Adding `safetensors` variant of this model

This is an automated PR created with https://huggingface.co/spaces/safetensors/convert

This new file is equivalent to `pytorch_model.bin` but safe in the sense that
no arbitrary code can be put into it.

These files also happen to load much faster than their pytorch counterpart:
https://colab.research.google.com/github/huggingface/notebooks/blob/main/safetensors_doc/en/speed.ipynb

The widgets on your model page will run using this model even if this is not merged
making sure the file actually works.

If you find any issues: please report here: https://huggingface.co/spaces/safetensors/convert/discussions

Feel free to ignore this PR.

model-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3f4e2b56ccc4e4d702024ae8a8b7b8538b0102b80c913ec23d6a378aa66c7d1
+size 1969362072

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f30929dfce04b28cb3cfd6735c236f7b44703db32075448f88edadf7667315c
+size 1933828880

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4099d0a0e4bb7131b0a47edb46f48defc0cbca85526d959c756ad7ef4f1e23f8
+size 1933828912

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3565e174cd555aa88fc1733982883e9afebe037ec5cd3b570cfffeb5a4bbef2
+size 1990443400

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9daceb91d89ee9b0ba759941e25f05d404bea4747d3b0d58110b63fc8f2c91fd
+size 1990443760

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c06141be4fc9ee3c78f1ba0efb1603a7454241651ed45e49812799a37bbc4e11
+size 1990443768

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35c13599f5104fcf4db20d62037e2f6bb37f5435994250c01ce6300bef923587
+size 1990452040

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27e36be9ee516aec36b628d752a1eba57f14819636658585cc041a0cba3f98d7
+size 845152384

model.safetensors.index.json

@@ -0,0 +1,458 @@
+{
+    "metadata": {
+        "total_size": 14643904512
+    },
+    "weight_map": {
+        "lm_head.weight": "model-00008-of-00008.safetensors",
+        "model.embed_tokens.weight": "model-00001-of-00008.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+        "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.0.self_attn.o_proj.bias": "model-00001-of-00008.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.0.self_attn.rotary_emb.inv_freq": "model-00001-of-00008.safetensors",
+        "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+        "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.1.self_attn.o_proj.bias": "model-00001-of-00008.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.1.self_attn.rotary_emb.inv_freq": "model-00001-of-00008.safetensors",
+        "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00003-of-00008.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+        "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00008.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.10.self_attn.o_proj.bias": "model-00003-of-00008.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00008.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.10.self_attn.rotary_emb.inv_freq": "model-00003-of-00008.safetensors",
+        "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00008.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00003-of-00008.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+        "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00008.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.11.self_attn.o_proj.bias": "model-00003-of-00008.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00008.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.11.self_attn.rotary_emb.inv_freq": "model-00003-of-00008.safetensors",
+        "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00008.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00004-of-00008.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+        "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00008.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.12.self_attn.o_proj.bias": "model-00003-of-00008.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00008.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.12.self_attn.rotary_emb.inv_freq": "model-00003-of-00008.safetensors",
+        "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00008.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00004-of-00008.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+        "model.layers.13.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.13.self_attn.o_proj.bias": "model-00004-of-00008.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.13.self_attn.q_proj.bias": "model-00004-of-00008.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.13.self_attn.rotary_emb.inv_freq": "model-00004-of-00008.safetensors",
+        "model.layers.13.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00004-of-00008.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+        "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.14.self_attn.o_proj.bias": "model-00004-of-00008.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00008.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.14.self_attn.rotary_emb.inv_freq": "model-00004-of-00008.safetensors",
+        "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00004-of-00008.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+        "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.15.self_attn.o_proj.bias": "model-00004-of-00008.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00008.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.15.self_attn.rotary_emb.inv_freq": "model-00004-of-00008.safetensors",
+        "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00004-of-00008.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+        "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.16.self_attn.o_proj.bias": "model-00004-of-00008.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00008.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.16.self_attn.rotary_emb.inv_freq": "model-00004-of-00008.safetensors",
+        "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00005-of-00008.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+        "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.17.self_attn.o_proj.bias": "model-00005-of-00008.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00008.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.17.self_attn.rotary_emb.inv_freq": "model-00005-of-00008.safetensors",
+        "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00005-of-00008.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.18.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+        "model.layers.18.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.18.self_attn.o_proj.bias": "model-00005-of-00008.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.18.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.18.self_attn.rotary_emb.inv_freq": "model-00005-of-00008.safetensors",
+        "model.layers.18.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.19.input_layernorm.weight": "model-00005-of-00008.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.19.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+        "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.19.self_attn.o_proj.bias": "model-00005-of-00008.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.19.self_attn.rotary_emb.inv_freq": "model-00005-of-00008.safetensors",
+        "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00002-of-00008.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+        "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.2.self_attn.o_proj.bias": "model-00001-of-00008.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.2.self_attn.rotary_emb.inv_freq": "model-00001-of-00008.safetensors",
+        "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.20.input_layernorm.weight": "model-00005-of-00008.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.20.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+        "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.20.self_attn.o_proj.bias": "model-00005-of-00008.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.20.self_attn.rotary_emb.inv_freq": "model-00005-of-00008.safetensors",
+        "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.21.input_layernorm.weight": "model-00005-of-00008.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+        "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.21.self_attn.o_proj.bias": "model-00005-of-00008.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.21.self_attn.rotary_emb.inv_freq": "model-00005-of-00008.safetensors",
+        "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00006-of-00008.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.22.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+        "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.22.self_attn.o_proj.bias": "model-00006-of-00008.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.22.self_attn.rotary_emb.inv_freq": "model-00006-of-00008.safetensors",
+        "model.layers.22.self_attn.v_proj.bias": "model-00006-of-00008.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.23.input_layernorm.weight": "model-00006-of-00008.safetensors",
+        "model.layers.23.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.23.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+        "model.layers.23.self_attn.k_proj.bias": "model-00006-of-00008.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.23.self_attn.o_proj.bias": "model-00006-of-00008.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.23.self_attn.q_proj.bias": "model-00006-of-00008.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.23.self_attn.rotary_emb.inv_freq": "model-00006-of-00008.safetensors",
+        "model.layers.23.self_attn.v_proj.bias": "model-00006-of-00008.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.24.input_layernorm.weight": "model-00006-of-00008.safetensors",
+        "model.layers.24.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.24.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+        "model.layers.24.self_attn.k_proj.bias": "model-00006-of-00008.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.24.self_attn.o_proj.bias": "model-00006-of-00008.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.24.self_attn.q_proj.bias": "model-00006-of-00008.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.24.self_attn.rotary_emb.inv_freq": "model-00006-of-00008.safetensors",
+        "model.layers.24.self_attn.v_proj.bias": "model-00006-of-00008.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.25.input_layernorm.weight": "model-00006-of-00008.safetensors",
+        "model.layers.25.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.25.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+        "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00008.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.25.self_attn.o_proj.bias": "model-00006-of-00008.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00008.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.25.self_attn.rotary_emb.inv_freq": "model-00006-of-00008.safetensors",
+        "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00008.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.26.input_layernorm.weight": "model-00006-of-00008.safetensors",
+        "model.layers.26.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.26.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+        "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00008.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.26.self_attn.o_proj.bias": "model-00006-of-00008.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00008.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.26.self_attn.rotary_emb.inv_freq": "model-00006-of-00008.safetensors",
+        "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00008.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.27.input_layernorm.weight": "model-00007-of-00008.safetensors",
+        "model.layers.27.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.27.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+        "model.layers.27.self_attn.k_proj.bias": "model-00007-of-00008.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.27.self_attn.o_proj.bias": "model-00007-of-00008.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00008.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.27.self_attn.rotary_emb.inv_freq": "model-00007-of-00008.safetensors",
+        "model.layers.27.self_attn.v_proj.bias": "model-00007-of-00008.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.28.input_layernorm.weight": "model-00007-of-00008.safetensors",
+        "model.layers.28.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.28.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+        "model.layers.28.self_attn.k_proj.bias": "model-00007-of-00008.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.28.self_attn.o_proj.bias": "model-00007-of-00008.safetensors",
+        "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.28.self_attn.q_proj.bias": "model-00007-of-00008.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.28.self_attn.rotary_emb.inv_freq": "model-00007-of-00008.safetensors",
+        "model.layers.28.self_attn.v_proj.bias": "model-00007-of-00008.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.29.input_layernorm.weight": "model-00007-of-00008.safetensors",
+        "model.layers.29.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.29.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+        "model.layers.29.self_attn.k_proj.bias": "model-00007-of-00008.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.29.self_attn.o_proj.bias": "model-00007-of-00008.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.29.self_attn.q_proj.bias": "model-00007-of-00008.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.29.self_attn.rotary_emb.inv_freq": "model-00007-of-00008.safetensors",
+        "model.layers.29.self_attn.v_proj.bias": "model-00007-of-00008.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00002-of-00008.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+        "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00008.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.3.self_attn.o_proj.bias": "model-00002-of-00008.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00008.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.3.self_attn.rotary_emb.inv_freq": "model-00002-of-00008.safetensors",
+        "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00008.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.30.input_layernorm.weight": "model-00007-of-00008.safetensors",
+        "model.layers.30.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.30.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+        "model.layers.30.self_attn.k_proj.bias": "model-00007-of-00008.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.30.self_attn.o_proj.bias": "model-00007-of-00008.safetensors",
+        "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.30.self_attn.q_proj.bias": "model-00007-of-00008.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.30.self_attn.rotary_emb.inv_freq": "model-00007-of-00008.safetensors",
+        "model.layers.30.self_attn.v_proj.bias": "model-00007-of-00008.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.31.input_layernorm.weight": "model-00007-of-00008.safetensors",
+        "model.layers.31.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.31.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+        "model.layers.31.self_attn.k_proj.bias": "model-00007-of-00008.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.31.self_attn.o_proj.bias": "model-00007-of-00008.safetensors",
+        "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.31.self_attn.q_proj.bias": "model-00007-of-00008.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.31.self_attn.rotary_emb.inv_freq": "model-00007-of-00008.safetensors",
+        "model.layers.31.self_attn.v_proj.bias": "model-00007-of-00008.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00002-of-00008.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+        "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00008.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.4.self_attn.o_proj.bias": "model-00002-of-00008.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00008.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.4.self_attn.rotary_emb.inv_freq": "model-00002-of-00008.safetensors",
+        "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00008.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00002-of-00008.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+        "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00008.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.5.self_attn.o_proj.bias": "model-00002-of-00008.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00008.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.5.self_attn.rotary_emb.inv_freq": "model-00002-of-00008.safetensors",
+        "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00008.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00002-of-00008.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+        "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00008.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.6.self_attn.o_proj.bias": "model-00002-of-00008.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00008.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.6.self_attn.rotary_emb.inv_freq": "model-00002-of-00008.safetensors",
+        "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00008.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00003-of-00008.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+        "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00008.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.7.self_attn.o_proj.bias": "model-00002-of-00008.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00008.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.7.self_attn.rotary_emb.inv_freq": "model-00002-of-00008.safetensors",
+        "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00008.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00003-of-00008.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+        "model.layers.8.self_attn.k_proj.bias": "model-00003-of-00008.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.8.self_attn.o_proj.bias": "model-00003-of-00008.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.8.self_attn.q_proj.bias": "model-00003-of-00008.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.8.self_attn.rotary_emb.inv_freq": "model-00003-of-00008.safetensors",
+        "model.layers.8.self_attn.v_proj.bias": "model-00003-of-00008.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00003-of-00008.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+        "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00008.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.9.self_attn.o_proj.bias": "model-00003-of-00008.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00008.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.9.self_attn.rotary_emb.inv_freq": "model-00003-of-00008.safetensors",
+        "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00008.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+        "model.norm.weight": "model-00007-of-00008.safetensors"
+    }
+}