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 sha256:6d77eaf477d0f7181418d9133561c22355c0e46b8c90f2660eb255cf47b18a4a
+size 1969362072

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:525d587c91aebda2e911a4ed404af345786a7c511652c8ef57b3a23e63b6abe5
+size 1933828880

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9f30980d079e85eaa15119ede43612b2ca50094793c8036ad21ef1de327c9d2
+size 1933828912

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:738d21b4b1485448ae7e088258cb5f0e9fa09c2bc2132d50ed1fb3d918755675
+size 1990443400

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1185db0ff5f3f534960aa88863b116afbf6641ef6909ca4ca11d062e93dad95
+size 1990443760

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93a94299f9eb30d73099a0ebf88b01eece48477b8f81d849ebcf3101a32871ae
+size 1990443768

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:475d47a9373aab676aab0389c08b015f1f5eea55d7394155ff198e1d78e92fe8
+size 1990452040

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8343e5fb26a257203bd2957b40f0fe09553bfec5f2c955b1d418fc901108aa7
+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"
+    }
+}