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-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27d2737c2397bb61e6c696586ec6eac0bb5073e148500e91ca9583ef45c341cb
+size 576717976

model-00002-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b885929907860f3a2c5d7e174360e41c4590287f0e1bc609f534a2806a6dc1ce
+size 595626008

model-00003-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cea4087821629a1d365c37aea20d2fd317c85fde3c6f1a5a98636d05605a006d
+size 528500664

model-00004-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0689e384c6bdf72f1be6320561ac93d6b1af267f7d30b7d4fdde4b442405ea9a
+size 585140016

model-00005-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c3b6e55f7abeef28c705ad6a09c79c0a8e2411f7e90b4b5d32e434448a16cb9
+size 538986656

model-00006-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4a6462d229ae810feea708238da221cccde6a3903764e8b70b4d232d2b66e32
+size 585123408

model-00007-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c1c6cdbb041048abddac0b7c37b4da329b1195ed990f129a84efacae07d3ef4
+size 595626008

model-00008-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90089e2cf4faa32ff8183a489f89fa0fcfa87b80b32135596d42d558db153ddf
+size 528500680

model-00009-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41b59f1cb45aa76a32c19f01c8e5540eb2d56d319ef948d50ecc4b4114d19f35
+size 585140032

model-00010-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:956ec870c42a4b8964b13a511bd01aaf002f2d9ed4bf57894d32cb94463bc39a
+size 538986672

model-00011-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e766f11b379fdfeac91f928932ca57a7e41724bf3ab0a6ee11f3ebc9a2b00e94
+size 585123424

model-00012-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8128a7b4f7f3b5c583a42ae4c0f018b70fb59f779998db0ff9921945d37e4ed4
+size 595626024

model-00013-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d379c60f6838aad4695a262ab43fb11704f517bf92d136262d2015970c9d33f2
+size 528500680

model-00014-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c8a3118836c6f3ebb9c56f33cb84423b5b7bb8e862f69ab1dfe361a5600a45e
+size 585140032

model-00015-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3dc7fd8d6afb858727e419bce069733a3b87cd1ac677d5fb43905c769b444c2
+size 538986672

model-00016-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fab7c7317081da83e2d7f20fcb1786371a5bf285ee6e759d9f326fd4f65c3caa
+size 585123424

model-00017-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9cd3b19654b05b6351dfdc8a0e2afedb4e01881d4f87b5e9a9554ba15ad9977
+size 595626024

model-00018-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:608859cbade79b51a2815d8f2f3b3d885369df986ec60fc3917a84d48529df7c
+size 528500680

model-00019-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0d5370d579ee1316ebefb7d8572916e016096553ce52f4a5ea94407d202d3e7
+size 585140032

model-00020-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdf6c3402537eda34356fea5427157abdddbbea9ce016708c08886991d8a2c6d
+size 538986672

model-00021-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec3a318793dac155ac8107b27fc2a909da3fb869a037a0d0214f3c0e80a49c44
+size 585123424

model-00022-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bae5a36f2b4bc34388840c674bc32317b9d033bde2e843c3d03e404e5aed9407
+size 595626024

model-00023-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cebfba2528570dcde0e876eb0d5a7d5f289369a44aefec803acd88e161214eb6
+size 528500680

model-00024-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43733d2b21f08f8dad70fbf3a8e2fb9c3c40dfea2d68cb5ce6e42bb6a6b3b692
+size 442524312

model.safetensors.index.json

@@ -0,0 +1,330 @@
+{
+    "metadata": {
+        "total_size": 13476839424
+    },
+    "weight_map": {
+        "lm_head.weight": "model-00024-of-00024.safetensors",
+        "model.embed_tokens.weight": "model-00001-of-00024.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00002-of-00024.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model-00001-of-00024.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00024.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model-00002-of-00024.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00024.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00024.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00024.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00024.safetensors",
+        "model.layers.0.self_attn.rotary_emb.inv_freq": "model-00001-of-00024.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00024.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00002-of-00024.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model-00002-of-00024.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00024.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model-00002-of-00024.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00024.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00024.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00024.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00024.safetensors",
+        "model.layers.1.self_attn.rotary_emb.inv_freq": "model-00002-of-00024.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00024.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00009-of-00024.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model-00009-of-00024.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "model-00008-of-00024.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model-00009-of-00024.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model-00009-of-00024.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model-00008-of-00024.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model-00008-of-00024.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model-00008-of-00024.safetensors",
+        "model.layers.10.self_attn.rotary_emb.inv_freq": "model-00008-of-00024.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model-00008-of-00024.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00009-of-00024.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model-00009-of-00024.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "model-00009-of-00024.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model-00009-of-00024.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model-00009-of-00024.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model-00009-of-00024.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model-00009-of-00024.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model-00009-of-00024.safetensors",
+        "model.layers.11.self_attn.rotary_emb.inv_freq": "model-00009-of-00024.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model-00009-of-00024.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00010-of-00024.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model-00010-of-00024.safetensors",
+        "model.layers.12.mlp.gate_proj.weight": "model-00010-of-00024.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model-00010-of-00024.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model-00010-of-00024.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model-00010-of-00024.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model-00010-of-00024.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model-00010-of-00024.safetensors",
+        "model.layers.12.self_attn.rotary_emb.inv_freq": "model-00010-of-00024.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model-00010-of-00024.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00011-of-00024.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model-00011-of-00024.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "model-00011-of-00024.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model-00011-of-00024.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model-00011-of-00024.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model-00010-of-00024.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model-00010-of-00024.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model-00010-of-00024.safetensors",
+        "model.layers.13.self_attn.rotary_emb.inv_freq": "model-00010-of-00024.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model-00010-of-00024.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00012-of-00024.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model-00011-of-00024.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model-00011-of-00024.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model-00012-of-00024.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00012-of-00024.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00011-of-00024.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00011-of-00024.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00011-of-00024.safetensors",
+        "model.layers.14.self_attn.rotary_emb.inv_freq": "model-00011-of-00024.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00011-of-00024.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00012-of-00024.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model-00012-of-00024.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model-00012-of-00024.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model-00012-of-00024.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model-00012-of-00024.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00012-of-00024.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00012-of-00024.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00012-of-00024.safetensors",
+        "model.layers.15.self_attn.rotary_emb.inv_freq": "model-00012-of-00024.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00012-of-00024.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00013-of-00024.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model-00013-of-00024.safetensors",
+        "model.layers.16.mlp.gate_proj.weight": "model-00013-of-00024.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "model-00013-of-00024.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model-00013-of-00024.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model-00012-of-00024.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model-00013-of-00024.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model-00012-of-00024.safetensors",
+        "model.layers.16.self_attn.rotary_emb.inv_freq": "model-00013-of-00024.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model-00012-of-00024.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00014-of-00024.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model-00014-of-00024.safetensors",
+        "model.layers.17.mlp.gate_proj.weight": "model-00013-of-00024.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model-00014-of-00024.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model-00014-of-00024.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model-00013-of-00024.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model-00013-of-00024.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model-00013-of-00024.safetensors",
+        "model.layers.17.self_attn.rotary_emb.inv_freq": "model-00013-of-00024.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model-00013-of-00024.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00014-of-00024.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "model-00014-of-00024.safetensors",
+        "model.layers.18.mlp.gate_proj.weight": "model-00014-of-00024.safetensors",
+        "model.layers.18.mlp.up_proj.weight": "model-00014-of-00024.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model-00014-of-00024.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model-00014-of-00024.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model-00014-of-00024.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model-00014-of-00024.safetensors",
+        "model.layers.18.self_attn.rotary_emb.inv_freq": "model-00014-of-00024.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model-00014-of-00024.safetensors",
+        "model.layers.19.input_layernorm.weight": "model-00015-of-00024.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "model-00015-of-00024.safetensors",
+        "model.layers.19.mlp.gate_proj.weight": "model-00015-of-00024.safetensors",
+        "model.layers.19.mlp.up_proj.weight": "model-00015-of-00024.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model-00015-of-00024.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model-00015-of-00024.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model-00015-of-00024.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model-00015-of-00024.safetensors",
+        "model.layers.19.self_attn.rotary_emb.inv_freq": "model-00015-of-00024.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model-00015-of-00024.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00003-of-00024.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model-00003-of-00024.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00024.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model-00003-of-00024.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00024.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00024.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00024.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00024.safetensors",
+        "model.layers.2.self_attn.rotary_emb.inv_freq": "model-00003-of-00024.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00024.safetensors",
+        "model.layers.20.input_layernorm.weight": "model-00016-of-00024.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model-00016-of-00024.safetensors",
+        "model.layers.20.mlp.gate_proj.weight": "model-00016-of-00024.safetensors",
+        "model.layers.20.mlp.up_proj.weight": "model-00016-of-00024.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model-00016-of-00024.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model-00015-of-00024.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model-00015-of-00024.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model-00015-of-00024.safetensors",
+        "model.layers.20.self_attn.rotary_emb.inv_freq": "model-00015-of-00024.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model-00015-of-00024.safetensors",
+        "model.layers.21.input_layernorm.weight": "model-00017-of-00024.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "model-00016-of-00024.safetensors",
+        "model.layers.21.mlp.gate_proj.weight": "model-00016-of-00024.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "model-00017-of-00024.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model-00017-of-00024.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model-00016-of-00024.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model-00016-of-00024.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model-00016-of-00024.safetensors",
+        "model.layers.21.self_attn.rotary_emb.inv_freq": "model-00016-of-00024.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model-00016-of-00024.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00017-of-00024.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "model-00017-of-00024.safetensors",
+        "model.layers.22.mlp.gate_proj.weight": "model-00017-of-00024.safetensors",
+        "model.layers.22.mlp.up_proj.weight": "model-00017-of-00024.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model-00017-of-00024.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model-00017-of-00024.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model-00017-of-00024.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model-00017-of-00024.safetensors",
+        "model.layers.22.self_attn.rotary_emb.inv_freq": "model-00017-of-00024.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model-00017-of-00024.safetensors",
+        "model.layers.23.input_layernorm.weight": "model-00018-of-00024.safetensors",
+        "model.layers.23.mlp.down_proj.weight": "model-00018-of-00024.safetensors",
+        "model.layers.23.mlp.gate_proj.weight": "model-00018-of-00024.safetensors",
+        "model.layers.23.mlp.up_proj.weight": "model-00018-of-00024.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model-00018-of-00024.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model-00017-of-00024.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model-00018-of-00024.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model-00017-of-00024.safetensors",
+        "model.layers.23.self_attn.rotary_emb.inv_freq": "model-00018-of-00024.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model-00017-of-00024.safetensors",
+        "model.layers.24.input_layernorm.weight": "model-00019-of-00024.safetensors",
+        "model.layers.24.mlp.down_proj.weight": "model-00019-of-00024.safetensors",
+        "model.layers.24.mlp.gate_proj.weight": "model-00018-of-00024.safetensors",
+        "model.layers.24.mlp.up_proj.weight": "model-00019-of-00024.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model-00019-of-00024.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model-00018-of-00024.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model-00018-of-00024.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model-00018-of-00024.safetensors",
+        "model.layers.24.self_attn.rotary_emb.inv_freq": "model-00018-of-00024.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model-00018-of-00024.safetensors",
+        "model.layers.25.input_layernorm.weight": "model-00019-of-00024.safetensors",
+        "model.layers.25.mlp.down_proj.weight": "model-00019-of-00024.safetensors",
+        "model.layers.25.mlp.gate_proj.weight": "model-00019-of-00024.safetensors",
+        "model.layers.25.mlp.up_proj.weight": "model-00019-of-00024.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model-00019-of-00024.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model-00019-of-00024.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model-00019-of-00024.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model-00019-of-00024.safetensors",
+        "model.layers.25.self_attn.rotary_emb.inv_freq": "model-00019-of-00024.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model-00019-of-00024.safetensors",
+        "model.layers.26.input_layernorm.weight": "model-00020-of-00024.safetensors",
+        "model.layers.26.mlp.down_proj.weight": "model-00020-of-00024.safetensors",
+        "model.layers.26.mlp.gate_proj.weight": "model-00020-of-00024.safetensors",
+        "model.layers.26.mlp.up_proj.weight": "model-00020-of-00024.safetensors",
+        "model.layers.26.post_attention_layernorm.weight": "model-00020-of-00024.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model-00020-of-00024.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model-00020-of-00024.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model-00020-of-00024.safetensors",
+        "model.layers.26.self_attn.rotary_emb.inv_freq": "model-00020-of-00024.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model-00020-of-00024.safetensors",
+        "model.layers.27.input_layernorm.weight": "model-00021-of-00024.safetensors",
+        "model.layers.27.mlp.down_proj.weight": "model-00021-of-00024.safetensors",
+        "model.layers.27.mlp.gate_proj.weight": "model-00021-of-00024.safetensors",
+        "model.layers.27.mlp.up_proj.weight": "model-00021-of-00024.safetensors",
+        "model.layers.27.post_attention_layernorm.weight": "model-00021-of-00024.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model-00020-of-00024.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model-00020-of-00024.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model-00020-of-00024.safetensors",
+        "model.layers.27.self_attn.rotary_emb.inv_freq": "model-00020-of-00024.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model-00020-of-00024.safetensors",
+        "model.layers.28.input_layernorm.weight": "model-00022-of-00024.safetensors",
+        "model.layers.28.mlp.down_proj.weight": "model-00021-of-00024.safetensors",
+        "model.layers.28.mlp.gate_proj.weight": "model-00021-of-00024.safetensors",
+        "model.layers.28.mlp.up_proj.weight": "model-00022-of-00024.safetensors",
+        "model.layers.28.post_attention_layernorm.weight": "model-00022-of-00024.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "model-00021-of-00024.safetensors",
+        "model.layers.28.self_attn.o_proj.weight": "model-00021-of-00024.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "model-00021-of-00024.safetensors",
+        "model.layers.28.self_attn.rotary_emb.inv_freq": "model-00021-of-00024.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "model-00021-of-00024.safetensors",
+        "model.layers.29.input_layernorm.weight": "model-00022-of-00024.safetensors",
+        "model.layers.29.mlp.down_proj.weight": "model-00022-of-00024.safetensors",
+        "model.layers.29.mlp.gate_proj.weight": "model-00022-of-00024.safetensors",
+        "model.layers.29.mlp.up_proj.weight": "model-00022-of-00024.safetensors",
+        "model.layers.29.post_attention_layernorm.weight": "model-00022-of-00024.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "model-00022-of-00024.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "model-00022-of-00024.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model-00022-of-00024.safetensors",
+        "model.layers.29.self_attn.rotary_emb.inv_freq": "model-00022-of-00024.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model-00022-of-00024.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00004-of-00024.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model-00004-of-00024.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00024.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model-00004-of-00024.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00024.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00024.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00024.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00024.safetensors",
+        "model.layers.3.self_attn.rotary_emb.inv_freq": "model-00003-of-00024.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00024.safetensors",
+        "model.layers.30.input_layernorm.weight": "model-00023-of-00024.safetensors",
+        "model.layers.30.mlp.down_proj.weight": "model-00023-of-00024.safetensors",
+        "model.layers.30.mlp.gate_proj.weight": "model-00023-of-00024.safetensors",
+        "model.layers.30.mlp.up_proj.weight": "model-00023-of-00024.safetensors",
+        "model.layers.30.post_attention_layernorm.weight": "model-00023-of-00024.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "model-00022-of-00024.safetensors",
+        "model.layers.30.self_attn.o_proj.weight": "model-00023-of-00024.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "model-00022-of-00024.safetensors",
+        "model.layers.30.self_attn.rotary_emb.inv_freq": "model-00023-of-00024.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "model-00022-of-00024.safetensors",
+        "model.layers.31.input_layernorm.weight": "model-00024-of-00024.safetensors",
+        "model.layers.31.mlp.down_proj.weight": "model-00024-of-00024.safetensors",
+        "model.layers.31.mlp.gate_proj.weight": "model-00023-of-00024.safetensors",
+        "model.layers.31.mlp.up_proj.weight": "model-00024-of-00024.safetensors",
+        "model.layers.31.post_attention_layernorm.weight": "model-00024-of-00024.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "model-00023-of-00024.safetensors",
+        "model.layers.31.self_attn.o_proj.weight": "model-00023-of-00024.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "model-00023-of-00024.safetensors",
+        "model.layers.31.self_attn.rotary_emb.inv_freq": "model-00023-of-00024.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "model-00023-of-00024.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00004-of-00024.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model-00004-of-00024.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "model-00004-of-00024.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model-00004-of-00024.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00024.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00024.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00024.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00024.safetensors",
+        "model.layers.4.self_attn.rotary_emb.inv_freq": "model-00004-of-00024.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00024.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00005-of-00024.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model-00005-of-00024.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "model-00005-of-00024.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model-00005-of-00024.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model-00005-of-00024.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model-00005-of-00024.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model-00005-of-00024.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model-00005-of-00024.safetensors",
+        "model.layers.5.self_attn.rotary_emb.inv_freq": "model-00005-of-00024.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model-00005-of-00024.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00006-of-00024.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model-00006-of-00024.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model-00006-of-00024.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model-00006-of-00024.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model-00006-of-00024.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model-00005-of-00024.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model-00005-of-00024.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model-00005-of-00024.safetensors",
+        "model.layers.6.self_attn.rotary_emb.inv_freq": "model-00005-of-00024.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model-00005-of-00024.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00007-of-00024.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model-00006-of-00024.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model-00006-of-00024.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model-00007-of-00024.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model-00007-of-00024.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model-00006-of-00024.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00006-of-00024.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model-00006-of-00024.safetensors",
+        "model.layers.7.self_attn.rotary_emb.inv_freq": "model-00006-of-00024.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model-00006-of-00024.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00007-of-00024.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model-00007-of-00024.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model-00007-of-00024.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model-00007-of-00024.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model-00007-of-00024.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model-00007-of-00024.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model-00007-of-00024.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model-00007-of-00024.safetensors",
+        "model.layers.8.self_attn.rotary_emb.inv_freq": "model-00007-of-00024.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model-00007-of-00024.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00008-of-00024.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model-00008-of-00024.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model-00008-of-00024.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model-00008-of-00024.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model-00008-of-00024.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model-00007-of-00024.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00008-of-00024.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model-00007-of-00024.safetensors",
+        "model.layers.9.self_attn.rotary_emb.inv_freq": "model-00008-of-00024.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model-00007-of-00024.safetensors",
+        "model.norm.weight": "model-00024-of-00024.safetensors"
+    }
+}