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-00000-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb365804cc33f6ad9c1eaca0b3d07830308280a4f8eea550e360f6608467c5a8
+size 404767824

model-00001-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09b83a9dbd4454b51e879493939e00b7e423b959c292e87af0280d7acfbf0224
+size 404767824

model-00002-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c76a49e0b50422ab8ed5baa1674cf6d55753397081b90f44488e73eba8a334a
+size 404767824

model-00003-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cbd018487661c83aab559fcc58520de1d7b12d5dd2f26ec49884af4db45c553
+size 404767824

model-00004-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95f6213bd360610b80bed87d90b604d5028c17b516395afaff197ba5405594bf
+size 404767824

model-00005-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06f4fe00a35bc495239be0d653fc702ffe9bf774dc431080d977a49c89b6f59a
+size 404767824

model-00006-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af9f7c7c472de02c87faa6bba1cd914c6729c97c0421c2ed45a86043d1971ed5
+size 404767824

model-00007-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ede05fa721872ad6495a63875a613bef3d3e54c2e23a682a211caa4d09c5aa2e
+size 404767824

model-00008-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8e8d1b4885ab8baf3b64ffd804d21708aafad26cdd28066ef2da8a6ee723f36
+size 404767824

model-00009-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7b44eed88a49df9d13c14e59706c67cbfa735ffba1a6ff3fd2e5418dfa49782
+size 404767824

model-00010-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca8fc83ecb14e6df4cea245760f45ad36ef2b732059b351ebbd3a01e4b872565
+size 404767832

model-00011-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dec3365bc05cbfab0f729add1e21d52a59a3d0fbaf4a71bfbd92dcb4b0f238df
+size 404767832

model-00012-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49d4b0647c8f645a04b75096f1ab093a18f63b6c2e0ae44852f069eb5d1fa32c
+size 404767832

model-00013-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:170504b5a39c5095be0dc50be563f28784d4b016c323823ddf8b57af0338112a
+size 404767832

model-00014-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1493c5d0c072c8143c8aeb04953198aa7bc34d9e76f328596cda84cb730efbc6
+size 404767832

model-00015-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:174c33d219d96aee28e75cdbddff192d54aa73da957dad44cb387ce7ec96efe2
+size 404767832

model-00016-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efb83a8eb8783ed6276ebc9f2c35f910fce85288538489abba8e110bc4f8d250
+size 404767832

model-00017-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:feacf09130b5d5ab9310a5ed9c2ac838e42d26d9bba3afe86f9c8273958267d6
+size 404767832

model-00018-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5605defff1c17aabd75f6c4fc9c05a8cbf55b32d0823e1ef55826fdad795120
+size 404767832

model-00019-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fd0dbda42ebbee817f429787a57e295908cc0a23c049b645fb96497331e5565
+size 404767832

model-00020-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cd49bdf4d5cc257bf74e248eb48eefb6d13ade215d42eedbcd3e7c510022bdf
+size 404767832

model-00021-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69456bacf4f8dd972cbf8dd2d749fad9dd5e6fc4914b1504080dce4f0c89e3ff
+size 404767832

model-00022-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f59dc60d014f6769533e57b44f390e8a2a7e9b018037c4b073a38aec3063780
+size 404767832

model-00023-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b25aad608fb463b52571c818c529ad95c106aea8c0b7d75b35ad7abc042b7eaf
+size 404767832

model-00024-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bf43608a2dcff0bafa4bb3c8a8dce4594365af68548ea933fab2c5b54723a29
+size 404767832

model-00025-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b94a0215436dbd393a39df964c2123b1f4b88c7e63904949346f4d6927dd3cb6
+size 404767832

model-00026-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:026a69a8de1c64bdd2512a4e250b35a2c046e6d648ec41a8179b4141da9af789
+size 404767832

model-00027-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c4273f2aca205c5277b04d4736b05edc6b3a47777dfd3ec9ba9d30caa373d56
+size 404767832

model-00028-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ad917166d4f489e9a07bca4fcf910f27debe3980a020b6e542e6b539980f660
+size 404767832

model-00029-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b6146f48be41a01c4cfa31148fa926ff8be24b20f01a59d77981660f4c19484
+size 404767832

model-00030-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aed1cec9ae96d0f2d3302ab7983698708861c8bdc0da63157e22adb791160576
+size 404767832

model-00031-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73e603d0f366a1972f98d054a52c723b0ea6f0fd37344fb053f61f281a864bf4
+size 404767832

model-00032-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8ca306eee19838ec2578d4b51145096137ccc77ee92caf61c4b4f5b04848a59
+size 524296528

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+    "weight_map": {
+        "model.decoder.layers.0.self_attn.q_proj.weight": "model-00000-of-00033.safetensors",
+        "model.decoder.layers.0.self_attn.k_proj.weight": "model-00000-of-00033.safetensors",
+        "model.decoder.layers.0.self_attn.v_proj.weight": "model-00000-of-00033.safetensors",
+        "model.decoder.layers.0.self_attn.o_proj.weight": "model-00000-of-00033.safetensors",
+        "model.decoder.layers.0.feed_forward.w1.weight": "model-00000-of-00033.safetensors",
+        "model.decoder.layers.0.feed_forward.w2.weight": "model-00000-of-00033.safetensors",
+        "model.decoder.layers.0.feed_forward.w3.weight": "model-00000-of-00033.safetensors",
+        "model.decoder.layers.0.attention_norm.weight": "model-00000-of-00033.safetensors",
+        "model.decoder.layers.0.ffn_norm.weight": "model-00000-of-00033.safetensors",
+        "model.decoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00033.safetensors",
+        "model.decoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00033.safetensors",
+        "model.decoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00033.safetensors",
+        "model.decoder.layers.1.self_attn.o_proj.weight": "model-00001-of-00033.safetensors",
+        "model.decoder.layers.1.feed_forward.w1.weight": "model-00001-of-00033.safetensors",
+        "model.decoder.layers.1.feed_forward.w2.weight": "model-00001-of-00033.safetensors",
+        "model.decoder.layers.1.feed_forward.w3.weight": "model-00001-of-00033.safetensors",
+        "model.decoder.layers.1.attention_norm.weight": "model-00001-of-00033.safetensors",
+        "model.decoder.layers.1.ffn_norm.weight": "model-00001-of-00033.safetensors",
+        "model.decoder.layers.2.self_attn.q_proj.weight": "model-00002-of-00033.safetensors",
+        "model.decoder.layers.2.self_attn.k_proj.weight": "model-00002-of-00033.safetensors",
+        "model.decoder.layers.2.self_attn.v_proj.weight": "model-00002-of-00033.safetensors",
+        "model.decoder.layers.2.self_attn.o_proj.weight": "model-00002-of-00033.safetensors",
+        "model.decoder.layers.2.feed_forward.w1.weight": "model-00002-of-00033.safetensors",
+        "model.decoder.layers.2.feed_forward.w2.weight": "model-00002-of-00033.safetensors",
+        "model.decoder.layers.2.feed_forward.w3.weight": "model-00002-of-00033.safetensors",
+        "model.decoder.layers.2.attention_norm.weight": "model-00002-of-00033.safetensors",
+        "model.decoder.layers.2.ffn_norm.weight": "model-00002-of-00033.safetensors",
+        "model.decoder.layers.3.self_attn.q_proj.weight": "model-00003-of-00033.safetensors",
+        "model.decoder.layers.3.self_attn.k_proj.weight": "model-00003-of-00033.safetensors",
+        "model.decoder.layers.3.self_attn.v_proj.weight": "model-00003-of-00033.safetensors",
+        "model.decoder.layers.3.self_attn.o_proj.weight": "model-00003-of-00033.safetensors",
+        "model.decoder.layers.3.feed_forward.w1.weight": "model-00003-of-00033.safetensors",
+        "model.decoder.layers.3.feed_forward.w2.weight": "model-00003-of-00033.safetensors",
+        "model.decoder.layers.3.feed_forward.w3.weight": "model-00003-of-00033.safetensors",
+        "model.decoder.layers.3.attention_norm.weight": "model-00003-of-00033.safetensors",
+        "model.decoder.layers.3.ffn_norm.weight": "model-00003-of-00033.safetensors",
+        "model.decoder.layers.4.self_attn.q_proj.weight": "model-00004-of-00033.safetensors",
+        "model.decoder.layers.4.self_attn.k_proj.weight": "model-00004-of-00033.safetensors",
+        "model.decoder.layers.4.self_attn.v_proj.weight": "model-00004-of-00033.safetensors",
+        "model.decoder.layers.4.self_attn.o_proj.weight": "model-00004-of-00033.safetensors",
+        "model.decoder.layers.4.feed_forward.w1.weight": "model-00004-of-00033.safetensors",
+        "model.decoder.layers.4.feed_forward.w2.weight": "model-00004-of-00033.safetensors",
+        "model.decoder.layers.4.feed_forward.w3.weight": "model-00004-of-00033.safetensors",
+        "model.decoder.layers.4.attention_norm.weight": "model-00004-of-00033.safetensors",
+        "model.decoder.layers.4.ffn_norm.weight": "model-00004-of-00033.safetensors",
+        "model.decoder.layers.5.self_attn.q_proj.weight": "model-00005-of-00033.safetensors",
+        "model.decoder.layers.5.self_attn.k_proj.weight": "model-00005-of-00033.safetensors",
+        "model.decoder.layers.5.self_attn.v_proj.weight": "model-00005-of-00033.safetensors",
+        "model.decoder.layers.5.self_attn.o_proj.weight": "model-00005-of-00033.safetensors",
+        "model.decoder.layers.5.feed_forward.w1.weight": "model-00005-of-00033.safetensors",
+        "model.decoder.layers.5.feed_forward.w2.weight": "model-00005-of-00033.safetensors",
+        "model.decoder.layers.5.feed_forward.w3.weight": "model-00005-of-00033.safetensors",
+        "model.decoder.layers.5.attention_norm.weight": "model-00005-of-00033.safetensors",
+        "model.decoder.layers.5.ffn_norm.weight": "model-00005-of-00033.safetensors",
+        "model.decoder.layers.6.self_attn.q_proj.weight": "model-00006-of-00033.safetensors",
+        "model.decoder.layers.6.self_attn.k_proj.weight": "model-00006-of-00033.safetensors",
+        "model.decoder.layers.6.self_attn.v_proj.weight": "model-00006-of-00033.safetensors",
+        "model.decoder.layers.6.self_attn.o_proj.weight": "model-00006-of-00033.safetensors",
+        "model.decoder.layers.6.feed_forward.w1.weight": "model-00006-of-00033.safetensors",
+        "model.decoder.layers.6.feed_forward.w2.weight": "model-00006-of-00033.safetensors",
+        "model.decoder.layers.6.feed_forward.w3.weight": "model-00006-of-00033.safetensors",
+        "model.decoder.layers.6.attention_norm.weight": "model-00006-of-00033.safetensors",
+        "model.decoder.layers.6.ffn_norm.weight": "model-00006-of-00033.safetensors",
+        "model.decoder.layers.7.self_attn.q_proj.weight": "model-00007-of-00033.safetensors",
+        "model.decoder.layers.7.self_attn.k_proj.weight": "model-00007-of-00033.safetensors",
+        "model.decoder.layers.7.self_attn.v_proj.weight": "model-00007-of-00033.safetensors",
+        "model.decoder.layers.7.self_attn.o_proj.weight": "model-00007-of-00033.safetensors",
+        "model.decoder.layers.7.feed_forward.w1.weight": "model-00007-of-00033.safetensors",
+        "model.decoder.layers.7.feed_forward.w2.weight": "model-00007-of-00033.safetensors",
+        "model.decoder.layers.7.feed_forward.w3.weight": "model-00007-of-00033.safetensors",
+        "model.decoder.layers.7.attention_norm.weight": "model-00007-of-00033.safetensors",
+        "model.decoder.layers.7.ffn_norm.weight": "model-00007-of-00033.safetensors",
+        "model.decoder.layers.8.self_attn.q_proj.weight": "model-00008-of-00033.safetensors",
+        "model.decoder.layers.8.self_attn.k_proj.weight": "model-00008-of-00033.safetensors",
+        "model.decoder.layers.8.self_attn.v_proj.weight": "model-00008-of-00033.safetensors",
+        "model.decoder.layers.8.self_attn.o_proj.weight": "model-00008-of-00033.safetensors",
+        "model.decoder.layers.8.feed_forward.w1.weight": "model-00008-of-00033.safetensors",
+        "model.decoder.layers.8.feed_forward.w2.weight": "model-00008-of-00033.safetensors",
+        "model.decoder.layers.8.feed_forward.w3.weight": "model-00008-of-00033.safetensors",
+        "model.decoder.layers.8.attention_norm.weight": "model-00008-of-00033.safetensors",
+        "model.decoder.layers.8.ffn_norm.weight": "model-00008-of-00033.safetensors",
+        "model.decoder.layers.9.self_attn.q_proj.weight": "model-00009-of-00033.safetensors",
+        "model.decoder.layers.9.self_attn.k_proj.weight": "model-00009-of-00033.safetensors",
+        "model.decoder.layers.9.self_attn.v_proj.weight": "model-00009-of-00033.safetensors",
+        "model.decoder.layers.9.self_attn.o_proj.weight": "model-00009-of-00033.safetensors",
+        "model.decoder.layers.9.feed_forward.w1.weight": "model-00009-of-00033.safetensors",
+        "model.decoder.layers.9.feed_forward.w2.weight": "model-00009-of-00033.safetensors",
+        "model.decoder.layers.9.feed_forward.w3.weight": "model-00009-of-00033.safetensors",
+        "model.decoder.layers.9.attention_norm.weight": "model-00009-of-00033.safetensors",
+        "model.decoder.layers.9.ffn_norm.weight": "model-00009-of-00033.safetensors",
+        "model.decoder.layers.10.self_attn.q_proj.weight": "model-00010-of-00033.safetensors",
+        "model.decoder.layers.10.self_attn.k_proj.weight": "model-00010-of-00033.safetensors",
+        "model.decoder.layers.10.self_attn.v_proj.weight": "model-00010-of-00033.safetensors",
+        "model.decoder.layers.10.self_attn.o_proj.weight": "model-00010-of-00033.safetensors",
+        "model.decoder.layers.10.feed_forward.w1.weight": "model-00010-of-00033.safetensors",
+        "model.decoder.layers.10.feed_forward.w2.weight": "model-00010-of-00033.safetensors",
+        "model.decoder.layers.10.feed_forward.w3.weight": "model-00010-of-00033.safetensors",
+        "model.decoder.layers.10.attention_norm.weight": "model-00010-of-00033.safetensors",
+        "model.decoder.layers.10.ffn_norm.weight": "model-00010-of-00033.safetensors",
+        "model.decoder.layers.11.self_attn.q_proj.weight": "model-00011-of-00033.safetensors",
+        "model.decoder.layers.11.self_attn.k_proj.weight": "model-00011-of-00033.safetensors",
+        "model.decoder.layers.11.self_attn.v_proj.weight": "model-00011-of-00033.safetensors",
+        "model.decoder.layers.11.self_attn.o_proj.weight": "model-00011-of-00033.safetensors",
+        "model.decoder.layers.11.feed_forward.w1.weight": "model-00011-of-00033.safetensors",
+        "model.decoder.layers.11.feed_forward.w2.weight": "model-00011-of-00033.safetensors",
+        "model.decoder.layers.11.feed_forward.w3.weight": "model-00011-of-00033.safetensors",
+        "model.decoder.layers.11.attention_norm.weight": "model-00011-of-00033.safetensors",
+        "model.decoder.layers.11.ffn_norm.weight": "model-00011-of-00033.safetensors",
+        "model.decoder.layers.12.self_attn.q_proj.weight": "model-00012-of-00033.safetensors",
+        "model.decoder.layers.12.self_attn.k_proj.weight": "model-00012-of-00033.safetensors",
+        "model.decoder.layers.12.self_attn.v_proj.weight": "model-00012-of-00033.safetensors",
+        "model.decoder.layers.12.self_attn.o_proj.weight": "model-00012-of-00033.safetensors",
+        "model.decoder.layers.12.feed_forward.w1.weight": "model-00012-of-00033.safetensors",
+        "model.decoder.layers.12.feed_forward.w2.weight": "model-00012-of-00033.safetensors",
+        "model.decoder.layers.12.feed_forward.w3.weight": "model-00012-of-00033.safetensors",
+        "model.decoder.layers.12.attention_norm.weight": "model-00012-of-00033.safetensors",
+        "model.decoder.layers.12.ffn_norm.weight": "model-00012-of-00033.safetensors",
+        "model.decoder.layers.13.self_attn.q_proj.weight": "model-00013-of-00033.safetensors",
+        "model.decoder.layers.13.self_attn.k_proj.weight": "model-00013-of-00033.safetensors",
+        "model.decoder.layers.13.self_attn.v_proj.weight": "model-00013-of-00033.safetensors",
+        "model.decoder.layers.13.self_attn.o_proj.weight": "model-00013-of-00033.safetensors",
+        "model.decoder.layers.13.feed_forward.w1.weight": "model-00013-of-00033.safetensors",
+        "model.decoder.layers.13.feed_forward.w2.weight": "model-00013-of-00033.safetensors",
+        "model.decoder.layers.13.feed_forward.w3.weight": "model-00013-of-00033.safetensors",
+        "model.decoder.layers.13.attention_norm.weight": "model-00013-of-00033.safetensors",
+        "model.decoder.layers.13.ffn_norm.weight": "model-00013-of-00033.safetensors",
+        "model.decoder.layers.14.self_attn.q_proj.weight": "model-00014-of-00033.safetensors",
+        "model.decoder.layers.14.self_attn.k_proj.weight": "model-00014-of-00033.safetensors",
+        "model.decoder.layers.14.self_attn.v_proj.weight": "model-00014-of-00033.safetensors",
+        "model.decoder.layers.14.self_attn.o_proj.weight": "model-00014-of-00033.safetensors",
+        "model.decoder.layers.14.feed_forward.w1.weight": "model-00014-of-00033.safetensors",
+        "model.decoder.layers.14.feed_forward.w2.weight": "model-00014-of-00033.safetensors",
+        "model.decoder.layers.14.feed_forward.w3.weight": "model-00014-of-00033.safetensors",
+        "model.decoder.layers.14.attention_norm.weight": "model-00014-of-00033.safetensors",
+        "model.decoder.layers.14.ffn_norm.weight": "model-00014-of-00033.safetensors",
+        "model.decoder.layers.15.self_attn.q_proj.weight": "model-00015-of-00033.safetensors",
+        "model.decoder.layers.15.self_attn.k_proj.weight": "model-00015-of-00033.safetensors",
+        "model.decoder.layers.15.self_attn.v_proj.weight": "model-00015-of-00033.safetensors",
+        "model.decoder.layers.15.self_attn.o_proj.weight": "model-00015-of-00033.safetensors",
+        "model.decoder.layers.15.feed_forward.w1.weight": "model-00015-of-00033.safetensors",
+        "model.decoder.layers.15.feed_forward.w2.weight": "model-00015-of-00033.safetensors",
+        "model.decoder.layers.15.feed_forward.w3.weight": "model-00015-of-00033.safetensors",
+        "model.decoder.layers.15.attention_norm.weight": "model-00015-of-00033.safetensors",
+        "model.decoder.layers.15.ffn_norm.weight": "model-00015-of-00033.safetensors",
+        "model.decoder.layers.16.self_attn.q_proj.weight": "model-00016-of-00033.safetensors",
+        "model.decoder.layers.16.self_attn.k_proj.weight": "model-00016-of-00033.safetensors",
+        "model.decoder.layers.16.self_attn.v_proj.weight": "model-00016-of-00033.safetensors",
+        "model.decoder.layers.16.self_attn.o_proj.weight": "model-00016-of-00033.safetensors",
+        "model.decoder.layers.16.feed_forward.w1.weight": "model-00016-of-00033.safetensors",
+        "model.decoder.layers.16.feed_forward.w2.weight": "model-00016-of-00033.safetensors",
+        "model.decoder.layers.16.feed_forward.w3.weight": "model-00016-of-00033.safetensors",
+        "model.decoder.layers.16.attention_norm.weight": "model-00016-of-00033.safetensors",
+        "model.decoder.layers.16.ffn_norm.weight": "model-00016-of-00033.safetensors",
+        "model.decoder.layers.17.self_attn.q_proj.weight": "model-00017-of-00033.safetensors",
+        "model.decoder.layers.17.self_attn.k_proj.weight": "model-00017-of-00033.safetensors",
+        "model.decoder.layers.17.self_attn.v_proj.weight": "model-00017-of-00033.safetensors",
+        "model.decoder.layers.17.self_attn.o_proj.weight": "model-00017-of-00033.safetensors",
+        "model.decoder.layers.17.feed_forward.w1.weight": "model-00017-of-00033.safetensors",
+        "model.decoder.layers.17.feed_forward.w2.weight": "model-00017-of-00033.safetensors",
+        "model.decoder.layers.17.feed_forward.w3.weight": "model-00017-of-00033.safetensors",
+        "model.decoder.layers.17.attention_norm.weight": "model-00017-of-00033.safetensors",
+        "model.decoder.layers.17.ffn_norm.weight": "model-00017-of-00033.safetensors",
+        "model.decoder.layers.18.self_attn.q_proj.weight": "model-00018-of-00033.safetensors",
+        "model.decoder.layers.18.self_attn.k_proj.weight": "model-00018-of-00033.safetensors",
+        "model.decoder.layers.18.self_attn.v_proj.weight": "model-00018-of-00033.safetensors",
+        "model.decoder.layers.18.self_attn.o_proj.weight": "model-00018-of-00033.safetensors",
+        "model.decoder.layers.18.feed_forward.w1.weight": "model-00018-of-00033.safetensors",
+        "model.decoder.layers.18.feed_forward.w2.weight": "model-00018-of-00033.safetensors",
+        "model.decoder.layers.18.feed_forward.w3.weight": "model-00018-of-00033.safetensors",
+        "model.decoder.layers.18.attention_norm.weight": "model-00018-of-00033.safetensors",
+        "model.decoder.layers.18.ffn_norm.weight": "model-00018-of-00033.safetensors",
+        "model.decoder.layers.19.self_attn.q_proj.weight": "model-00019-of-00033.safetensors",
+        "model.decoder.layers.19.self_attn.k_proj.weight": "model-00019-of-00033.safetensors",
+        "model.decoder.layers.19.self_attn.v_proj.weight": "model-00019-of-00033.safetensors",
+        "model.decoder.layers.19.self_attn.o_proj.weight": "model-00019-of-00033.safetensors",
+        "model.decoder.layers.19.feed_forward.w1.weight": "model-00019-of-00033.safetensors",
+        "model.decoder.layers.19.feed_forward.w2.weight": "model-00019-of-00033.safetensors",
+        "model.decoder.layers.19.feed_forward.w3.weight": "model-00019-of-00033.safetensors",
+        "model.decoder.layers.19.attention_norm.weight": "model-00019-of-00033.safetensors",
+        "model.decoder.layers.19.ffn_norm.weight": "model-00019-of-00033.safetensors",
+        "model.decoder.layers.20.self_attn.q_proj.weight": "model-00020-of-00033.safetensors",
+        "model.decoder.layers.20.self_attn.k_proj.weight": "model-00020-of-00033.safetensors",
+        "model.decoder.layers.20.self_attn.v_proj.weight": "model-00020-of-00033.safetensors",
+        "model.decoder.layers.20.self_attn.o_proj.weight": "model-00020-of-00033.safetensors",
+        "model.decoder.layers.20.feed_forward.w1.weight": "model-00020-of-00033.safetensors",
+        "model.decoder.layers.20.feed_forward.w2.weight": "model-00020-of-00033.safetensors",
+        "model.decoder.layers.20.feed_forward.w3.weight": "model-00020-of-00033.safetensors",
+        "model.decoder.layers.20.attention_norm.weight": "model-00020-of-00033.safetensors",
+        "model.decoder.layers.20.ffn_norm.weight": "model-00020-of-00033.safetensors",
+        "model.decoder.layers.21.self_attn.q_proj.weight": "model-00021-of-00033.safetensors",
+        "model.decoder.layers.21.self_attn.k_proj.weight": "model-00021-of-00033.safetensors",
+        "model.decoder.layers.21.self_attn.v_proj.weight": "model-00021-of-00033.safetensors",
+        "model.decoder.layers.21.self_attn.o_proj.weight": "model-00021-of-00033.safetensors",
+        "model.decoder.layers.21.feed_forward.w1.weight": "model-00021-of-00033.safetensors",
+        "model.decoder.layers.21.feed_forward.w2.weight": "model-00021-of-00033.safetensors",
+        "model.decoder.layers.21.feed_forward.w3.weight": "model-00021-of-00033.safetensors",
+        "model.decoder.layers.21.attention_norm.weight": "model-00021-of-00033.safetensors",
+        "model.decoder.layers.21.ffn_norm.weight": "model-00021-of-00033.safetensors",
+        "model.decoder.layers.22.self_attn.q_proj.weight": "model-00022-of-00033.safetensors",
+        "model.decoder.layers.22.self_attn.k_proj.weight": "model-00022-of-00033.safetensors",
+        "model.decoder.layers.22.self_attn.v_proj.weight": "model-00022-of-00033.safetensors",
+        "model.decoder.layers.22.self_attn.o_proj.weight": "model-00022-of-00033.safetensors",
+        "model.decoder.layers.22.feed_forward.w1.weight": "model-00022-of-00033.safetensors",
+        "model.decoder.layers.22.feed_forward.w2.weight": "model-00022-of-00033.safetensors",
+        "model.decoder.layers.22.feed_forward.w3.weight": "model-00022-of-00033.safetensors",
+        "model.decoder.layers.22.attention_norm.weight": "model-00022-of-00033.safetensors",
+        "model.decoder.layers.22.ffn_norm.weight": "model-00022-of-00033.safetensors",
+        "model.decoder.layers.23.self_attn.q_proj.weight": "model-00023-of-00033.safetensors",
+        "model.decoder.layers.23.self_attn.k_proj.weight": "model-00023-of-00033.safetensors",
+        "model.decoder.layers.23.self_attn.v_proj.weight": "model-00023-of-00033.safetensors",
+        "model.decoder.layers.23.self_attn.o_proj.weight": "model-00023-of-00033.safetensors",
+        "model.decoder.layers.23.feed_forward.w1.weight": "model-00023-of-00033.safetensors",
+        "model.decoder.layers.23.feed_forward.w2.weight": "model-00023-of-00033.safetensors",
+        "model.decoder.layers.23.feed_forward.w3.weight": "model-00023-of-00033.safetensors",
+        "model.decoder.layers.23.attention_norm.weight": "model-00023-of-00033.safetensors",
+        "model.decoder.layers.23.ffn_norm.weight": "model-00023-of-00033.safetensors",
+        "model.decoder.layers.24.self_attn.q_proj.weight": "model-00024-of-00033.safetensors",
+        "model.decoder.layers.24.self_attn.k_proj.weight": "model-00024-of-00033.safetensors",
+        "model.decoder.layers.24.self_attn.v_proj.weight": "model-00024-of-00033.safetensors",
+        "model.decoder.layers.24.self_attn.o_proj.weight": "model-00024-of-00033.safetensors",
+        "model.decoder.layers.24.feed_forward.w1.weight": "model-00024-of-00033.safetensors",
+        "model.decoder.layers.24.feed_forward.w2.weight": "model-00024-of-00033.safetensors",
+        "model.decoder.layers.24.feed_forward.w3.weight": "model-00024-of-00033.safetensors",
+        "model.decoder.layers.24.attention_norm.weight": "model-00024-of-00033.safetensors",
+        "model.decoder.layers.24.ffn_norm.weight": "model-00024-of-00033.safetensors",
+        "model.decoder.layers.25.self_attn.q_proj.weight": "model-00025-of-00033.safetensors",
+        "model.decoder.layers.25.self_attn.k_proj.weight": "model-00025-of-00033.safetensors",
+        "model.decoder.layers.25.self_attn.v_proj.weight": "model-00025-of-00033.safetensors",
+        "model.decoder.layers.25.self_attn.o_proj.weight": "model-00025-of-00033.safetensors",
+        "model.decoder.layers.25.feed_forward.w1.weight": "model-00025-of-00033.safetensors",
+        "model.decoder.layers.25.feed_forward.w2.weight": "model-00025-of-00033.safetensors",
+        "model.decoder.layers.25.feed_forward.w3.weight": "model-00025-of-00033.safetensors",
+        "model.decoder.layers.25.attention_norm.weight": "model-00025-of-00033.safetensors",
+        "model.decoder.layers.25.ffn_norm.weight": "model-00025-of-00033.safetensors",
+        "model.decoder.layers.26.self_attn.q_proj.weight": "model-00026-of-00033.safetensors",
+        "model.decoder.layers.26.self_attn.k_proj.weight": "model-00026-of-00033.safetensors",
+        "model.decoder.layers.26.self_attn.v_proj.weight": "model-00026-of-00033.safetensors",
+        "model.decoder.layers.26.self_attn.o_proj.weight": "model-00026-of-00033.safetensors",
+        "model.decoder.layers.26.feed_forward.w1.weight": "model-00026-of-00033.safetensors",
+        "model.decoder.layers.26.feed_forward.w2.weight": "model-00026-of-00033.safetensors",
+        "model.decoder.layers.26.feed_forward.w3.weight": "model-00026-of-00033.safetensors",
+        "model.decoder.layers.26.attention_norm.weight": "model-00026-of-00033.safetensors",
+        "model.decoder.layers.26.ffn_norm.weight": "model-00026-of-00033.safetensors",
+        "model.decoder.layers.27.self_attn.q_proj.weight": "model-00027-of-00033.safetensors",
+        "model.decoder.layers.27.self_attn.k_proj.weight": "model-00027-of-00033.safetensors",
+        "model.decoder.layers.27.self_attn.v_proj.weight": "model-00027-of-00033.safetensors",
+        "model.decoder.layers.27.self_attn.o_proj.weight": "model-00027-of-00033.safetensors",
+        "model.decoder.layers.27.feed_forward.w1.weight": "model-00027-of-00033.safetensors",
+        "model.decoder.layers.27.feed_forward.w2.weight": "model-00027-of-00033.safetensors",
+        "model.decoder.layers.27.feed_forward.w3.weight": "model-00027-of-00033.safetensors",
+        "model.decoder.layers.27.attention_norm.weight": "model-00027-of-00033.safetensors",
+        "model.decoder.layers.27.ffn_norm.weight": "model-00027-of-00033.safetensors",
+        "model.decoder.layers.28.self_attn.q_proj.weight": "model-00028-of-00033.safetensors",
+        "model.decoder.layers.28.self_attn.k_proj.weight": "model-00028-of-00033.safetensors",
+        "model.decoder.layers.28.self_attn.v_proj.weight": "model-00028-of-00033.safetensors",
+        "model.decoder.layers.28.self_attn.o_proj.weight": "model-00028-of-00033.safetensors",
+        "model.decoder.layers.28.feed_forward.w1.weight": "model-00028-of-00033.safetensors",
+        "model.decoder.layers.28.feed_forward.w2.weight": "model-00028-of-00033.safetensors",
+        "model.decoder.layers.28.feed_forward.w3.weight": "model-00028-of-00033.safetensors",
+        "model.decoder.layers.28.attention_norm.weight": "model-00028-of-00033.safetensors",
+        "model.decoder.layers.28.ffn_norm.weight": "model-00028-of-00033.safetensors",
+        "model.decoder.layers.29.self_attn.q_proj.weight": "model-00029-of-00033.safetensors",
+        "model.decoder.layers.29.self_attn.k_proj.weight": "model-00029-of-00033.safetensors",
+        "model.decoder.layers.29.self_attn.v_proj.weight": "model-00029-of-00033.safetensors",
+        "model.decoder.layers.29.self_attn.o_proj.weight": "model-00029-of-00033.safetensors",
+        "model.decoder.layers.29.feed_forward.w1.weight": "model-00029-of-00033.safetensors",
+        "model.decoder.layers.29.feed_forward.w2.weight": "model-00029-of-00033.safetensors",
+        "model.decoder.layers.29.feed_forward.w3.weight": "model-00029-of-00033.safetensors",
+        "model.decoder.layers.29.attention_norm.weight": "model-00029-of-00033.safetensors",
+        "model.decoder.layers.29.ffn_norm.weight": "model-00029-of-00033.safetensors",
+        "model.decoder.layers.30.self_attn.q_proj.weight": "model-00030-of-00033.safetensors",
+        "model.decoder.layers.30.self_attn.k_proj.weight": "model-00030-of-00033.safetensors",
+        "model.decoder.layers.30.self_attn.v_proj.weight": "model-00030-of-00033.safetensors",
+        "model.decoder.layers.30.self_attn.o_proj.weight": "model-00030-of-00033.safetensors",
+        "model.decoder.layers.30.feed_forward.w1.weight": "model-00030-of-00033.safetensors",
+        "model.decoder.layers.30.feed_forward.w2.weight": "model-00030-of-00033.safetensors",
+        "model.decoder.layers.30.feed_forward.w3.weight": "model-00030-of-00033.safetensors",
+        "model.decoder.layers.30.attention_norm.weight": "model-00030-of-00033.safetensors",
+        "model.decoder.layers.30.ffn_norm.weight": "model-00030-of-00033.safetensors",
+        "model.decoder.layers.31.self_attn.q_proj.weight": "model-00031-of-00033.safetensors",
+        "model.decoder.layers.31.self_attn.k_proj.weight": "model-00031-of-00033.safetensors",
+        "model.decoder.layers.31.self_attn.v_proj.weight": "model-00031-of-00033.safetensors",
+        "model.decoder.layers.31.self_attn.o_proj.weight": "model-00031-of-00033.safetensors",
+        "model.decoder.layers.31.feed_forward.w1.weight": "model-00031-of-00033.safetensors",
+        "model.decoder.layers.31.feed_forward.w2.weight": "model-00031-of-00033.safetensors",
+        "model.decoder.layers.31.feed_forward.w3.weight": "model-00031-of-00033.safetensors",
+        "model.decoder.layers.31.attention_norm.weight": "model-00031-of-00033.safetensors",
+        "model.decoder.layers.31.ffn_norm.weight": "model-00031-of-00033.safetensors",
+        "model.decoder.embed_tokens.weight": "model-00032-of-00033.safetensors",
+        "model.decoder.norm.weight": "model-00032-of-00033.safetensors",
+        "lm_head.weight": "model-00032-of-00033.safetensors"
+    },
+    "metadata": {
+        "total_size": 13476831232
+    }
+}