Adding `safetensors` variant of this model (#2)

- Adding `safetensors` variant of this model (372e0385cb74f5973c27148bbf17983a4bc591a7)


Co-authored-by: Safetensors convertbot <SFconvertbot@users.noreply.huggingface.co>

model-00001-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c2ac74bbbfb37117881620e13ac548241ca52c768a9b316b9f0d97f041d8d53
+size 3990716416

model-00002-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b71f58437db0fd368d556bcda6009e4b442d44c927504d1f44152021ca87338
+size 3925979792

model-00003-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c17627e7b854d03835684751130a8cff1668a82c629c15a41a5b13368c01cb1
+size 3803270160

model-00004-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b21c0e1bc77c31a25b7b973d8e01a98a59bc21f52977ccd1af699a07f4a6c6c
+size 3953243040

model-00005-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d60ae3f7e5b49c9f6e7d52111a69441ec53bef38c0b4b820a9fdf6a3c0d8a54
+size 3776006968

model-00006-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe403ecb658b5c8e7258187c25d500c42a370e84e28abcdc692e0453bd7cc628
+size 3803297032

model-00007-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1834c0de521e32b038bc1ee71fac942f4c704b14be4e5d215e24a5884841da26
+size 3925979824

model-00008-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b8c5306c212e9991d161ca555c69ac39b3a05c9c115f82c9eae09c6865b14dd
+size 3803270176

model-00009-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0045da2b7a7731166c34f3682f04cb3cb6506e3e8da5e554fa55f7b486ec9467
+size 3953243040

model-00010-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12d61fa267ad9d31d6f9582a4331b8d71edac5a32300fbfd0527f50393765b4e
+size 3776006968

model-00011-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5321c98c207f2e069dcc022a7669865af49e46775652578910efb09b7e947a68
+size 3803297032

model-00012-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f044932c3988b560e761957a6016ec8f6dee5e03f204fc71ba9818d252d0430a
+size 3925979824

model-00013-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31f246c4bff771afe4a88f15edd487edc26e2b8187806730422777faf1c0a9f1
+size 3803270176

model-00014-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b6cc8c4b490a516ef9840fdb4abafb51449cfa7476d7ebdbc34da630cc8ee7b
+size 3953243040

model-00015-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c619e40885bf472e24bc515b87be5d21dfb190fa9c56cb45380fd962d5dc86f6
+size 3776006968

model-00016-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d72dacd4c930f3faafddb5a4a8f7c2ebfa84579bc3c582d2fe8d6c17b4eaa6bb
+size 3803297032

model-00017-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81d4d34e0af39f83e36952a394de76966bac4b3307282ade94ab4dbd1f6695e3
+size 3281890816

model.safetensors.index.json

@@ -0,0 +1,610 @@
+{
+    "metadata": {
+        "total_size": 65057929216
+    },
+    "weight_map": {
+        "lm_head.weight": "model-00017-of-00017.safetensors",
+        "model.embed_tokens.weight": "model-00001-of-00017.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00001-of-00017.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model-00001-of-00017.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00017.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model-00001-of-00017.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00017.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00017.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00017.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00017.safetensors",
+        "model.layers.0.self_attn.rotary_emb.inv_freq": "model-00001-of-00017.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00017.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00001-of-00017.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model-00001-of-00017.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00017.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model-00001-of-00017.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00017.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00017.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00017.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00017.safetensors",
+        "model.layers.1.self_attn.rotary_emb.inv_freq": "model-00001-of-00017.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00017.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00004-of-00017.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model-00004-of-00017.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00017.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00017.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00017.safetensors",
+        "model.layers.10.self_attn.rotary_emb.inv_freq": "model-00003-of-00017.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00017.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00004-of-00017.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model-00004-of-00017.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00017.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00017.safetensors",
+        "model.layers.11.self_attn.rotary_emb.inv_freq": "model-00004-of-00017.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00017.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00004-of-00017.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model-00004-of-00017.safetensors",
+        "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00017.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00017.safetensors",
+        "model.layers.12.self_attn.rotary_emb.inv_freq": "model-00004-of-00017.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00017.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00004-of-00017.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model-00004-of-00017.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00017.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00017.safetensors",
+        "model.layers.13.self_attn.rotary_emb.inv_freq": "model-00004-of-00017.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00017.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00005-of-00017.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00017.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model-00005-of-00017.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00017.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00017.safetensors",
+        "model.layers.14.self_attn.rotary_emb.inv_freq": "model-00005-of-00017.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00017.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00005-of-00017.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00017.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model-00005-of-00017.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00017.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00017.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00017.safetensors",
+        "model.layers.15.self_attn.rotary_emb.inv_freq": "model-00005-of-00017.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00017.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00005-of-00017.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
+        "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00017.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "model-00005-of-00017.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00017.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00017.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00017.safetensors",
+        "model.layers.16.self_attn.rotary_emb.inv_freq": "model-00005-of-00017.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00017.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00006-of-00017.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
+        "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00017.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model-00006-of-00017.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00017.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00017.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00017.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00017.safetensors",
+        "model.layers.17.self_attn.rotary_emb.inv_freq": "model-00005-of-00017.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00017.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00006-of-00017.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "model-00006-of-00017.safetensors",
+        "model.layers.18.mlp.gate_proj.weight": "model-00006-of-00017.safetensors",
+        "model.layers.18.mlp.up_proj.weight": "model-00006-of-00017.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00017.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
+        "model.layers.18.self_attn.rotary_emb.inv_freq": "model-00006-of-00017.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
+        "model.layers.19.input_layernorm.weight": "model-00006-of-00017.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "model-00006-of-00017.safetensors",
+        "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00017.safetensors",
+        "model.layers.19.mlp.up_proj.weight": "model-00006-of-00017.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00017.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
+        "model.layers.19.self_attn.rotary_emb.inv_freq": "model-00006-of-00017.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00001-of-00017.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model-00001-of-00017.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00017.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model-00001-of-00017.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00017.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00017.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00017.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00017.safetensors",
+        "model.layers.2.self_attn.rotary_emb.inv_freq": "model-00001-of-00017.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00017.safetensors",
+        "model.layers.20.input_layernorm.weight": "model-00006-of-00017.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model-00006-of-00017.safetensors",
+        "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00017.safetensors",
+        "model.layers.20.mlp.up_proj.weight": "model-00006-of-00017.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00017.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
+        "model.layers.20.self_attn.rotary_emb.inv_freq": "model-00006-of-00017.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
+        "model.layers.21.input_layernorm.weight": "model-00007-of-00017.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "model-00007-of-00017.safetensors",
+        "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "model-00007-of-00017.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
+        "model.layers.21.self_attn.rotary_emb.inv_freq": "model-00006-of-00017.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00007-of-00017.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "model-00007-of-00017.safetensors",
+        "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
+        "model.layers.22.mlp.up_proj.weight": "model-00007-of-00017.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00017.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00017.safetensors",
+        "model.layers.22.self_attn.rotary_emb.inv_freq": "model-00007-of-00017.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00017.safetensors",
+        "model.layers.23.input_layernorm.weight": "model-00007-of-00017.safetensors",
+        "model.layers.23.mlp.down_proj.weight": "model-00007-of-00017.safetensors",
+        "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
+        "model.layers.23.mlp.up_proj.weight": "model-00007-of-00017.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00017.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00017.safetensors",
+        "model.layers.23.self_attn.rotary_emb.inv_freq": "model-00007-of-00017.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00017.safetensors",
+        "model.layers.24.input_layernorm.weight": "model-00007-of-00017.safetensors",
+        "model.layers.24.mlp.down_proj.weight": "model-00007-of-00017.safetensors",
+        "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
+        "model.layers.24.mlp.up_proj.weight": "model-00007-of-00017.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00017.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00017.safetensors",
+        "model.layers.24.self_attn.rotary_emb.inv_freq": "model-00007-of-00017.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00017.safetensors",
+        "model.layers.25.input_layernorm.weight": "model-00008-of-00017.safetensors",
+        "model.layers.25.mlp.down_proj.weight": "model-00008-of-00017.safetensors",
+        "model.layers.25.mlp.gate_proj.weight": "model-00008-of-00017.safetensors",
+        "model.layers.25.mlp.up_proj.weight": "model-00008-of-00017.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
+        "model.layers.25.self_attn.rotary_emb.inv_freq": "model-00008-of-00017.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
+        "model.layers.26.input_layernorm.weight": "model-00008-of-00017.safetensors",
+        "model.layers.26.mlp.down_proj.weight": "model-00008-of-00017.safetensors",
+        "model.layers.26.mlp.gate_proj.weight": "model-00008-of-00017.safetensors",
+        "model.layers.26.mlp.up_proj.weight": "model-00008-of-00017.safetensors",
+        "model.layers.26.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
+        "model.layers.26.self_attn.rotary_emb.inv_freq": "model-00008-of-00017.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
+        "model.layers.27.input_layernorm.weight": "model-00008-of-00017.safetensors",
+        "model.layers.27.mlp.down_proj.weight": "model-00008-of-00017.safetensors",
+        "model.layers.27.mlp.gate_proj.weight": "model-00008-of-00017.safetensors",
+        "model.layers.27.mlp.up_proj.weight": "model-00008-of-00017.safetensors",
+        "model.layers.27.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
+        "model.layers.27.self_attn.rotary_emb.inv_freq": "model-00008-of-00017.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
+        "model.layers.28.input_layernorm.weight": "model-00009-of-00017.safetensors",
+        "model.layers.28.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
+        "model.layers.28.mlp.gate_proj.weight": "model-00008-of-00017.safetensors",
+        "model.layers.28.mlp.up_proj.weight": "model-00009-of-00017.safetensors",
+        "model.layers.28.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
+        "model.layers.28.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
+        "model.layers.28.self_attn.rotary_emb.inv_freq": "model-00008-of-00017.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
+        "model.layers.29.input_layernorm.weight": "model-00009-of-00017.safetensors",
+        "model.layers.29.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
+        "model.layers.29.mlp.gate_proj.weight": "model-00009-of-00017.safetensors",
+        "model.layers.29.mlp.up_proj.weight": "model-00009-of-00017.safetensors",
+        "model.layers.29.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "model-00009-of-00017.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model-00009-of-00017.safetensors",
+        "model.layers.29.self_attn.rotary_emb.inv_freq": "model-00009-of-00017.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model-00009-of-00017.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00002-of-00017.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00017.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00017.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00017.safetensors",
+        "model.layers.3.self_attn.rotary_emb.inv_freq": "model-00001-of-00017.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00017.safetensors",
+        "model.layers.30.input_layernorm.weight": "model-00009-of-00017.safetensors",
+        "model.layers.30.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
+        "model.layers.30.mlp.gate_proj.weight": "model-00009-of-00017.safetensors",
+        "model.layers.30.mlp.up_proj.weight": "model-00009-of-00017.safetensors",
+        "model.layers.30.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "model-00009-of-00017.safetensors",
+        "model.layers.30.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "model-00009-of-00017.safetensors",
+        "model.layers.30.self_attn.rotary_emb.inv_freq": "model-00009-of-00017.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "model-00009-of-00017.safetensors",
+        "model.layers.31.input_layernorm.weight": "model-00009-of-00017.safetensors",
+        "model.layers.31.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
+        "model.layers.31.mlp.gate_proj.weight": "model-00009-of-00017.safetensors",
+        "model.layers.31.mlp.up_proj.weight": "model-00009-of-00017.safetensors",
+        "model.layers.31.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "model-00009-of-00017.safetensors",
+        "model.layers.31.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "model-00009-of-00017.safetensors",
+        "model.layers.31.self_attn.rotary_emb.inv_freq": "model-00009-of-00017.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "model-00009-of-00017.safetensors",
+        "model.layers.32.input_layernorm.weight": "model-00010-of-00017.safetensors",
+        "model.layers.32.mlp.down_proj.weight": "model-00010-of-00017.safetensors",
+        "model.layers.32.mlp.gate_proj.weight": "model-00010-of-00017.safetensors",
+        "model.layers.32.mlp.up_proj.weight": "model-00010-of-00017.safetensors",
+        "model.layers.32.post_attention_layernorm.weight": "model-00010-of-00017.safetensors",
+        "model.layers.32.self_attn.k_proj.weight": "model-00009-of-00017.safetensors",
+        "model.layers.32.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
+        "model.layers.32.self_attn.q_proj.weight": "model-00009-of-00017.safetensors",
+        "model.layers.32.self_attn.rotary_emb.inv_freq": "model-00010-of-00017.safetensors",
+        "model.layers.32.self_attn.v_proj.weight": "model-00009-of-00017.safetensors",
+        "model.layers.33.input_layernorm.weight": "model-00010-of-00017.safetensors",
+        "model.layers.33.mlp.down_proj.weight": "model-00010-of-00017.safetensors",
+        "model.layers.33.mlp.gate_proj.weight": "model-00010-of-00017.safetensors",
+        "model.layers.33.mlp.up_proj.weight": "model-00010-of-00017.safetensors",
+        "model.layers.33.post_attention_layernorm.weight": "model-00010-of-00017.safetensors",
+        "model.layers.33.self_attn.k_proj.weight": "model-00010-of-00017.safetensors",
+        "model.layers.33.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
+        "model.layers.33.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
+        "model.layers.33.self_attn.rotary_emb.inv_freq": "model-00010-of-00017.safetensors",
+        "model.layers.33.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
+        "model.layers.34.input_layernorm.weight": "model-00010-of-00017.safetensors",
+        "model.layers.34.mlp.down_proj.weight": "model-00010-of-00017.safetensors",
+        "model.layers.34.mlp.gate_proj.weight": "model-00010-of-00017.safetensors",
+        "model.layers.34.mlp.up_proj.weight": "model-00010-of-00017.safetensors",
+        "model.layers.34.post_attention_layernorm.weight": "model-00010-of-00017.safetensors",
+        "model.layers.34.self_attn.k_proj.weight": "model-00010-of-00017.safetensors",
+        "model.layers.34.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
+        "model.layers.34.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
+        "model.layers.34.self_attn.rotary_emb.inv_freq": "model-00010-of-00017.safetensors",
+        "model.layers.34.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
+        "model.layers.35.input_layernorm.weight": "model-00011-of-00017.safetensors",
+        "model.layers.35.mlp.down_proj.weight": "model-00010-of-00017.safetensors",
+        "model.layers.35.mlp.gate_proj.weight": "model-00010-of-00017.safetensors",
+        "model.layers.35.mlp.up_proj.weight": "model-00011-of-00017.safetensors",
+        "model.layers.35.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
+        "model.layers.35.self_attn.k_proj.weight": "model-00010-of-00017.safetensors",
+        "model.layers.35.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
+        "model.layers.35.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
+        "model.layers.35.self_attn.rotary_emb.inv_freq": "model-00010-of-00017.safetensors",
+        "model.layers.35.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
+        "model.layers.36.input_layernorm.weight": "model-00011-of-00017.safetensors",
+        "model.layers.36.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
+        "model.layers.36.mlp.gate_proj.weight": "model-00011-of-00017.safetensors",
+        "model.layers.36.mlp.up_proj.weight": "model-00011-of-00017.safetensors",
+        "model.layers.36.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
+        "model.layers.36.self_attn.k_proj.weight": "model-00011-of-00017.safetensors",
+        "model.layers.36.self_attn.o_proj.weight": "model-00011-of-00017.safetensors",
+        "model.layers.36.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
+        "model.layers.36.self_attn.rotary_emb.inv_freq": "model-00011-of-00017.safetensors",
+        "model.layers.36.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
+        "model.layers.37.input_layernorm.weight": "model-00011-of-00017.safetensors",
+        "model.layers.37.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
+        "model.layers.37.mlp.gate_proj.weight": "model-00011-of-00017.safetensors",
+        "model.layers.37.mlp.up_proj.weight": "model-00011-of-00017.safetensors",
+        "model.layers.37.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
+        "model.layers.37.self_attn.k_proj.weight": "model-00011-of-00017.safetensors",
+        "model.layers.37.self_attn.o_proj.weight": "model-00011-of-00017.safetensors",
+        "model.layers.37.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
+        "model.layers.37.self_attn.rotary_emb.inv_freq": "model-00011-of-00017.safetensors",
+        "model.layers.37.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
+        "model.layers.38.input_layernorm.weight": "model-00011-of-00017.safetensors",
+        "model.layers.38.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
+        "model.layers.38.mlp.gate_proj.weight": "model-00011-of-00017.safetensors",
+        "model.layers.38.mlp.up_proj.weight": "model-00011-of-00017.safetensors",
+        "model.layers.38.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
+        "model.layers.38.self_attn.k_proj.weight": "model-00011-of-00017.safetensors",
+        "model.layers.38.self_attn.o_proj.weight": "model-00011-of-00017.safetensors",
+        "model.layers.38.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
+        "model.layers.38.self_attn.rotary_emb.inv_freq": "model-00011-of-00017.safetensors",
+        "model.layers.38.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
+        "model.layers.39.input_layernorm.weight": "model-00012-of-00017.safetensors",
+        "model.layers.39.mlp.down_proj.weight": "model-00012-of-00017.safetensors",
+        "model.layers.39.mlp.gate_proj.weight": "model-00012-of-00017.safetensors",
+        "model.layers.39.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
+        "model.layers.39.post_attention_layernorm.weight": "model-00012-of-00017.safetensors",
+        "model.layers.39.self_attn.k_proj.weight": "model-00011-of-00017.safetensors",
+        "model.layers.39.self_attn.o_proj.weight": "model-00011-of-00017.safetensors",
+        "model.layers.39.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
+        "model.layers.39.self_attn.rotary_emb.inv_freq": "model-00011-of-00017.safetensors",
+        "model.layers.39.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00002-of-00017.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
+        "model.layers.4.self_attn.rotary_emb.inv_freq": "model-00002-of-00017.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
+        "model.layers.40.input_layernorm.weight": "model-00012-of-00017.safetensors",
+        "model.layers.40.mlp.down_proj.weight": "model-00012-of-00017.safetensors",
+        "model.layers.40.mlp.gate_proj.weight": "model-00012-of-00017.safetensors",
+        "model.layers.40.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
+        "model.layers.40.post_attention_layernorm.weight": "model-00012-of-00017.safetensors",
+        "model.layers.40.self_attn.k_proj.weight": "model-00012-of-00017.safetensors",
+        "model.layers.40.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
+        "model.layers.40.self_attn.q_proj.weight": "model-00012-of-00017.safetensors",
+        "model.layers.40.self_attn.rotary_emb.inv_freq": "model-00012-of-00017.safetensors",
+        "model.layers.40.self_attn.v_proj.weight": "model-00012-of-00017.safetensors",
+        "model.layers.41.input_layernorm.weight": "model-00012-of-00017.safetensors",
+        "model.layers.41.mlp.down_proj.weight": "model-00012-of-00017.safetensors",
+        "model.layers.41.mlp.gate_proj.weight": "model-00012-of-00017.safetensors",
+        "model.layers.41.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
+        "model.layers.41.post_attention_layernorm.weight": "model-00012-of-00017.safetensors",
+        "model.layers.41.self_attn.k_proj.weight": "model-00012-of-00017.safetensors",
+        "model.layers.41.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
+        "model.layers.41.self_attn.q_proj.weight": "model-00012-of-00017.safetensors",
+        "model.layers.41.self_attn.rotary_emb.inv_freq": "model-00012-of-00017.safetensors",
+        "model.layers.41.self_attn.v_proj.weight": "model-00012-of-00017.safetensors",
+        "model.layers.42.input_layernorm.weight": "model-00012-of-00017.safetensors",
+        "model.layers.42.mlp.down_proj.weight": "model-00012-of-00017.safetensors",
+        "model.layers.42.mlp.gate_proj.weight": "model-00012-of-00017.safetensors",
+        "model.layers.42.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
+        "model.layers.42.post_attention_layernorm.weight": "model-00012-of-00017.safetensors",
+        "model.layers.42.self_attn.k_proj.weight": "model-00012-of-00017.safetensors",
+        "model.layers.42.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
+        "model.layers.42.self_attn.q_proj.weight": "model-00012-of-00017.safetensors",
+        "model.layers.42.self_attn.rotary_emb.inv_freq": "model-00012-of-00017.safetensors",
+        "model.layers.42.self_attn.v_proj.weight": "model-00012-of-00017.safetensors",
+        "model.layers.43.input_layernorm.weight": "model-00013-of-00017.safetensors",
+        "model.layers.43.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
+        "model.layers.43.mlp.gate_proj.weight": "model-00013-of-00017.safetensors",
+        "model.layers.43.mlp.up_proj.weight": "model-00013-of-00017.safetensors",
+        "model.layers.43.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
+        "model.layers.43.self_attn.k_proj.weight": "model-00013-of-00017.safetensors",
+        "model.layers.43.self_attn.o_proj.weight": "model-00013-of-00017.safetensors",
+        "model.layers.43.self_attn.q_proj.weight": "model-00013-of-00017.safetensors",
+        "model.layers.43.self_attn.rotary_emb.inv_freq": "model-00013-of-00017.safetensors",
+        "model.layers.43.self_attn.v_proj.weight": "model-00013-of-00017.safetensors",
+        "model.layers.44.input_layernorm.weight": "model-00013-of-00017.safetensors",
+        "model.layers.44.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
+        "model.layers.44.mlp.gate_proj.weight": "model-00013-of-00017.safetensors",
+        "model.layers.44.mlp.up_proj.weight": "model-00013-of-00017.safetensors",
+        "model.layers.44.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
+        "model.layers.44.self_attn.k_proj.weight": "model-00013-of-00017.safetensors",
+        "model.layers.44.self_attn.o_proj.weight": "model-00013-of-00017.safetensors",
+        "model.layers.44.self_attn.q_proj.weight": "model-00013-of-00017.safetensors",
+        "model.layers.44.self_attn.rotary_emb.inv_freq": "model-00013-of-00017.safetensors",
+        "model.layers.44.self_attn.v_proj.weight": "model-00013-of-00017.safetensors",
+        "model.layers.45.input_layernorm.weight": "model-00013-of-00017.safetensors",
+        "model.layers.45.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
+        "model.layers.45.mlp.gate_proj.weight": "model-00013-of-00017.safetensors",
+        "model.layers.45.mlp.up_proj.weight": "model-00013-of-00017.safetensors",
+        "model.layers.45.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
+        "model.layers.45.self_attn.k_proj.weight": "model-00013-of-00017.safetensors",
+        "model.layers.45.self_attn.o_proj.weight": "model-00013-of-00017.safetensors",
+        "model.layers.45.self_attn.q_proj.weight": "model-00013-of-00017.safetensors",
+        "model.layers.45.self_attn.rotary_emb.inv_freq": "model-00013-of-00017.safetensors",
+        "model.layers.45.self_attn.v_proj.weight": "model-00013-of-00017.safetensors",
+        "model.layers.46.input_layernorm.weight": "model-00014-of-00017.safetensors",
+        "model.layers.46.mlp.down_proj.weight": "model-00014-of-00017.safetensors",
+        "model.layers.46.mlp.gate_proj.weight": "model-00013-of-00017.safetensors",
+        "model.layers.46.mlp.up_proj.weight": "model-00014-of-00017.safetensors",
+        "model.layers.46.post_attention_layernorm.weight": "model-00014-of-00017.safetensors",
+        "model.layers.46.self_attn.k_proj.weight": "model-00013-of-00017.safetensors",
+        "model.layers.46.self_attn.o_proj.weight": "model-00013-of-00017.safetensors",
+        "model.layers.46.self_attn.q_proj.weight": "model-00013-of-00017.safetensors",
+        "model.layers.46.self_attn.rotary_emb.inv_freq": "model-00013-of-00017.safetensors",
+        "model.layers.46.self_attn.v_proj.weight": "model-00013-of-00017.safetensors",
+        "model.layers.47.input_layernorm.weight": "model-00014-of-00017.safetensors",
+        "model.layers.47.mlp.down_proj.weight": "model-00014-of-00017.safetensors",
+        "model.layers.47.mlp.gate_proj.weight": "model-00014-of-00017.safetensors",
+        "model.layers.47.mlp.up_proj.weight": "model-00014-of-00017.safetensors",
+        "model.layers.47.post_attention_layernorm.weight": "model-00014-of-00017.safetensors",
+        "model.layers.47.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
+        "model.layers.47.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
+        "model.layers.47.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
+        "model.layers.47.self_attn.rotary_emb.inv_freq": "model-00014-of-00017.safetensors",
+        "model.layers.47.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
+        "model.layers.48.input_layernorm.weight": "model-00014-of-00017.safetensors",
+        "model.layers.48.mlp.down_proj.weight": "model-00014-of-00017.safetensors",
+        "model.layers.48.mlp.gate_proj.weight": "model-00014-of-00017.safetensors",
+        "model.layers.48.mlp.up_proj.weight": "model-00014-of-00017.safetensors",
+        "model.layers.48.post_attention_layernorm.weight": "model-00014-of-00017.safetensors",
+        "model.layers.48.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
+        "model.layers.48.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
+        "model.layers.48.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
+        "model.layers.48.self_attn.rotary_emb.inv_freq": "model-00014-of-00017.safetensors",
+        "model.layers.48.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
+        "model.layers.49.input_layernorm.weight": "model-00014-of-00017.safetensors",
+        "model.layers.49.mlp.down_proj.weight": "model-00014-of-00017.safetensors",
+        "model.layers.49.mlp.gate_proj.weight": "model-00014-of-00017.safetensors",
+        "model.layers.49.mlp.up_proj.weight": "model-00014-of-00017.safetensors",
+        "model.layers.49.post_attention_layernorm.weight": "model-00014-of-00017.safetensors",
+        "model.layers.49.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
+        "model.layers.49.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
+        "model.layers.49.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
+        "model.layers.49.self_attn.rotary_emb.inv_freq": "model-00014-of-00017.safetensors",
+        "model.layers.49.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00002-of-00017.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
+        "model.layers.5.self_attn.rotary_emb.inv_freq": "model-00002-of-00017.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
+        "model.layers.50.input_layernorm.weight": "model-00015-of-00017.safetensors",
+        "model.layers.50.mlp.down_proj.weight": "model-00015-of-00017.safetensors",
+        "model.layers.50.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
+        "model.layers.50.mlp.up_proj.weight": "model-00015-of-00017.safetensors",
+        "model.layers.50.post_attention_layernorm.weight": "model-00015-of-00017.safetensors",
+        "model.layers.50.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
+        "model.layers.50.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
+        "model.layers.50.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
+        "model.layers.50.self_attn.rotary_emb.inv_freq": "model-00015-of-00017.safetensors",
+        "model.layers.50.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
+        "model.layers.51.input_layernorm.weight": "model-00015-of-00017.safetensors",
+        "model.layers.51.mlp.down_proj.weight": "model-00015-of-00017.safetensors",
+        "model.layers.51.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
+        "model.layers.51.mlp.up_proj.weight": "model-00015-of-00017.safetensors",
+        "model.layers.51.post_attention_layernorm.weight": "model-00015-of-00017.safetensors",
+        "model.layers.51.self_attn.k_proj.weight": "model-00015-of-00017.safetensors",
+        "model.layers.51.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
+        "model.layers.51.self_attn.q_proj.weight": "model-00015-of-00017.safetensors",
+        "model.layers.51.self_attn.rotary_emb.inv_freq": "model-00015-of-00017.safetensors",
+        "model.layers.51.self_attn.v_proj.weight": "model-00015-of-00017.safetensors",
+        "model.layers.52.input_layernorm.weight": "model-00015-of-00017.safetensors",
+        "model.layers.52.mlp.down_proj.weight": "model-00015-of-00017.safetensors",
+        "model.layers.52.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
+        "model.layers.52.mlp.up_proj.weight": "model-00015-of-00017.safetensors",
+        "model.layers.52.post_attention_layernorm.weight": "model-00015-of-00017.safetensors",
+        "model.layers.52.self_attn.k_proj.weight": "model-00015-of-00017.safetensors",
+        "model.layers.52.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
+        "model.layers.52.self_attn.q_proj.weight": "model-00015-of-00017.safetensors",
+        "model.layers.52.self_attn.rotary_emb.inv_freq": "model-00015-of-00017.safetensors",
+        "model.layers.52.self_attn.v_proj.weight": "model-00015-of-00017.safetensors",
+        "model.layers.53.input_layernorm.weight": "model-00016-of-00017.safetensors",
+        "model.layers.53.mlp.down_proj.weight": "model-00015-of-00017.safetensors",
+        "model.layers.53.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
+        "model.layers.53.mlp.up_proj.weight": "model-00016-of-00017.safetensors",
+        "model.layers.53.post_attention_layernorm.weight": "model-00016-of-00017.safetensors",
+        "model.layers.53.self_attn.k_proj.weight": "model-00015-of-00017.safetensors",
+        "model.layers.53.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
+        "model.layers.53.self_attn.q_proj.weight": "model-00015-of-00017.safetensors",
+        "model.layers.53.self_attn.rotary_emb.inv_freq": "model-00015-of-00017.safetensors",
+        "model.layers.53.self_attn.v_proj.weight": "model-00015-of-00017.safetensors",
+        "model.layers.54.input_layernorm.weight": "model-00016-of-00017.safetensors",
+        "model.layers.54.mlp.down_proj.weight": "model-00016-of-00017.safetensors",
+        "model.layers.54.mlp.gate_proj.weight": "model-00016-of-00017.safetensors",
+        "model.layers.54.mlp.up_proj.weight": "model-00016-of-00017.safetensors",
+        "model.layers.54.post_attention_layernorm.weight": "model-00016-of-00017.safetensors",
+        "model.layers.54.self_attn.k_proj.weight": "model-00016-of-00017.safetensors",
+        "model.layers.54.self_attn.o_proj.weight": "model-00016-of-00017.safetensors",
+        "model.layers.54.self_attn.q_proj.weight": "model-00016-of-00017.safetensors",
+        "model.layers.54.self_attn.rotary_emb.inv_freq": "model-00016-of-00017.safetensors",
+        "model.layers.54.self_attn.v_proj.weight": "model-00016-of-00017.safetensors",
+        "model.layers.55.input_layernorm.weight": "model-00016-of-00017.safetensors",
+        "model.layers.55.mlp.down_proj.weight": "model-00016-of-00017.safetensors",
+        "model.layers.55.mlp.gate_proj.weight": "model-00016-of-00017.safetensors",
+        "model.layers.55.mlp.up_proj.weight": "model-00016-of-00017.safetensors",
+        "model.layers.55.post_attention_layernorm.weight": "model-00016-of-00017.safetensors",
+        "model.layers.55.self_attn.k_proj.weight": "model-00016-of-00017.safetensors",
+        "model.layers.55.self_attn.o_proj.weight": "model-00016-of-00017.safetensors",
+        "model.layers.55.self_attn.q_proj.weight": "model-00016-of-00017.safetensors",
+        "model.layers.55.self_attn.rotary_emb.inv_freq": "model-00016-of-00017.safetensors",
+        "model.layers.55.self_attn.v_proj.weight": "model-00016-of-00017.safetensors",
+        "model.layers.56.input_layernorm.weight": "model-00016-of-00017.safetensors",
+        "model.layers.56.mlp.down_proj.weight": "model-00016-of-00017.safetensors",
+        "model.layers.56.mlp.gate_proj.weight": "model-00016-of-00017.safetensors",
+        "model.layers.56.mlp.up_proj.weight": "model-00016-of-00017.safetensors",
+        "model.layers.56.post_attention_layernorm.weight": "model-00016-of-00017.safetensors",
+        "model.layers.56.self_attn.k_proj.weight": "model-00016-of-00017.safetensors",
+        "model.layers.56.self_attn.o_proj.weight": "model-00016-of-00017.safetensors",
+        "model.layers.56.self_attn.q_proj.weight": "model-00016-of-00017.safetensors",
+        "model.layers.56.self_attn.rotary_emb.inv_freq": "model-00016-of-00017.safetensors",
+        "model.layers.56.self_attn.v_proj.weight": "model-00016-of-00017.safetensors",
+        "model.layers.57.input_layernorm.weight": "model-00017-of-00017.safetensors",
+        "model.layers.57.mlp.down_proj.weight": "model-00017-of-00017.safetensors",
+        "model.layers.57.mlp.gate_proj.weight": "model-00017-of-00017.safetensors",
+        "model.layers.57.mlp.up_proj.weight": "model-00017-of-00017.safetensors",
+        "model.layers.57.post_attention_layernorm.weight": "model-00017-of-00017.safetensors",
+        "model.layers.57.self_attn.k_proj.weight": "model-00016-of-00017.safetensors",
+        "model.layers.57.self_attn.o_proj.weight": "model-00016-of-00017.safetensors",
+        "model.layers.57.self_attn.q_proj.weight": "model-00016-of-00017.safetensors",
+        "model.layers.57.self_attn.rotary_emb.inv_freq": "model-00016-of-00017.safetensors",
+        "model.layers.57.self_attn.v_proj.weight": "model-00016-of-00017.safetensors",
+        "model.layers.58.input_layernorm.weight": "model-00017-of-00017.safetensors",
+        "model.layers.58.mlp.down_proj.weight": "model-00017-of-00017.safetensors",
+        "model.layers.58.mlp.gate_proj.weight": "model-00017-of-00017.safetensors",
+        "model.layers.58.mlp.up_proj.weight": "model-00017-of-00017.safetensors",
+        "model.layers.58.post_attention_layernorm.weight": "model-00017-of-00017.safetensors",
+        "model.layers.58.self_attn.k_proj.weight": "model-00017-of-00017.safetensors",
+        "model.layers.58.self_attn.o_proj.weight": "model-00017-of-00017.safetensors",
+        "model.layers.58.self_attn.q_proj.weight": "model-00017-of-00017.safetensors",
+        "model.layers.58.self_attn.rotary_emb.inv_freq": "model-00017-of-00017.safetensors",
+        "model.layers.58.self_attn.v_proj.weight": "model-00017-of-00017.safetensors",
+        "model.layers.59.input_layernorm.weight": "model-00017-of-00017.safetensors",
+        "model.layers.59.mlp.down_proj.weight": "model-00017-of-00017.safetensors",
+        "model.layers.59.mlp.gate_proj.weight": "model-00017-of-00017.safetensors",
+        "model.layers.59.mlp.up_proj.weight": "model-00017-of-00017.safetensors",
+        "model.layers.59.post_attention_layernorm.weight": "model-00017-of-00017.safetensors",
+        "model.layers.59.self_attn.k_proj.weight": "model-00017-of-00017.safetensors",
+        "model.layers.59.self_attn.o_proj.weight": "model-00017-of-00017.safetensors",
+        "model.layers.59.self_attn.q_proj.weight": "model-00017-of-00017.safetensors",
+        "model.layers.59.self_attn.rotary_emb.inv_freq": "model-00017-of-00017.safetensors",
+        "model.layers.59.self_attn.v_proj.weight": "model-00017-of-00017.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00002-of-00017.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
+        "model.layers.6.self_attn.rotary_emb.inv_freq": "model-00002-of-00017.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00003-of-00017.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model-00003-of-00017.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model-00003-of-00017.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00017.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00017.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00017.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00017.safetensors",
+        "model.layers.7.self_attn.rotary_emb.inv_freq": "model-00003-of-00017.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00017.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00003-of-00017.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model-00003-of-00017.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model-00003-of-00017.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00017.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00017.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00017.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00017.safetensors",
+        "model.layers.8.self_attn.rotary_emb.inv_freq": "model-00003-of-00017.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00017.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00003-of-00017.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model-00003-of-00017.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model-00003-of-00017.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00017.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00017.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00017.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00017.safetensors",
+        "model.layers.9.self_attn.rotary_emb.inv_freq": "model-00003-of-00017.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00017.safetensors",
+        "model.norm.weight": "model-00017-of-00017.safetensors"
+    }
+}