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-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05c40bfbe2225a6cd3e1f77888951682ce720eac8011e58ee6b045aaf683b903
+size 4918115960

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:118c6d6acf4826b1a4df0151ffb6eba0df8b4edaae64e515d8986fb651c9d8d1
+size 4991642256

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7fee0a2f3d707904c195aa8d249b08e6a32b9a038c982afd5b81ee9a0d92d5d
+size 4991631960

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c904b2ae8384400b3df1578464ecd8d125d957841932dead30639640ac37aec
+size 4991631960

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8102fec371b3dea00a0e9c6fb80267e43693628b199d607fdfc391c516452484
+size 4991631960

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0eea9d37aec1835caca6505ba5e55bdc21bc5f7fbcd7366a9f80ce2995a95d8
+size 3447361816

model.safetensors.index.json

@@ -0,0 +1,490 @@
+{
+    "metadata": {
+        "total_size": 28331960320
+    },
+    "weight_map": {
+        "lm_head.weight": "model-00006-of-00006.safetensors",
+        "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+        "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+        "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.14.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.14.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.14.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.15.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.15.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.15.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.16.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.16.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.16.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+        "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.21.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.22.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.22.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.22.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.23.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.23.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.23.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.23.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.23.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.24.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.24.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.24.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.25.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.25.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.25.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.26.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.26.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.26.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.28.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.28.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.28.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.29.input_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.29.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.29.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.29.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.29.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.29.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+        "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.30.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.30.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.30.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.30.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.30.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.31.input_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.31.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.31.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.31.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.31.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.31.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.32.input_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.32.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.32.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.32.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.32.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.32.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.33.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.33.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.33.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.34.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.34.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.34.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.35.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.35.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.35.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.36.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.36.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.36.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.37.input_layernorm.weight": "model-00006-of-00006.safetensors",
+        "model.layers.37.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.37.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.37.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+        "model.layers.37.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+        "model.layers.37.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.37.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+        "model.layers.37.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.37.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+        "model.layers.37.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.38.input_layernorm.weight": "model-00006-of-00006.safetensors",
+        "model.layers.38.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.38.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.38.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+        "model.layers.38.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+        "model.layers.38.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.38.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.38.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+        "model.layers.38.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.38.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+        "model.layers.38.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.39.input_layernorm.weight": "model-00006-of-00006.safetensors",
+        "model.layers.39.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.39.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+        "model.layers.39.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+        "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.39.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+        "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.39.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+        "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+        "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+        "model.norm.weight": "model-00006-of-00006.safetensors"
+    }
+}