dense_4h_to_h.bias": "model-00004-of-00008.safetensors",
+        "transformer.layers.11.mlp.dense_4h_to_h.weight": "model-00004-of-00008.safetensors",
+        "transformer.layers.11.mlp.dense_h_to_4h.bias": "model-00004-of-00008.safetensors",
+        "transformer.layers.11.mlp.dense_h_to_4h.weight": "model-00004-of-00008.safetensors",
+        "transformer.layers.11.post_attention_layernorm.bias": "model-00004-of-00008.safetensors",
+        "transformer.layers.11.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+        "transformer.layers.12.attention.dense.bias": "model-00004-of-00008.safetensors",
+        "transformer.layers.12.attention.dense.weight": "model-00004-of-00008.safetensors",
+        "transformer.layers.12.attention.query_key_value.bias": "model-00004-of-00008.safetensors",
+        "transformer.layers.12.attention.query_key_value.weight": "model-00004-of-00008.safetensors",
+        "transformer.layers.12.attention.rotary_emb.inv_freq": "model-00004-of-00008.safetensors",
+        "transformer.layers.12.input_layernorm.bias": "model-00004-of-00008.safetensors",
+        "transformer.layers.12.input_layernorm.weight": "model-00004-of-00008.safetensors",
+        "transformer.layers.12.mlp.dense_4h_to_h.bias": "model-00004-of-00008.safetensors",
+        "transformer.layers.12.mlp.dense_4h_to_h.weight": "model-00004-of-00008.safetensors",
+        "transformer.layers.12.mlp.dense_h_to_4h.bias": "model-00004-of-00008.safetensors",
+        "transformer.layers.12.mlp.dense_h_to_4h.weight": "model-00004-of-00008.safetensors",
+        "transformer.layers.12.post_attention_layernorm.bias": "model-00004-of-00008.safetensors",
+        "transformer.layers.12.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+        "transformer.layers.13.attention.dense.bias": "model-00004-of-00008.safetensors",
+        "transformer.layers.13.attention.dense.weight": "model-00004-of-00008.safetensors",
+        "transformer.layers.13.attention.query_key_value.bias": "model-00004-of-00008.safetensors",
+        "transformer.layers.13.attention.query_key_value.weight": "model-00004-of-00008.safetensors",
+        "transformer.layers.13.attention.rotary_emb.inv_freq": "model-00004-of-00008.safetensors",
+        "transformer.layers.13.input_layernorm.bias": "model-00004-of-00008.safetensors",
+        "transformer.layers.13.input_layernorm.weight": "model-00004-of-00008.safetensors",
+        "transformer.layers.13.mlp.dense_4h_to_h.bias": "model-00004-of-00008.safetensors",
+        "transformer.layers.13.mlp.dense_4h_to_h.weight": "model-00004-of-00008.safetensors",
+        "transformer.layers.13.mlp.dense_h_to_4h.bias": "model-00004-of-00008.safetensors",
+        "transformer.layers.13.mlp.dense_h_to_4h.weight": "model-00004-of-00008.safetensors",
+        "transformer.layers.13.post_attention_layernorm.bias": "model-00004-of-00008.safetensors",
+        "transformer.layers.13.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+        "transformer.layers.14.attention.dense.bias": "model-00004-of-00008.safetensors",
+        "transformer.layers.14.attention.dense.weight": "model-00004-of-00008.safetensors",
+        "transformer.layers.14.attention.query_key_value.bias": "model-00004-of-00008.safetensors",
+        "transformer.layers.14.attention.query_key_value.weight": "model-00004-of-00008.safetensors",
+        "transformer.layers.14.attention.rotary_emb.inv_freq": "model-00004-of-00008.safetensors",
+        "transformer.layers.14.input_layernorm.bias": "model-00004-of-00008.safetensors",
+        "transformer.layers.14.input_layernorm.weight": "model-00004-of-00008.safetensors",
+        "transformer.layers.14.mlp.dense_4h_to_h.bias": "model-00004-of-00008.safetensors",
+        "transformer.layers.14.mlp.dense_4h_to_h.weight": "model-00004-of-00008.safetensors",
+        "transformer.layers.14.mlp.dense_h_to_4h.bias": "model-00004-of-00008.safetensors",
+        "transformer.layers.14.mlp.dense_h_to_4h.weight": "model-00004-of-00008.safetensors",
+        "transformer.layers.14.post_attention_layernorm.bias": "model-00004-of-00008.safetensors",
+        "transformer.layers.14.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+        "transformer.layers.15.attention.dense.bias": "model-00004-of-00008.safetensors",
+        "transformer.layers.15.attention.dense.weight": "model-00004-of-00008.safetensors",
+        "transformer.layers.15.attention.query_key_value.bias": "model-00004-of-00008.safetensors",
+        "transformer.layers.15.attention.query_key_value.weight": "model-00004-of-00008.safetensors",
+        "transformer.layers.15.attention.rotary_emb.inv_freq": "model-00004-of-00008.safetensors",
+        "transformer.layers.15.input_layernorm.bias": "model-00004-of-00008.safetensors",
+        "transformer.layers.15.input_layernorm.weight": "model-00004-of-00008.safetensors",
+        "transformer.layers.15.mlp.dense_4h_to_h.bias": "model-00004-of-00008.safetensors",
+        "transformer.layers.15.mlp.dense_4h_to_h.weight": "model-00004-of-00008.safetensors",
+        "transformer.layers.15.mlp.dense_h_to_4h.bias": "model-00004-of-00008.safetensors",
+        "transformer.layers.15.mlp.dense_h_to_4h.weight": "model-00004-of-00008.safetensors",
+        "transformer.layers.15.post_attention_layernorm.bias": "model-00004-of-00008.safetensors",
+        "transformer.layers.15.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+        "transformer.layers.16.attention.dense.bias": "model-00005-of-00008.safetensors",
+        "transformer.layers.16.attention.dense.weight": "model-00005-of-00008.safetensors",
+        "transformer.layers.16.attention.query_key_value.bias": "model-00005-of-00008.safetensors",
+        "transformer.layers.16.attention.query_key_value.weight": "model-00005-of-00008.safetensors",
+        "transformer.layers.16.attention.rotary_emb.inv_freq": "model-00004-of-00008.safetensors",
+        "transformer.layers.16.input_layernorm.bias": "model-00004-of-00008.safetensors",
+        "transformer.layers.16.input_layernorm.weight": "model-00004-of-00008.safetensors",
+        "transformer.layers.16.mlp.dense_4h_to_h.bias": "model-00005-of-00008.safetensors",
+        "transformer.layers.16.mlp.dense_4h_to_h.weight": "model-00005-of-00008.safetensors",
+        "transformer.layers.16.mlp.dense_h_to_4h.bias": "model-00005-of-00008.safetensors",
+        "transformer.layers.16.mlp.dense_h_to_4h.weight": "model-00005-of-00008.safetensors",
+        "transformer.layers.16.post_attention_layernorm.bias": "model-00005-of-00008.safetensors",
+        "transformer.layers.16.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+        "transformer.layers.17.attention.dense.bias": "model-00005-of-00008.safetensors",
+        "transformer.layers.17.attention.dense.weight": "model-00005-of-00008.safetensors",
+        "transformer.layers.17.attention.query_key_value.bias": "model-00005-of-00008.safetensors",
+        "transformer.layers.17.attention.query_key_value.weight": "model-00005-of-00008.safetensors",
+        "transformer.layers.17.attention.rotary_emb.inv_freq": "model-00005-of-00008.safetensors",
+        "transformer.layers.17.input_layernorm.bias": "model-00005-of-00008.safetensors",
+        "transformer.layers.17.input_layernorm.weight": "model-00005-of-00008.safetensors",
+        "transformer.layers.17.mlp.dense_4h_to_h.bias": "model-00005-of-00008.safetensors",
+        "transformer.layers.17.mlp.dense_4h_to_h.weight": "model-00005-of-00008.safetensors",
+        "transformer.layers.17.mlp.dense_h_to_4h.bias": "model-00005-of-00008.safetensors",
+        "transformer.layers.17.mlp.dense_h_to_4h.weight": "model-00005-of-00008.safetensors",
+        "transformer.layers.17.post_attention_layernorm.bias": "model-00005-of-00008.safetensors",
+        "transformer.layers.17.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+        "transformer.layers.18.attention.dense.bias": "model-00005-of-00008.safetensors",
+        "transformer.layers.18.attention.dense.weight": "model-00005-of-00008.safetensors",
+        "transformer.layers.18.attention.query_key_value.bias": "model-00005-of-00008.safetensors",
+        "transformer.layers.18.attention.query_key_value.weight": "model-00005-of-00008.safetensors",
+        "transformer.layers.18.attention.rotary_emb.inv_freq": "model-00005-of-00008.safetensors",
+        "transformer.layers.18.input_layernorm.bias": "model-00005-of-00008.safetensors",
+        "transformer.layers.18.input_layernorm.weight": "model-00005-of-00008.safetensors",
+        "transformer.layers.18.mlp.dense_4h_to_h.bias": "model-00005-of-00008.safetensors",
+        "transformer.layers.18.mlp.dense_4h_to_h.weight": "model-00005-of-00008.safetensors",
+        "transformer.layers.18.mlp.dense_h_to_4h.bias": "model-00005-of-00008.safetensors",
+        "transformer.layers.18.mlp.dense_h_to_4h.weight": "model-00005-of-00008.safetensors",
+        "transformer.layers.18.post_attention_layernorm.bias": "model-00005-of-00008.safetensors",
+        "transformer.layers.18.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+        "transformer.layers.19.attention.dense.bias": "model-00005-of-00008.safetensors",
+        "transformer.layers.19.attention.dense.weight": "model-00005-of-00008.safetensors",
+        "transformer.layers.19.attention.query_key_value.bias": "model-00005-of-00008.safetensors",
+        "transformer.layers.19.attention.query_key_value.weight": "model-00005-of-00008.safetensors",
+        "transformer.layers.19.attention.rotary_emb.inv_freq": "model-00005-of-00008.safetensors",
+        "transformer.layers.19.input_layernorm.bias": "model-00005-of-00008.safetensors",
+        "transformer.layers.19.input_layernorm.weight": "model-00005-of-00008.safetensors",
+        "transformer.layers.19.mlp.dense_4h_to_h.bias": "model-00005-of-00008.safetensors",
+        "transformer.layers.19.mlp.dense_4h_to_h.weight": "model-00005-of-00008.safetensors",
+        "transformer.layers.19.mlp.dense_h_to_4h.bias": "model-00005-of-00008.safetensors",
+        "transformer.layers.19.mlp.dense_h_to_4h.weight": "model-00005-of-00008.safetensors",
+        "transformer.layers.19.post_attention_layernorm.bias": "model-00005-of-00008.safetensors",
+        "transformer.layers.19.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+        "transformer.layers.2.attention.dense.bias": "model-00002-of-00008.safetensors",
+        "transformer.layers.2.attention.dense.weight": "model-00002-of-00008.safetensors",
+        "transformer.layers.2.attention.query_key_value.bias": "model-00002-of-00008.safetensors",
+        "transformer.layers.2.attention.query_key_value.weight": "model-00002-of-00008.safetensors",
+        "transformer.layers.2.attention.rotary_emb.inv_freq": "model-00002-of-00008.safetensors",
+        "transformer.layers.2.input_layernorm.bias": "model-00002-of-00008.safetensors",
+        "transformer.layers.2.input_layernorm.weight": "model-00002-of-00008.safetensors",
+        "transformer.layers.2.mlp.dense_4h_to_h.bias": "model-00002-of-00008.safetensors",
+        "transformer.layers.2.mlp.dense_4h_to_h.weight": "model-00002-of-00008.safetensors",
+        "transformer.layers.2.mlp.dense_h_to_4h.bias": "model-00002-of-00008.safetensors",
+        "transformer.layers.2.mlp.dense_h_to_4h.weight": "model-00002-of-00008.safetensors",
+        "transformer.layers.2.post_attention_layernorm.bias": "model-00002-of-00008.safetensors",
+        "transformer.layers.2.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+        "transformer.layers.20.attention.dense.bias": "model-00005-of-00008.safetensors",
+        "transformer.layers.20.attention.dense.weight": "model-00005-of-00008.safetensors",
+        "transformer.layers.20.attention.query_key_value.bias": "model-00005-of-00008.safetensors",
+        "transformer.layers.20.attention.query_key_value.weight": "model-00005-of-00008.safetensors",
+        "transformer.layers.20.attention.rotary_emb.inv_freq": "model-00005-of-00008.safetensors",
+        "transformer.layers.20.input_layernorm.bias": "model-00005-of-00008.safetensors",
+        "transformer.layers.20.input_layernorm.weight": "model-00005-of-00008.safetensors",
+        "transformer.layers.20.mlp.dense_4h_to_h.bias": "model-00006-of-00008.safetensors",
+        "transformer.layers.20.mlp.dense_4h_to_h.weight": "model-00006-of-00008.safetensors",
+        "transformer.layers.20.mlp.dense_h_to_4h.bias": "model-00005-of-00008.safetensors",
+        "transformer.layers.20.mlp.dense_h_to_4h.weight": "model-00005-of-00008.safetensors",
+        "transformer.layers.20.post_attention_layernorm.bias": "model-00005-of-00008.safetensors",
+        "transformer.layers.20.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+        "transformer.layers.21.attention.dense.bias": "model-00006-of-00008.safetensors",
+        "transformer.layers.21.attention.dense.weight": "model-00006-of-00008.safetensors",
+        "transformer.layers.21.attention.query_key_value.bias": "model-00006-of-00008.safetensors",
+        "transformer.layers.21.attention.query_key_value.weight": "model-00006-of-00008.safetensors",
+        "transformer.layers.21.attention.rotary_emb.inv_freq": "model-00006-of-00008.safetensors",
+        "transformer.layers.21.input_layernorm.bias": "model-00006-of-00008.safetensors",
+        "transformer.layers.21.input_layernorm.weight": "model-00006-of-00008.safetensors",
+        "transformer.layers.21.mlp.dense_4h_to_h.bias": "model-00006-of-00008.safetensors",
+        "transformer.layers.21.mlp.dense_4h_to_h.weight": "model-00006-of-00008.safetensors",
+        "transformer.layers.21.mlp.dense_h_to_4h.bias": "model-00006-of-00008.safetensors",
+        "transformer.layers.21.mlp.dense_h_to_4h.weight": "model-00006-of-00008.safetensors",
+        "transformer.layers.21.post_attention_layernorm.bias": "model-00006-of-00008.safetensors",
+        "transformer.layers.21.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+        "transformer.layers.22.attention.dense.bias": "model-00006-of-00008.safetensors",
+        "transformer.layers.22.attention.dense.weight": "model-00006-of-00008.safetensors",
+        "transformer.layers.22.attention.query_key_value.bias": "model-00006-of-00008.safetensors",
+        "transformer.layers.22.attention.query_key_value.weight": "model-00006-of-00008.safetensors",
+        "transformer.layers.22.attention.rotary_emb.inv_freq": "model-00006-of-00008.safetensors",
+        "transformer.layers.22.input_layernorm.bias": "model-00006-of-00008.safetensors",
+        "transformer.layers.22.input_layernorm.weight": "model-00006-of-00008.safetensors",
+        "transformer.layers.22.mlp.dense_4h_to_h.bias": "model-00006-of-00008.safetensors",
+        "transformer.layers.22.mlp.dense_4h_to_h.weight": "model-00006-of-00008.safetensors",
+        "transformer.layers.22.mlp.dense_h_to_4h.bias": "model-00006-of-00008.safetensors",
+        "transformer.layers.22.mlp.dense_h_to_4h.weight": "model-00006-of-00008.safetensors",
+        "transformer.layers.22.post_attention_layernorm.bias": "model-00006-of-00008.safetensors",
+        "transformer.layers.22.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+        "transformer.layers.23.attention.dense.bias": "model-00006-of-00008.safetensors",
+        "transformer.layers.23.attention.dense.weight": "model-00006-of-00008.safetensors",
+        "transformer.layers.23.attention.query_key_value.bias": "model-00006-of-00008.safetensors",
+        "transformer.layers.23.attention.query_key_value.weight": "model-00006-of-00008.safetensors",
+        "transformer.layers.23.attention.rotary_emb.inv_freq": "model-00006-of-00008.safetensors",
+        "transformer.layers.23.input_layernorm.bias": "model-00006-of-00008.safetensors",
+        "transformer.layers.23.input_layernorm.weight": "model-00006-of-00008.safetensors",
+        "transformer.layers.23.mlp.dense_4h_to_h.bias": "model-00006-of-00008.safetensors",
+        "transformer.layers.23.mlp.dense_4h_to_h.weight": "model-00006-of-00008.safetensors",
+        "transformer.layers.23.mlp.dense_h_to_4h.bias": "model-00006-of-00008.safetensors",
+        "transformer.layers.23.mlp.dense_h_to_4h.weight": "model-00006-of-00008.safetensors",
+        "transformer.layers.23.post_attention_layernorm.bias": "model-00006-of-00008.safetensors",
+        "transformer.layers.23.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+        "transformer.layers.24.attention.dense.bias": "model-00006-of-00008.safetensors",
+        "transformer.layers.24.attention.dense.weight": "model-00006-of-00008.safetensors",
+        "transformer.layers.24.attention.query_key_value.bias": "model-00006-of-00008.safetensors",
+        "transformer.layers.24.attention.query_key_value.weight": "model-00006-of-00008.safetensors",
+        "transformer.layers.24.attention.rotary_emb.inv_freq": "model-00006-of-00008.safetensors",
+        "transformer.layers.24.input_layernorm.bias": "model-00006-of-00008.safetensors",
+        "transformer.layers.24.input_layernorm.weight": "model-00006-of-00008.safetensors",
+        "transformer.layers.24.mlp.dense_4h_to_h.bias": "model-00006-of-00008.safetensors",
+        "transformer.layers.24.mlp.dense_4h_to_h.weight": "model-00006-of-00008.safetensors",
+        "transformer.layers.24.mlp.dense_h_to_4h.bias": "model-00006-of-00008.safetensors",
+        "transformer.layers.24.mlp.dense_h_to_4h.weight": "model-00006-of-00008.safetensors",
+        "transformer.layers.24.post_attention_layernorm.bias": "model-00006-of-00008.safetensors",
+        "transformer.layers.24.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+        "transformer.layers.25.attention.dense.bias": "model-00006-of-00008.safetensors",
+        "transformer.layers.25.attention.dense.weight": "model-00006-of-00008.safetensors",
+        "transformer.layers.25.attention.query_key_value.bias": "model-00006-of-00008.safetensors",
+        "transformer.layers.25.attention.query_key_value.weight": "model-00006-of-00008.safetensors",
+        "transformer.layers.25.attention.rotary_emb.inv_freq": "model-00006-of-00008.safetensors",
+        "transformer.layers.25.input_layernorm.bias": "model-00006-of-00008.safetensors",
+        "transformer.layers.25.input_layernorm.weight": "model-00006-of-00008.safetensors",
+        "transformer.layers.25.mlp.dense_4h_to_h.bias": "model-00007-of-00008.safetensors",
+        "transformer.layers.25.mlp.dense_4h_to_h.weight": "model-00007-of-00008.safetensors",
+        "transformer.layers.25.mlp.dense_h_to_4h.bias": "model-00007-of-00008.safetensors",
+        "transformer.layers.25.mlp.dense_h_to_4h.weight": "model-00007-of-00008.safetensors",
+        "transformer.layers.25.post_attention_layernorm.bias": "model-00006-of-00008.safetensors",
+        "transformer.layers.25.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+        "transformer.layers.26.attention.dense.bias": "model-00007-of-00008.safetensors",
+        "transformer.layers.26.attention.dense.weight": "model-00007-of-00008.safetensors",
+        "transformer.layers.26.attention.query_key_value.bias": "model-00007-of-00008.safetensors",
+        "transformer.layers.26.attention.query_key_value.weight": "model-00007-of-00008.safetensors",
+        "transformer.layers.26.attention.rotary_emb.inv_freq": "model-00007-of-00008.safetensors",
+        "transformer.layers.26.input_layernorm.bias": "model-00007-of-00008.safetensors",
+        "transformer.layers.26.input_layernorm.weight": "model-00007-of-00008.safetensors",
+        "transformer.layers.26.mlp.dense_4h_to_h.bias": "model-00007-of-00008.safetensors",
+        "transformer.layers.26.mlp.dense_4h_to_h.weight": "model-00007-of-00008.safetensors",
+        "transformer.layers.26.mlp.dense_h_to_4h.bias": "model-00007-of-00008.safetensors",
+        "transformer.layers.26.mlp.dense_h_to_4h.weight": "model-00007-of-00008.safetensors",
+        "transformer.layers.26.post_attention_layernorm.bias": "model-00007-of-00008.safetensors",
+        "transformer.layers.26.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+        "transformer.layers.27.attention.dense.bias": "model-00007-of-00008.safetensors",
+        "transformer.layers.27.attention.dense.weight": "model-00007-of-00008.safetensors",
+        "transformer.layers.27.attention.query_key_value.bias": "model-00007-of-00008.safetensors",
+        "transformer.layers.27.attention.query_key_value.weight": "model-00007-of-00008.safetensors",
+        "transformer.layers.27.attention.rotary_emb.inv_freq": "model-00007-of-00008.safetensors",
+        "transformer.layers.27.input_layernorm.bias": "model-00007-of-00008.safetensors",
+        "transformer.layers.27.input_layernorm.weight": "model-00007-of-00008.safetensors",
+        "transformer.layers.27.mlp.dense_4h_to_h.bias": "model-00007-of-00008.safetensors",
+        "transformer.layers.27.mlp.dense_4h_to_h.weight": "model-00007-of-00008.safetensors",
+        "transformer.layers.27.mlp.dense_h_to_4h.bias": "model-00007-of-00008.safetensors",
+        "transformer.layers.27.mlp.dense_h_to_4h.weight": "model-00007-of-00008.safetensors",
+        "transformer.layers.27.post_attention_layernorm.bias": "model-00007-of-00008.safetensors",
+        "transformer.layers.27.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+        "transformer.layers.3.attention.dense.bias": "model-00002-of-00008.safetensors",
+        "transformer.layers.3.attention.dense.weight": "model-00002-of-00008.safetensors",
+        "transformer.layers.3.attention.query_key_value.bias": "model-00002-of-00008.safetensors",
+        "transformer.layers.3.attention.query_key_value.weight": "model-00002-of-00008.safetensors",
+        "transformer.layers.3.attention.rotary_emb.inv_freq": "model-00002-of-00008.safetensors",
+        "transformer.layers.3.input_layernorm.bias": "model-00002-of-00008.safetensors",
+        "transformer.layers.3.input_layernorm.weight": "model-00002-of-00008.safetensors",
+        "transformer.layers.3.mlp.dense_4h_to_h.bias": "model-00002-of-00008.safetensors",
+        "transformer.layers.3.mlp.dense_4h_to_h.weight": "model-00002-of-00008.safetensors",
+        "transformer.layers.3.mlp.dense_h_to_4h.bias": "model-00002-of-00008.safetensors",
+        "transformer.layers.3.mlp.dense_h_to_4h.weight": "model-00002-of-00008.safetensors",
+        "transformer.layers.3.post_attention_layernorm.bias": "model-00002-of-00008.safetensors",
+        "transformer.layers.3.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+        "transformer.layers.4.attention.dense.bias": "model-00002-of-00008.safetensors",
+        "transformer.layers.4.attention.dense.weight": "model-00002-of-00008.safetensors",
+        "transformer.layers.4.attention.query_key_value.bias": "model-00002-of-00008.safetensors",
+        "transformer.layers.4.attention.query_key_value.weight": "model-00002-of-00008.safetensors",
+        "transformer.layers.4.attention.rotary_emb.inv_freq": "model-00002-of-00008.safetensors",
+        "transformer.layers.4.input_layernorm.bias": "model-00002-of-00008.safetensors",
+        "transformer.layers.4.input_layernorm.weight": "model-00002-of-00008.safetensors",
+        "transformer.layers.4.mlp.dense_4h_to_h.bias": "model-00002-of-00008.safetensors",
+        "transformer.layers.4.mlp.dense_4h_to_h.weight": "model-00002-of-00008.safetensors",
+        "transformer.layers.4.mlp.dense_h_to_4h.bias": "model-00002-of-00008.safetensors",
+        "transformer.layers.4.mlp.dense_h_to_4h.weight": "model-00002-of-00008.safetensors",
+        "transformer.layers.4.post_attention_layernorm.bias": "model-00002-of-00008.safetensors",
+        "transformer.layers.4.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+        "transformer.layers.5.attention.dense.bias": "model-00002-of-00008.safetensors",
+        "transformer.layers.5.attention.dense.weight": "model-00002-of-00008.safetensors",
+        "transformer.layers.5.attention.query_key_value.bias": "model-00002-of-00008.safetensors",
+        "transformer.layers.5.attention.query_key_value.weight": "model-00002-of-00008.safetensors",
+        "transformer.layers.5.attention.rotary_emb.inv_freq": "model-00002-of-00008.safetensors",
+        "transformer.layers.5.input_layernorm.bias": "model-00002-of-00008.safetensors",
+        "transformer.layers.5.input_layernorm.weight": "model-00002-of-00008.safetensors",
+        "transformer.layers.5.mlp.dense_4h_to_h.bias": "model-00002-of-00008.safetensors",
+        "transformer.layers.5.mlp.dense_4h_to_h.weight": "model-00002-of-00008.safetensors",
+        "transformer.layers.5.mlp.dense_h_to_4h.bias": "model-00002-of-00008.safetensors",
+        "transformer.layers.5.mlp.dense_h_to_4h.weight": "model-00002-of-00008.safetensors",
+        "transformer.layers.5.post_attention_layernorm.bias": "model-00002-of-00008.safetensors",
+        "transformer.layers.5.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+        "transformer.layers.6.attention.dense.bias": "model-00002-of-00008.safetensors",
+        "transformer.layers.6.attention.dense.weight": "model-00002-of-00008.safetensors",
+        "transformer.layers.6.attention.query_key_value.bias": "model-00002-of-00008.safetensors",
+        "transformer.layers.6.attention.query_key_value.weight": "model-00002-of-00008.safetensors",
+        "transformer.layers.6.attention.rotary_emb.inv_freq": "model-00002-of-00008.safetensors",
+        "transformer.layers.6.input_layernorm.bias": "model-00002-of-00008.safetensors",
+        "transformer.layers.6.input_layernorm.weight": "model-00002-of-00008.safetensors",
+        "transformer.layers.6.mlp.dense_4h_to_h.bias": "model-00003-of-00008.safetensors",
+        "transformer.layers.6.mlp.dense_4h_to_h.weight": "model-00003-of-00008.safetensors",
+        "transformer.layers.6.mlp.dense_h_to_4h.bias": "model-00003-of-00008.safetensors",
+        "transformer.layers.6.mlp.dense_h_to_4h.weight": "model-00003-of-00008.safetensors",
+        "transformer.layers.6.post_attention_layernorm.bias": "model-00002-of-00008.safetensors",
+        "transformer.layers.6.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+        "transformer.layers.7.attention.dense.bias": "model-00003-of-00008.safetensors",
+        "transformer.layers.7.attention.dense.weight": "model-00003-of-00008.safetensors",
+        "transformer.layers.7.attention.query_key_value.bias": "model-00003-of-00008.safetensors",
+        "transformer.layers.7.attention.query_key_value.weight": "model-00003-of-00008.safetensors",
+        "transformer.layers.7.attention.rotary_emb.inv_freq": "model-00003-of-00008.safetensors",
+        "transformer.layers.7.input_layernorm.bias": "model-00003-of-00008.safetensors",
+        "transformer.layers.7.input_layernorm.weight": "model-00003-of-00008.safetensors",
+        "transformer.layers.7.mlp.dense_4h_to_h.bias": "model-00003-of-00008.safetensors",
+        "transformer.layers.7.mlp.dense_4h_to_h.weight": "model-00003-of-00008.safetensors",
+        "transformer.layers.7.mlp.dense_h_to_4h.bias": "model-00003-of-00008.safetensors",
+        "transformer.layers.7.mlp.dense_h_to_4h.weight": "model-00003-of-00008.safetensors",
+        "transformer.layers.7.post_attention_layernorm.bias": "model-00003-of-00008.safetensors",
+        "transformer.layers.7.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+        "transformer.layers.8.attention.dense.bias": "model-00003-of-00008.safetensors",
+        "transformer.layers.8.attention.dense.weight": "model-00003-of-00008.safetensors",
+        "transformer.layers.8.attention.query_key_value.bias": "model-00003-of-00008.safetensors",
+        "transformer.layers.8.attention.query_key_value.weight": "model-00003-of-00008.safetensors",
+        "transformer.layers.8.attention.rotary_emb.inv_freq": "model-00003-of-00008.safetensors",
+        "transformer.layers.8.input_layernorm.bias": "model-00003-of-00008.safetensors",
+        "transformer.layers.8.input_layernorm.weight": "model-00003-of-00008.safetensors",
+        "transformer.layers.8.mlp.dense_4h_to_h.bias": "model-00003-of-00008.safetensors",
+        "transformer.layers.8.mlp.dense_4h_to_h.weight": "model-00003-of-00008.safetensors",
+        "transformer.layers.8.mlp.dense_h_to_4h.bias": "model-00003-of-00008.safetensors",
+        "transformer.layers.8.mlp.dense_h_to_4h.weight": "model-00003-of-00008.safetensors",
+        "transformer.layers.8.post_attention_layernorm.bias": "model-00003-of-00008.safetensors",
+        "transformer.layers.8.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+        "transformer.layers.9.attention.dense.bias": "model-00003-of-00008.safetensors",
+        "transformer.layers.9.attention.dense.weight": "model-00003-of-00008.safetensors",
+        "transformer.layers.9.attention.query_key_value.bias": "model-00003-of-00008.safetensors",
+        "transformer.layers.9.attention.query_key_value.weight": "model-00003-of-00008.safetensors",
+        "transformer.layers.9.attention.rotary_emb.inv_freq": "model-00003-of-00008.safetensors",
+        "transformer.layers.9.input_layernorm.bias": "model-00003-of-00008.safetensors",
+        "transformer.layers.9.input_layernorm.weight": "model-00003-of-00008.safetensors",
+        "transformer.layers.9.mlp.dense_4h_to_h.bias": "model-00003-of-00008.safetensors",
+        "transformer.layers.9.mlp.dense_4h_to_h.weight": "model-00003-of-00008.safetensors",
+        "transformer.layers.9.mlp.dense_h_to_4h.bias": "model-00003-of-00008.safetensors",
+        "transformer.layers.9.mlp.dense_h_to_4h.weight": "model-00003-of-00008.safetensors",
+        "transformer.layers.9.post_attention_layernorm.bias": "model-00003-of-00008.safetensors",
+        "transformer.layers.9.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+        "transformer.word_embeddings.weight": "model-00001-of-00008.safetensors"
+    }
+}