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 sha256:39323df4e2f1092aa4de6a97b3518598735ff635f1edb9986b4fa35e8308e92e
+size 4943162240

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42d7f5c87fea478f38aa649e8f778560dcd7887f5d2ed42e3c4c3047e1f474f4
+size 2560734832

model.safetensors.index.json

@@ -0,0 +1,154 @@
+{
+    "metadata": {
+        "total_size": 7503880192
+    },
+    "weight_map": {
+        "lm_head.weight": "model-00002-of-00002.safetensors",
+        "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.norm.weight": "model-00002-of-00002.safetensors"
+    }
+}