From 406085e2f97635684b7d0705e91e46b31f89accd Mon Sep 17 00:00:00 2001
From: ai-modelscope <ai@modelscope.cn>
Date: Sat, 15 Feb 2025 20:06:20 +0800
Subject: [PATCH] Update README.md

---
 LICENSE                          |   51 +
 config.json                      |   16 +-
 generation_config.json           |    1 +
 model-00001-of-00011.safetensors |    3 -
 model-00002-of-00011.safetensors |    3 -
 model-00003-of-00011.safetensors |    3 -
 model-00004-of-00011.safetensors |    3 -
 model-00005-of-00011.safetensors |    3 -
 model-00006-of-00011.safetensors |    3 -
 model-00007-of-00011.safetensors |    3 -
 model-00008-of-00011.safetensors |    3 -
 model-00009-of-00011.safetensors |    3 -
 model-00010-of-00011.safetensors |    3 -
 model-00011-of-00011.safetensors |    3 -
 model.safetensors.index.json     | 3596 ++++++++++--------------------
 15 files changed, 1181 insertions(+), 2516 deletions(-)
 create mode 100644 LICENSE
 delete mode 100644 model-00001-of-00011.safetensors
 delete mode 100644 model-00002-of-00011.safetensors
 delete mode 100644 model-00003-of-00011.safetensors
 delete mode 100644 model-00004-of-00011.safetensors
 delete mode 100644 model-00005-of-00011.safetensors
 delete mode 100644 model-00006-of-00011.safetensors
 delete mode 100644 model-00007-of-00011.safetensors
 delete mode 100644 model-00008-of-00011.safetensors
 delete mode 100644 model-00009-of-00011.safetensors
 delete mode 100644 model-00010-of-00011.safetensors
 delete mode 100644 model-00011-of-00011.safetensors

diff --git a/LICENSE b/LICENSE
new file mode 100644
index 0000000..6cb169c
--- /dev/null
+++ b/LICENSE
@@ -0,0 +1,51 @@
+Qwen LICENSE AGREEMENT
+
+Qwen LICENSE AGREEMENT Release Date: September 19, 2024
+
+By clicking to agree or by using or distributing any portion or element of the Qwen Materials, you will be deemed to have recognized and accepted the content of this Agreement, which is effective immediately.
+
+1. Definitions
+    a. This Qwen LICENSE AGREEMENT (this "Agreement") shall mean the terms and conditions for use, reproduction, distribution and modification of the Materials as defined by this Agreement.
+    b. "We" (or "Us") shall mean Alibaba Cloud.
+    c. "You" (or "Your") shall mean a natural person or legal entity exercising the rights granted by this Agreement and/or using the Materials for any purpose and in any field of use.
+    d. "Third Parties" shall mean individuals or legal entities that are not under common control with us or you.
+    e. "Qwen" shall mean the large language models, and software and algorithms, consisting of trained model weights, parameters (including optimizer states), machine-learning model code, inference-enabling code, training-enabling code, fine-tuning enabling code and other elements of the foregoing distributed by us.
+    f. "Materials" shall mean, collectively, Alibaba Cloud's proprietary Qwen and Documentation (and any portion thereof) made available under this Agreement.
+    g. "Source" form shall mean the preferred form for making modifications, including but not limited to model source code, documentation source, and configuration files.
+    h. "Object" form shall mean any form resulting from mechanical transformation or translation of a Source form, including but not limited to compiled object code, generated documentation, and conversions to other media types.
+
+2. Grant of Rights
+You are granted a non-exclusive, worldwide, non-transferable and royalty-free limited license under Alibaba Cloud's intellectual property or other rights owned by us embodied in the Materials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the Materials.
+
+3. Redistribution
+You may distribute copies or make the Materials, or derivative works thereof, available as part of a product or service that contains any of them, with or without modifications, and in Source or Object form, provided that you meet the following conditions:
+    a. You shall give any other recipients of the Materials or derivative works a copy of this Agreement;
+    b. You shall cause any modified files to carry prominent notices stating that you changed the files;
+    c. You shall retain in all copies of the Materials that you distribute the following attribution notices within a "Notice" text file distributed as a part of such copies: "Qwen is licensed under the Qwen LICENSE AGREEMENT, Copyright (c) Alibaba Cloud. All Rights Reserved."; and
+    d. You may add your own copyright statement to your modifications and may provide additional or different license terms and conditions for use, reproduction, or distribution of your modifications, or for any such derivative works as a whole, provided your use, reproduction, and distribution of the work otherwise complies with the terms and conditions of this Agreement.
+
+4. Restrictions
+If you are commercially using the Materials, and your product or service has more than 100 million monthly active users, you shall request a license from us. You cannot exercise your rights under this Agreement without our express authorization.
+
+5. Rules of use
+    a. The Materials may be subject to export controls or restrictions in China, the United States or other countries or regions. You shall comply with applicable laws and regulations in your use of the Materials.
+    b. If you use the Materials or any outputs or results therefrom to create, train, fine-tune, or improve an AI model that is distributed or made available, you shall prominently display “Built with Qwen” or “Improved using Qwen” in the related product documentation.
+
+6. Intellectual Property
+    a. We retain ownership of all intellectual property rights in and to the Materials and derivatives made by or for us. Conditioned upon compliance with the terms and conditions of this Agreement, with respect to any derivative works and modifications of the Materials that are made by you, you are and will be the owner of such derivative works and modifications.
+    b. No trademark license is granted to use the trade names, trademarks, service marks, or product names of us, except as required to fulfill notice requirements under this Agreement or as required for reasonable and customary use in describing and redistributing the Materials.
+    c. If you commence a lawsuit or other proceedings (including a cross-claim or counterclaim in a lawsuit) against us or any entity alleging that the Materials or any output therefrom, or any part of the foregoing, infringe any intellectual property or other right owned or licensable by you, then all licenses granted to you under this Agreement shall terminate as of the date such lawsuit or other proceeding is commenced or brought.
+
+7. Disclaimer of Warranty and Limitation of Liability
+    a. We are not obligated to support, update, provide training for, or develop any further version of the Qwen Materials or to grant any license thereto.
+    b. THE MATERIALS ARE PROVIDED "AS IS" WITHOUT ANY EXPRESS OR IMPLIED WARRANTY OF ANY KIND INCLUDING WARRANTIES OF MERCHANTABILITY, NONINFRINGEMENT, OR FITNESS FOR A PARTICULAR PURPOSE. WE MAKE NO WARRANTY AND ASSUME NO RESPONSIBILITY FOR THE SAFETY OR STABILITY OF THE MATERIALS AND ANY OUTPUT THEREFROM.
+    c. IN NO EVENT SHALL WE BE LIABLE TO YOU FOR ANY DAMAGES, INCLUDING, BUT NOT LIMITED TO ANY DIRECT, OR INDIRECT, SPECIAL OR CONSEQUENTIAL DAMAGES ARISING FROM YOUR USE OR INABILITY TO USE THE MATERIALS OR ANY OUTPUT OF IT, NO MATTER HOW IT’S CAUSED.
+    d. You will defend, indemnify and hold harmless us from and against any claim by any third party arising out of or related to your use or distribution of the Materials.
+
+8. Survival and Termination.
+    a. The term of this Agreement shall commence upon your acceptance of this Agreement or access to the Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein.
+    b. We may terminate this Agreement if you breach any of the terms or conditions of this Agreement. Upon termination of this Agreement, you must delete and cease use of the Materials. Sections 7 and 9 shall survive the termination of this Agreement.
+
+9. Governing Law and Jurisdiction.
+    a. This Agreement and any dispute arising out of or relating to it will be governed by the laws of China, without regard to conflict of law principles, and the UN Convention on Contracts for the International Sale of Goods does not apply to this Agreement.
+    b. The People's Courts in Hangzhou City shall have exclusive jurisdiction over any dispute arising out of this Agreement.
diff --git a/config.json b/config.json
index 62a0d77..52884b6 100644
--- a/config.json
+++ b/config.json
@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "Qwen/Qwen2.5-VL-72B-Instruct",
+  "_name_or_path": "Qwen/Qwen2.5-VL-7B-Instruct",
   "architectures": [
     "Qwen2_5_VLForConditionalGeneration"
   ],
@@ -7,16 +7,16 @@
   "bos_token_id": 151643,
   "eos_token_id": 151645,
   "hidden_act": "silu",
-  "hidden_size": 8192,
+  "hidden_size": 3584,
   "image_token_id": 151655,
   "initializer_range": 0.02,
-  "intermediate_size": 29568,
+  "intermediate_size": 18944,
   "max_position_embeddings": 128000,
-  "max_window_layers": 80,
+  "max_window_layers": 28,
   "model_type": "qwen2_5_vl",
-  "num_attention_heads": 64,
-  "num_hidden_layers": 80,
-  "num_key_value_heads": 8,
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
   "quantization_config": {
     "bits": 4,
     "group_size": 128,
@@ -48,9 +48,7 @@
   "vision_config": {
     "hidden_size": 1280,
     "in_chans": 3,
-    "intermediate_size": 3456,
     "model_type": "qwen2_5_vl",
-    "out_hidden_size": 8192,
     "spatial_patch_size": 14,
     "tokens_per_second": 2,
     "torch_dtype": "bfloat16"
diff --git a/generation_config.json b/generation_config.json
index ee397dd..e70c840 100644
--- a/generation_config.json
+++ b/generation_config.json
@@ -7,6 +7,7 @@
   ],
   "pad_token_id": 151643,
   "repetition_penalty": 1.05,
+  "temperature": 0.1,
   "top_k": 1,
   "top_p": 0.001,
   "transformers_version": "4.49.0.dev0"
diff --git a/model-00001-of-00011.safetensors b/model-00001-of-00011.safetensors
deleted file mode 100644
index 9083150..0000000
--- a/model-00001-of-00011.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5aa03692a761ca148c4e2c8ca861cb5197695f2b04a47fed5caecb8e6f434f87
-size 3979075232
diff --git a/model-00002-of-00011.safetensors b/model-00002-of-00011.safetensors
deleted file mode 100644
index 6faf595..0000000
--- a/model-00002-of-00011.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:57d329bf91b1206ebc8e5d1bf20dc3381b3a50e2e4467576478f3a3a416c150f
-size 3899899512
diff --git a/model-00003-of-00011.safetensors b/model-00003-of-00011.safetensors
deleted file mode 100644
index 7592d5f..0000000
--- a/model-00003-of-00011.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:66990f734c4a69320bd766620c95ddae1fe9697208bf2bcb8a473d1e6eec1fd0
-size 3978401488
diff --git a/model-00004-of-00011.safetensors b/model-00004-of-00011.safetensors
deleted file mode 100644
index 1e50729..0000000
--- a/model-00004-of-00011.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:246bf8e838e2ffebb751023591e4f3321128025ad35b8f8a2b379d94687b72b4
-size 3978401520
diff --git a/model-00005-of-00011.safetensors b/model-00005-of-00011.safetensors
deleted file mode 100644
index dfa55d7..0000000
--- a/model-00005-of-00011.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c2b7aca7356426ef5d9bfe3f45c0a38b58918437213b506d877b0f4d9f43c3da
-size 3899899728
diff --git a/model-00006-of-00011.safetensors b/model-00006-of-00011.safetensors
deleted file mode 100644
index 275d91b..0000000
--- a/model-00006-of-00011.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b64238049fe13ce2925e5a74227919b1872814658d957ea6627ce2f5a64cc0f5
-size 3978401520
diff --git a/model-00007-of-00011.safetensors b/model-00007-of-00011.safetensors
deleted file mode 100644
index 74444f7..0000000
--- a/model-00007-of-00011.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7aeae23b07b2bc8cd9b36382d2ef06ead4a5ef44d812ac93dc248cbce38fe7e1
-size 3978401520
diff --git a/model-00008-of-00011.safetensors b/model-00008-of-00011.safetensors
deleted file mode 100644
index ac0fe52..0000000
--- a/model-00008-of-00011.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f72800b8363763a4a6edf81fe1561364cd66de91c55d208bcb28ea307d56e367
-size 3899899728
diff --git a/model-00009-of-00011.safetensors b/model-00009-of-00011.safetensors
deleted file mode 100644
index aaea0df..0000000
--- a/model-00009-of-00011.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c0caf1e0b1f3cd377279b0a81bd2fda0d63d844e8cc759bc7afa12428b8c6a0b
-size 3978401520
diff --git a/model-00010-of-00011.safetensors b/model-00010-of-00011.safetensors
deleted file mode 100644
index a42f7e1..0000000
--- a/model-00010-of-00011.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:54e8c3507bc1740d2c78e5ecad102de4ae097463e144903ba512b475028b5068
-size 3978401520
diff --git a/model-00011-of-00011.safetensors b/model-00011-of-00011.safetensors
deleted file mode 100644
index 05963cd..0000000
--- a/model-00011-of-00011.safetensors
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:83da05e1e8126c3fde80fe8857b52933d82d73352946abd9241f8b909b08bb1c
-size 3325018416
diff --git a/model.safetensors.index.json b/model.safetensors.index.json
index 7120fe6..5abd428 100644
--- a/model.safetensors.index.json
+++ b/model.safetensors.index.json
@@ -1,2480 +1,1128 @@
 {
   "metadata": {
-    "total_size": 42873922048
+    "total_size": 6923847680
   },
   "weight_map": {
-    "visual.patch_embed.proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.0.norm1.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.0.norm2.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.0.attn.qkv.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.0.attn.qkv.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.0.attn.proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.0.attn.proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.1.norm1.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.1.norm2.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.1.attn.qkv.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.1.attn.qkv.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.1.attn.proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.1.attn.proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.2.norm1.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.2.norm2.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.2.attn.qkv.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.2.attn.qkv.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.2.attn.proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.2.attn.proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.3.norm1.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.3.norm2.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.3.attn.qkv.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.3.attn.qkv.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.3.attn.proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.3.attn.proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.4.norm1.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.4.norm2.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.4.attn.qkv.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.4.attn.qkv.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.4.attn.proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.4.attn.proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.5.norm1.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.5.norm2.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.5.attn.qkv.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.5.attn.qkv.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.5.attn.proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.5.attn.proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.6.norm1.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.6.norm2.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.6.attn.qkv.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.6.attn.qkv.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.6.attn.proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.6.attn.proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.7.norm1.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.7.norm2.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.7.attn.qkv.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.7.attn.qkv.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.7.attn.proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.7.attn.proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.8.norm1.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.8.norm2.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.8.attn.qkv.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.8.attn.qkv.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.8.attn.proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.8.attn.proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.9.norm1.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.9.norm2.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.9.attn.qkv.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.9.attn.qkv.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.9.attn.proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.9.attn.proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.10.norm1.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.10.norm2.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.10.attn.qkv.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.10.attn.qkv.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.10.attn.proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.10.attn.proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.11.norm1.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.11.norm2.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.11.attn.qkv.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.11.attn.qkv.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.11.attn.proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.11.attn.proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.12.norm1.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.12.norm2.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.12.attn.qkv.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.12.attn.qkv.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.12.attn.proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.12.attn.proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.13.norm1.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.13.norm2.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.13.attn.qkv.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.13.attn.qkv.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.13.attn.proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.13.attn.proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.14.norm1.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.14.norm2.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.14.attn.qkv.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.14.attn.qkv.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.14.attn.proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.14.attn.proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.15.norm1.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.15.norm2.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.15.attn.qkv.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.15.attn.qkv.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.15.attn.proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.15.attn.proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.16.norm1.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.16.norm2.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.16.attn.qkv.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.16.attn.qkv.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.16.attn.proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.16.attn.proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.17.norm1.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.17.norm2.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.17.attn.qkv.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.17.attn.qkv.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.17.attn.proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.17.attn.proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.18.norm1.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.18.norm2.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.18.attn.qkv.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.18.attn.qkv.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.18.attn.proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.18.attn.proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.19.norm1.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.19.norm2.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.19.attn.qkv.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.19.attn.qkv.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.19.attn.proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.19.attn.proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.20.norm1.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.20.norm2.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.20.attn.qkv.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.20.attn.qkv.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.20.attn.proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.20.attn.proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.21.norm1.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.21.norm2.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.21.attn.qkv.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.21.attn.qkv.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.21.attn.proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.21.attn.proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.22.norm1.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.22.norm2.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.22.attn.qkv.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.22.attn.qkv.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.22.attn.proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.22.attn.proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.23.norm1.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.23.norm2.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.23.attn.qkv.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.23.attn.qkv.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.23.attn.proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.23.attn.proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.24.norm1.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.24.norm2.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.24.attn.qkv.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.24.attn.qkv.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.24.attn.proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.24.attn.proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.25.norm1.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.25.norm2.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.25.attn.qkv.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.25.attn.qkv.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.25.attn.proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.25.attn.proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.26.norm1.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.26.norm2.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.26.attn.qkv.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.26.attn.qkv.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.26.attn.proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.26.attn.proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.27.norm1.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.27.norm2.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.27.attn.qkv.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.27.attn.qkv.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.27.attn.proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.27.attn.proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.28.norm1.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.28.norm2.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.28.attn.qkv.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.28.attn.qkv.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.28.attn.proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.28.attn.proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.29.norm1.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.29.norm2.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.29.attn.qkv.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.29.attn.qkv.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.29.attn.proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.29.attn.proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.30.norm1.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.30.norm2.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.30.attn.qkv.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.30.attn.qkv.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.30.attn.proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.30.attn.proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.31.norm1.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.31.norm2.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.31.attn.qkv.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.31.attn.qkv.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.31.attn.proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.31.attn.proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
-    "visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00011.safetensors",
-    "visual.merger.ln_q.weight": "model-00001-of-00011.safetensors",
-    "visual.merger.mlp.0.weight": "model-00001-of-00011.safetensors",
-    "visual.merger.mlp.0.bias": "model-00001-of-00011.safetensors",
-    "visual.merger.mlp.2.weight": "model-00001-of-00011.safetensors",
-    "visual.merger.mlp.2.bias": "model-00001-of-00011.safetensors",
-    "model.embed_tokens.weight": "model-00001-of-00011.safetensors",
-    "model.layers.0.self_attn.q_proj.qweight": "model-00001-of-00011.safetensors",
-    "model.layers.0.self_attn.q_proj.qzeros": "model-00001-of-00011.safetensors",
-    "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00011.safetensors",
-    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
-    "model.layers.0.self_attn.k_proj.qweight": "model-00001-of-00011.safetensors",
-    "model.layers.0.self_attn.k_proj.qzeros": "model-00001-of-00011.safetensors",
-    "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00011.safetensors",
-    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00011.safetensors",
-    "model.layers.0.self_attn.v_proj.qweight": "model-00001-of-00011.safetensors",
-    "model.layers.0.self_attn.v_proj.qzeros": "model-00001-of-00011.safetensors",
-    "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00011.safetensors",
-    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
-    "model.layers.0.self_attn.o_proj.qweight": "model-00001-of-00011.safetensors",
-    "model.layers.0.self_attn.o_proj.qzeros": "model-00001-of-00011.safetensors",
-    "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00011.safetensors",
-    "model.layers.0.mlp.gate_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.0.mlp.gate_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.0.mlp.gate_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.0.mlp.up_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.0.mlp.up_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.0.mlp.up_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.0.mlp.down_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.0.mlp.down_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.0.mlp.down_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00002-of-00011.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
-    "model.layers.1.self_attn.q_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.1.self_attn.q_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.1.self_attn.q_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.1.self_attn.q_proj.bias": "model-00002-of-00011.safetensors",
-    "model.layers.1.self_attn.k_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.1.self_attn.k_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.1.self_attn.k_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.1.self_attn.k_proj.bias": "model-00002-of-00011.safetensors",
-    "model.layers.1.self_attn.v_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.1.self_attn.v_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.1.self_attn.v_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.1.self_attn.v_proj.bias": "model-00002-of-00011.safetensors",
-    "model.layers.1.self_attn.o_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.1.self_attn.o_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.1.self_attn.o_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.1.mlp.gate_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.1.mlp.gate_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.1.mlp.gate_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.1.mlp.up_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.1.mlp.up_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.1.mlp.up_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.1.mlp.down_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.1.mlp.down_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.1.mlp.down_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00002-of-00011.safetensors",
-    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
-    "model.layers.2.self_attn.q_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.2.self_attn.q_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.2.self_attn.q_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.2.self_attn.q_proj.bias": "model-00002-of-00011.safetensors",
-    "model.layers.2.self_attn.k_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.2.self_attn.k_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.2.self_attn.k_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.2.self_attn.k_proj.bias": "model-00002-of-00011.safetensors",
-    "model.layers.2.self_attn.v_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.2.self_attn.v_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.2.self_attn.v_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.2.self_attn.v_proj.bias": "model-00002-of-00011.safetensors",
-    "model.layers.2.self_attn.o_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.2.self_attn.o_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.2.self_attn.o_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.2.mlp.gate_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.2.mlp.gate_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.2.mlp.gate_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.2.mlp.up_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.2.mlp.up_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.2.mlp.up_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.2.mlp.down_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.2.mlp.down_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.2.mlp.down_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00002-of-00011.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
-    "model.layers.3.self_attn.q_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.3.self_attn.q_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.3.self_attn.q_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00011.safetensors",
-    "model.layers.3.self_attn.k_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.3.self_attn.k_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.3.self_attn.k_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00011.safetensors",
-    "model.layers.3.self_attn.v_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.3.self_attn.v_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.3.self_attn.v_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00011.safetensors",
-    "model.layers.3.self_attn.o_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.3.self_attn.o_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.3.self_attn.o_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.3.mlp.gate_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.3.mlp.gate_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.3.mlp.gate_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.3.mlp.up_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.3.mlp.up_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.3.mlp.up_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.3.mlp.down_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.3.mlp.down_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.3.mlp.down_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00002-of-00011.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
-    "model.layers.4.self_attn.q_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.4.self_attn.q_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.4.self_attn.q_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00011.safetensors",
-    "model.layers.4.self_attn.k_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.4.self_attn.k_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.4.self_attn.k_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00011.safetensors",
-    "model.layers.4.self_attn.v_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.4.self_attn.v_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.4.self_attn.v_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00011.safetensors",
-    "model.layers.4.self_attn.o_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.4.self_attn.o_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.4.self_attn.o_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.4.mlp.gate_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.4.mlp.gate_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.4.mlp.gate_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.4.mlp.up_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.4.mlp.up_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.4.mlp.up_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.4.mlp.down_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.4.mlp.down_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.4.mlp.down_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00002-of-00011.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
-    "model.layers.5.self_attn.q_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.5.self_attn.q_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.5.self_attn.q_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00011.safetensors",
-    "model.layers.5.self_attn.k_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.5.self_attn.k_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.5.self_attn.k_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00011.safetensors",
-    "model.layers.5.self_attn.v_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.5.self_attn.v_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.5.self_attn.v_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00011.safetensors",
-    "model.layers.5.self_attn.o_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.5.self_attn.o_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.5.self_attn.o_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.5.mlp.gate_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.5.mlp.gate_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.5.mlp.gate_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.5.mlp.up_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.5.mlp.up_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.5.mlp.up_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.5.mlp.down_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.5.mlp.down_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.5.mlp.down_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00002-of-00011.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
-    "model.layers.6.self_attn.q_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.6.self_attn.q_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.6.self_attn.q_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00011.safetensors",
-    "model.layers.6.self_attn.k_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.6.self_attn.k_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.6.self_attn.k_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00011.safetensors",
-    "model.layers.6.self_attn.v_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.6.self_attn.v_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.6.self_attn.v_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00011.safetensors",
-    "model.layers.6.self_attn.o_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.6.self_attn.o_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.6.self_attn.o_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.6.mlp.gate_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.6.mlp.gate_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.6.mlp.gate_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.6.mlp.up_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.6.mlp.up_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.6.mlp.up_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.6.mlp.down_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.6.mlp.down_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.6.mlp.down_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00002-of-00011.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
-    "model.layers.7.self_attn.q_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.7.self_attn.q_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.7.self_attn.q_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00011.safetensors",
-    "model.layers.7.self_attn.k_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.7.self_attn.k_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.7.self_attn.k_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00011.safetensors",
-    "model.layers.7.self_attn.v_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.7.self_attn.v_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.7.self_attn.v_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00011.safetensors",
-    "model.layers.7.self_attn.o_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.7.self_attn.o_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.7.self_attn.o_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.7.mlp.gate_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.7.mlp.gate_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.7.mlp.gate_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.7.mlp.up_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.7.mlp.up_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.7.mlp.up_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.7.mlp.down_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.7.mlp.down_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.7.mlp.down_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00002-of-00011.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
-    "model.layers.8.self_attn.q_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.8.self_attn.q_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.8.self_attn.q_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00011.safetensors",
-    "model.layers.8.self_attn.k_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.8.self_attn.k_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.8.self_attn.k_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00011.safetensors",
-    "model.layers.8.self_attn.v_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.8.self_attn.v_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.8.self_attn.v_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00011.safetensors",
-    "model.layers.8.self_attn.o_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.8.self_attn.o_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.8.self_attn.o_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.8.mlp.gate_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.8.mlp.gate_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.8.mlp.gate_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.8.mlp.up_proj.qweight": "model-00002-of-00011.safetensors",
-    "model.layers.8.mlp.up_proj.qzeros": "model-00002-of-00011.safetensors",
-    "model.layers.8.mlp.up_proj.scales": "model-00002-of-00011.safetensors",
-    "model.layers.8.mlp.down_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.8.mlp.down_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.8.mlp.down_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00003-of-00011.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
-    "model.layers.9.self_attn.q_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.9.self_attn.q_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.9.self_attn.q_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00011.safetensors",
-    "model.layers.9.self_attn.k_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.9.self_attn.k_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.9.self_attn.k_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00011.safetensors",
-    "model.layers.9.self_attn.v_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.9.self_attn.v_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.9.self_attn.v_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00011.safetensors",
-    "model.layers.9.self_attn.o_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.9.self_attn.o_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.9.self_attn.o_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.9.mlp.gate_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.9.mlp.gate_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.9.mlp.gate_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.9.mlp.up_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.9.mlp.up_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.9.mlp.up_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.9.mlp.down_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.9.mlp.down_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.9.mlp.down_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00003-of-00011.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
-    "model.layers.10.self_attn.q_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.10.self_attn.q_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.10.self_attn.q_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00011.safetensors",
-    "model.layers.10.self_attn.k_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.10.self_attn.k_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.10.self_attn.k_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00011.safetensors",
-    "model.layers.10.self_attn.v_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.10.self_attn.v_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.10.self_attn.v_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00011.safetensors",
-    "model.layers.10.self_attn.o_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.10.self_attn.o_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.10.self_attn.o_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.10.mlp.gate_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.10.mlp.gate_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.10.mlp.gate_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.10.mlp.up_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.10.mlp.up_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.10.mlp.up_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.10.mlp.down_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.10.mlp.down_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.10.mlp.down_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00003-of-00011.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
-    "model.layers.11.self_attn.q_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.11.self_attn.q_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.11.self_attn.q_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00011.safetensors",
-    "model.layers.11.self_attn.k_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.11.self_attn.k_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.11.self_attn.k_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00011.safetensors",
-    "model.layers.11.self_attn.v_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.11.self_attn.v_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.11.self_attn.v_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00011.safetensors",
-    "model.layers.11.self_attn.o_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.11.self_attn.o_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.11.self_attn.o_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.11.mlp.gate_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.11.mlp.gate_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.11.mlp.gate_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.11.mlp.up_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.11.mlp.up_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.11.mlp.up_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.11.mlp.down_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.11.mlp.down_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.11.mlp.down_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00003-of-00011.safetensors",
-    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
-    "model.layers.12.self_attn.q_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.12.self_attn.q_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.12.self_attn.q_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00011.safetensors",
-    "model.layers.12.self_attn.k_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.12.self_attn.k_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.12.self_attn.k_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00011.safetensors",
-    "model.layers.12.self_attn.v_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.12.self_attn.v_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.12.self_attn.v_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00011.safetensors",
-    "model.layers.12.self_attn.o_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.12.self_attn.o_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.12.self_attn.o_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.12.mlp.gate_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.12.mlp.gate_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.12.mlp.gate_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.12.mlp.up_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.12.mlp.up_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.12.mlp.up_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.12.mlp.down_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.12.mlp.down_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.12.mlp.down_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00003-of-00011.safetensors",
-    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
-    "model.layers.13.self_attn.q_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.13.self_attn.q_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.13.self_attn.q_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00011.safetensors",
-    "model.layers.13.self_attn.k_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.13.self_attn.k_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.13.self_attn.k_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00011.safetensors",
-    "model.layers.13.self_attn.v_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.13.self_attn.v_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.13.self_attn.v_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00011.safetensors",
-    "model.layers.13.self_attn.o_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.13.self_attn.o_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.13.self_attn.o_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.13.mlp.gate_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.13.mlp.gate_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.13.mlp.gate_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.13.mlp.up_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.13.mlp.up_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.13.mlp.up_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.13.mlp.down_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.13.mlp.down_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.13.mlp.down_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00003-of-00011.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
-    "model.layers.14.self_attn.q_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.14.self_attn.q_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.14.self_attn.q_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.14.self_attn.q_proj.bias": "model-00003-of-00011.safetensors",
-    "model.layers.14.self_attn.k_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.14.self_attn.k_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.14.self_attn.k_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.14.self_attn.k_proj.bias": "model-00003-of-00011.safetensors",
-    "model.layers.14.self_attn.v_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.14.self_attn.v_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.14.self_attn.v_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.14.self_attn.v_proj.bias": "model-00003-of-00011.safetensors",
-    "model.layers.14.self_attn.o_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.14.self_attn.o_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.14.self_attn.o_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.14.mlp.gate_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.14.mlp.gate_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.14.mlp.gate_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.14.mlp.up_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.14.mlp.up_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.14.mlp.up_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.14.mlp.down_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.14.mlp.down_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.14.mlp.down_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00003-of-00011.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
-    "model.layers.15.self_attn.q_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.15.self_attn.q_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.15.self_attn.q_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.15.self_attn.q_proj.bias": "model-00003-of-00011.safetensors",
-    "model.layers.15.self_attn.k_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.15.self_attn.k_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.15.self_attn.k_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.15.self_attn.k_proj.bias": "model-00003-of-00011.safetensors",
-    "model.layers.15.self_attn.v_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.15.self_attn.v_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.15.self_attn.v_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.15.self_attn.v_proj.bias": "model-00003-of-00011.safetensors",
-    "model.layers.15.self_attn.o_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.15.self_attn.o_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.15.self_attn.o_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.15.mlp.gate_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.15.mlp.gate_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.15.mlp.gate_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.15.mlp.up_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.15.mlp.up_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.15.mlp.up_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.15.mlp.down_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.15.mlp.down_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.15.mlp.down_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00003-of-00011.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
-    "model.layers.16.self_attn.q_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.16.self_attn.q_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.16.self_attn.q_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.16.self_attn.q_proj.bias": "model-00003-of-00011.safetensors",
-    "model.layers.16.self_attn.k_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.16.self_attn.k_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.16.self_attn.k_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.16.self_attn.k_proj.bias": "model-00003-of-00011.safetensors",
-    "model.layers.16.self_attn.v_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.16.self_attn.v_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.16.self_attn.v_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.16.self_attn.v_proj.bias": "model-00003-of-00011.safetensors",
-    "model.layers.16.self_attn.o_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.16.self_attn.o_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.16.self_attn.o_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.16.mlp.gate_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.16.mlp.gate_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.16.mlp.gate_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.16.mlp.up_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.16.mlp.up_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.16.mlp.up_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.16.mlp.down_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.16.mlp.down_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.16.mlp.down_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00003-of-00011.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
-    "model.layers.17.self_attn.q_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.17.self_attn.q_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.17.self_attn.q_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00011.safetensors",
-    "model.layers.17.self_attn.k_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.17.self_attn.k_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.17.self_attn.k_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00011.safetensors",
-    "model.layers.17.self_attn.v_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.17.self_attn.v_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.17.self_attn.v_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00011.safetensors",
-    "model.layers.17.self_attn.o_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.17.self_attn.o_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.17.self_attn.o_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.17.mlp.gate_proj.qweight": "model-00003-of-00011.safetensors",
-    "model.layers.17.mlp.gate_proj.qzeros": "model-00003-of-00011.safetensors",
-    "model.layers.17.mlp.gate_proj.scales": "model-00003-of-00011.safetensors",
-    "model.layers.17.mlp.up_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.17.mlp.up_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.17.mlp.up_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.17.mlp.down_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.17.mlp.down_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.17.mlp.down_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00004-of-00011.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
-    "model.layers.18.self_attn.q_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.18.self_attn.q_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.18.self_attn.q_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00011.safetensors",
-    "model.layers.18.self_attn.k_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.18.self_attn.k_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.18.self_attn.k_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00011.safetensors",
-    "model.layers.18.self_attn.v_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.18.self_attn.v_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.18.self_attn.v_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00011.safetensors",
-    "model.layers.18.self_attn.o_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.18.self_attn.o_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.18.self_attn.o_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.18.mlp.gate_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.18.mlp.gate_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.18.mlp.gate_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.18.mlp.up_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.18.mlp.up_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.18.mlp.up_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.18.mlp.down_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.18.mlp.down_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.18.mlp.down_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00004-of-00011.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
-    "model.layers.19.self_attn.q_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.19.self_attn.q_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.19.self_attn.q_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.19.self_attn.q_proj.bias": "model-00004-of-00011.safetensors",
-    "model.layers.19.self_attn.k_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.19.self_attn.k_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.19.self_attn.k_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.19.self_attn.k_proj.bias": "model-00004-of-00011.safetensors",
-    "model.layers.19.self_attn.v_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.19.self_attn.v_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.19.self_attn.v_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.19.self_attn.v_proj.bias": "model-00004-of-00011.safetensors",
-    "model.layers.19.self_attn.o_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.19.self_attn.o_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.19.self_attn.o_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.19.mlp.gate_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.19.mlp.gate_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.19.mlp.gate_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.19.mlp.up_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.19.mlp.up_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.19.mlp.up_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.19.mlp.down_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.19.mlp.down_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.19.mlp.down_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00004-of-00011.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
-    "model.layers.20.self_attn.q_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.20.self_attn.q_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.20.self_attn.q_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.20.self_attn.q_proj.bias": "model-00004-of-00011.safetensors",
-    "model.layers.20.self_attn.k_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.20.self_attn.k_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.20.self_attn.k_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.20.self_attn.k_proj.bias": "model-00004-of-00011.safetensors",
-    "model.layers.20.self_attn.v_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.20.self_attn.v_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.20.self_attn.v_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.20.self_attn.v_proj.bias": "model-00004-of-00011.safetensors",
-    "model.layers.20.self_attn.o_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.20.self_attn.o_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.20.self_attn.o_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.20.mlp.gate_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.20.mlp.gate_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.20.mlp.gate_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.20.mlp.up_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.20.mlp.up_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.20.mlp.up_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.20.mlp.down_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.20.mlp.down_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.20.mlp.down_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00004-of-00011.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
-    "model.layers.21.self_attn.q_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.21.self_attn.q_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.21.self_attn.q_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.21.self_attn.q_proj.bias": "model-00004-of-00011.safetensors",
-    "model.layers.21.self_attn.k_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.21.self_attn.k_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.21.self_attn.k_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.21.self_attn.k_proj.bias": "model-00004-of-00011.safetensors",
-    "model.layers.21.self_attn.v_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.21.self_attn.v_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.21.self_attn.v_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.21.self_attn.v_proj.bias": "model-00004-of-00011.safetensors",
-    "model.layers.21.self_attn.o_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.21.self_attn.o_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.21.self_attn.o_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.21.mlp.gate_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.21.mlp.gate_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.21.mlp.gate_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.21.mlp.up_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.21.mlp.up_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.21.mlp.up_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.21.mlp.down_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.21.mlp.down_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.21.mlp.down_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00004-of-00011.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
-    "model.layers.22.self_attn.q_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.22.self_attn.q_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.22.self_attn.q_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.22.self_attn.q_proj.bias": "model-00004-of-00011.safetensors",
-    "model.layers.22.self_attn.k_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.22.self_attn.k_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.22.self_attn.k_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.22.self_attn.k_proj.bias": "model-00004-of-00011.safetensors",
-    "model.layers.22.self_attn.v_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.22.self_attn.v_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.22.self_attn.v_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.22.self_attn.v_proj.bias": "model-00004-of-00011.safetensors",
-    "model.layers.22.self_attn.o_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.22.self_attn.o_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.22.self_attn.o_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.22.mlp.gate_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.22.mlp.gate_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.22.mlp.gate_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.22.mlp.up_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.22.mlp.up_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.22.mlp.up_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.22.mlp.down_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.22.mlp.down_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.22.mlp.down_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00004-of-00011.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
-    "model.layers.23.self_attn.q_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.23.self_attn.q_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.23.self_attn.q_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.23.self_attn.q_proj.bias": "model-00004-of-00011.safetensors",
-    "model.layers.23.self_attn.k_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.23.self_attn.k_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.23.self_attn.k_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.23.self_attn.k_proj.bias": "model-00004-of-00011.safetensors",
-    "model.layers.23.self_attn.v_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.23.self_attn.v_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.23.self_attn.v_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.23.self_attn.v_proj.bias": "model-00004-of-00011.safetensors",
-    "model.layers.23.self_attn.o_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.23.self_attn.o_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.23.self_attn.o_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.23.mlp.gate_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.23.mlp.gate_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.23.mlp.gate_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.23.mlp.up_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.23.mlp.up_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.23.mlp.up_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.23.mlp.down_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.23.mlp.down_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.23.mlp.down_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00004-of-00011.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
-    "model.layers.24.self_attn.q_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.24.self_attn.q_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.24.self_attn.q_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.24.self_attn.q_proj.bias": "model-00004-of-00011.safetensors",
-    "model.layers.24.self_attn.k_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.24.self_attn.k_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.24.self_attn.k_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.24.self_attn.k_proj.bias": "model-00004-of-00011.safetensors",
-    "model.layers.24.self_attn.v_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.24.self_attn.v_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.24.self_attn.v_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.24.self_attn.v_proj.bias": "model-00004-of-00011.safetensors",
-    "model.layers.24.self_attn.o_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.24.self_attn.o_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.24.self_attn.o_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.24.mlp.gate_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.24.mlp.gate_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.24.mlp.gate_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.24.mlp.up_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.24.mlp.up_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.24.mlp.up_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.24.mlp.down_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.24.mlp.down_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.24.mlp.down_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00004-of-00011.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
-    "model.layers.25.self_attn.q_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.25.self_attn.q_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.25.self_attn.q_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.25.self_attn.q_proj.bias": "model-00004-of-00011.safetensors",
-    "model.layers.25.self_attn.k_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.25.self_attn.k_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.25.self_attn.k_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.25.self_attn.k_proj.bias": "model-00004-of-00011.safetensors",
-    "model.layers.25.self_attn.v_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.25.self_attn.v_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.25.self_attn.v_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.25.self_attn.v_proj.bias": "model-00004-of-00011.safetensors",
-    "model.layers.25.self_attn.o_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.25.self_attn.o_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.25.self_attn.o_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.25.mlp.gate_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.25.mlp.gate_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.25.mlp.gate_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.25.mlp.up_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.25.mlp.up_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.25.mlp.up_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.25.mlp.down_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.25.mlp.down_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.25.mlp.down_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00004-of-00011.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
-    "model.layers.26.self_attn.q_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.26.self_attn.q_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.26.self_attn.q_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.26.self_attn.q_proj.bias": "model-00004-of-00011.safetensors",
-    "model.layers.26.self_attn.k_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.26.self_attn.k_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.26.self_attn.k_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.26.self_attn.k_proj.bias": "model-00004-of-00011.safetensors",
-    "model.layers.26.self_attn.v_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.26.self_attn.v_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.26.self_attn.v_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.26.self_attn.v_proj.bias": "model-00004-of-00011.safetensors",
-    "model.layers.26.self_attn.o_proj.qweight": "model-00004-of-00011.safetensors",
-    "model.layers.26.self_attn.o_proj.qzeros": "model-00004-of-00011.safetensors",
-    "model.layers.26.self_attn.o_proj.scales": "model-00004-of-00011.safetensors",
-    "model.layers.26.mlp.gate_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.26.mlp.gate_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.26.mlp.gate_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.26.mlp.up_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.26.mlp.up_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.26.mlp.up_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.26.mlp.down_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.26.mlp.down_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.26.mlp.down_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00005-of-00011.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
-    "model.layers.27.self_attn.q_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.27.self_attn.q_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.27.self_attn.q_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.27.self_attn.q_proj.bias": "model-00005-of-00011.safetensors",
-    "model.layers.27.self_attn.k_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.27.self_attn.k_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.27.self_attn.k_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.27.self_attn.k_proj.bias": "model-00005-of-00011.safetensors",
-    "model.layers.27.self_attn.v_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.27.self_attn.v_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.27.self_attn.v_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.27.self_attn.v_proj.bias": "model-00005-of-00011.safetensors",
-    "model.layers.27.self_attn.o_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.27.self_attn.o_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.27.self_attn.o_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.27.mlp.gate_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.27.mlp.gate_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.27.mlp.gate_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.27.mlp.up_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.27.mlp.up_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.27.mlp.up_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.27.mlp.down_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.27.mlp.down_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.27.mlp.down_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00005-of-00011.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
-    "model.layers.28.self_attn.q_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.28.self_attn.q_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.28.self_attn.q_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.28.self_attn.q_proj.bias": "model-00005-of-00011.safetensors",
-    "model.layers.28.self_attn.k_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.28.self_attn.k_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.28.self_attn.k_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.28.self_attn.k_proj.bias": "model-00005-of-00011.safetensors",
-    "model.layers.28.self_attn.v_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.28.self_attn.v_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.28.self_attn.v_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.28.self_attn.v_proj.bias": "model-00005-of-00011.safetensors",
-    "model.layers.28.self_attn.o_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.28.self_attn.o_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.28.self_attn.o_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.28.mlp.gate_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.28.mlp.gate_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.28.mlp.gate_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.28.mlp.up_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.28.mlp.up_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.28.mlp.up_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.28.mlp.down_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.28.mlp.down_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.28.mlp.down_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.28.input_layernorm.weight": "model-00005-of-00011.safetensors",
-    "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
-    "model.layers.29.self_attn.q_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.29.self_attn.q_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.29.self_attn.q_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.29.self_attn.q_proj.bias": "model-00005-of-00011.safetensors",
-    "model.layers.29.self_attn.k_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.29.self_attn.k_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.29.self_attn.k_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.29.self_attn.k_proj.bias": "model-00005-of-00011.safetensors",
-    "model.layers.29.self_attn.v_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.29.self_attn.v_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.29.self_attn.v_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.29.self_attn.v_proj.bias": "model-00005-of-00011.safetensors",
-    "model.layers.29.self_attn.o_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.29.self_attn.o_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.29.self_attn.o_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.29.mlp.gate_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.29.mlp.gate_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.29.mlp.gate_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.29.mlp.up_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.29.mlp.up_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.29.mlp.up_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.29.mlp.down_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.29.mlp.down_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.29.mlp.down_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.29.input_layernorm.weight": "model-00005-of-00011.safetensors",
-    "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
-    "model.layers.30.self_attn.q_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.30.self_attn.q_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.30.self_attn.q_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.30.self_attn.q_proj.bias": "model-00005-of-00011.safetensors",
-    "model.layers.30.self_attn.k_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.30.self_attn.k_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.30.self_attn.k_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.30.self_attn.k_proj.bias": "model-00005-of-00011.safetensors",
-    "model.layers.30.self_attn.v_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.30.self_attn.v_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.30.self_attn.v_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.30.self_attn.v_proj.bias": "model-00005-of-00011.safetensors",
-    "model.layers.30.self_attn.o_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.30.self_attn.o_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.30.self_attn.o_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.30.mlp.gate_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.30.mlp.gate_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.30.mlp.gate_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.30.mlp.up_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.30.mlp.up_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.30.mlp.up_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.30.mlp.down_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.30.mlp.down_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.30.mlp.down_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.30.input_layernorm.weight": "model-00005-of-00011.safetensors",
-    "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
-    "model.layers.31.self_attn.q_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.31.self_attn.q_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.31.self_attn.q_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.31.self_attn.q_proj.bias": "model-00005-of-00011.safetensors",
-    "model.layers.31.self_attn.k_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.31.self_attn.k_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.31.self_attn.k_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.31.self_attn.k_proj.bias": "model-00005-of-00011.safetensors",
-    "model.layers.31.self_attn.v_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.31.self_attn.v_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.31.self_attn.v_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.31.self_attn.v_proj.bias": "model-00005-of-00011.safetensors",
-    "model.layers.31.self_attn.o_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.31.self_attn.o_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.31.self_attn.o_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.31.mlp.gate_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.31.mlp.gate_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.31.mlp.gate_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.31.mlp.up_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.31.mlp.up_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.31.mlp.up_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.31.mlp.down_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.31.mlp.down_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.31.mlp.down_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.31.input_layernorm.weight": "model-00005-of-00011.safetensors",
-    "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
-    "model.layers.32.self_attn.q_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.32.self_attn.q_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.32.self_attn.q_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.32.self_attn.q_proj.bias": "model-00005-of-00011.safetensors",
-    "model.layers.32.self_attn.k_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.32.self_attn.k_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.32.self_attn.k_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.32.self_attn.k_proj.bias": "model-00005-of-00011.safetensors",
-    "model.layers.32.self_attn.v_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.32.self_attn.v_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.32.self_attn.v_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.32.self_attn.v_proj.bias": "model-00005-of-00011.safetensors",
-    "model.layers.32.self_attn.o_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.32.self_attn.o_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.32.self_attn.o_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.32.mlp.gate_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.32.mlp.gate_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.32.mlp.gate_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.32.mlp.up_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.32.mlp.up_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.32.mlp.up_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.32.mlp.down_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.32.mlp.down_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.32.mlp.down_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.32.input_layernorm.weight": "model-00005-of-00011.safetensors",
-    "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
-    "model.layers.33.self_attn.q_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.33.self_attn.q_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.33.self_attn.q_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.33.self_attn.q_proj.bias": "model-00005-of-00011.safetensors",
-    "model.layers.33.self_attn.k_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.33.self_attn.k_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.33.self_attn.k_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.33.self_attn.k_proj.bias": "model-00005-of-00011.safetensors",
-    "model.layers.33.self_attn.v_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.33.self_attn.v_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.33.self_attn.v_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.33.self_attn.v_proj.bias": "model-00005-of-00011.safetensors",
-    "model.layers.33.self_attn.o_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.33.self_attn.o_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.33.self_attn.o_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.33.mlp.gate_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.33.mlp.gate_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.33.mlp.gate_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.33.mlp.up_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.33.mlp.up_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.33.mlp.up_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.33.mlp.down_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.33.mlp.down_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.33.mlp.down_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.33.input_layernorm.weight": "model-00005-of-00011.safetensors",
-    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
-    "model.layers.34.self_attn.q_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.34.self_attn.q_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.34.self_attn.q_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.34.self_attn.q_proj.bias": "model-00005-of-00011.safetensors",
-    "model.layers.34.self_attn.k_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.34.self_attn.k_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.34.self_attn.k_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.34.self_attn.k_proj.bias": "model-00005-of-00011.safetensors",
-    "model.layers.34.self_attn.v_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.34.self_attn.v_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.34.self_attn.v_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.34.self_attn.v_proj.bias": "model-00005-of-00011.safetensors",
-    "model.layers.34.self_attn.o_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.34.self_attn.o_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.34.self_attn.o_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.34.mlp.gate_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.34.mlp.gate_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.34.mlp.gate_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.34.mlp.up_proj.qweight": "model-00005-of-00011.safetensors",
-    "model.layers.34.mlp.up_proj.qzeros": "model-00005-of-00011.safetensors",
-    "model.layers.34.mlp.up_proj.scales": "model-00005-of-00011.safetensors",
-    "model.layers.34.mlp.down_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.34.mlp.down_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.34.mlp.down_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.34.input_layernorm.weight": "model-00006-of-00011.safetensors",
-    "model.layers.34.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
-    "model.layers.35.self_attn.q_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.35.self_attn.q_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.35.self_attn.q_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.35.self_attn.q_proj.bias": "model-00006-of-00011.safetensors",
-    "model.layers.35.self_attn.k_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.35.self_attn.k_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.35.self_attn.k_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.35.self_attn.k_proj.bias": "model-00006-of-00011.safetensors",
-    "model.layers.35.self_attn.v_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.35.self_attn.v_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.35.self_attn.v_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.35.self_attn.v_proj.bias": "model-00006-of-00011.safetensors",
-    "model.layers.35.self_attn.o_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.35.self_attn.o_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.35.self_attn.o_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.35.mlp.gate_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.35.mlp.gate_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.35.mlp.gate_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.35.mlp.up_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.35.mlp.up_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.35.mlp.up_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.35.mlp.down_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.35.mlp.down_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.35.mlp.down_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.35.input_layernorm.weight": "model-00006-of-00011.safetensors",
-    "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
-    "model.layers.36.self_attn.q_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.36.self_attn.q_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.36.self_attn.q_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.36.self_attn.q_proj.bias": "model-00006-of-00011.safetensors",
-    "model.layers.36.self_attn.k_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.36.self_attn.k_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.36.self_attn.k_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.36.self_attn.k_proj.bias": "model-00006-of-00011.safetensors",
-    "model.layers.36.self_attn.v_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.36.self_attn.v_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.36.self_attn.v_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.36.self_attn.v_proj.bias": "model-00006-of-00011.safetensors",
-    "model.layers.36.self_attn.o_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.36.self_attn.o_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.36.self_attn.o_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.36.mlp.gate_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.36.mlp.gate_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.36.mlp.gate_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.36.mlp.up_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.36.mlp.up_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.36.mlp.up_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.36.mlp.down_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.36.mlp.down_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.36.mlp.down_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.36.input_layernorm.weight": "model-00006-of-00011.safetensors",
-    "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
-    "model.layers.37.self_attn.q_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.37.self_attn.q_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.37.self_attn.q_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.37.self_attn.q_proj.bias": "model-00006-of-00011.safetensors",
-    "model.layers.37.self_attn.k_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.37.self_attn.k_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.37.self_attn.k_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.37.self_attn.k_proj.bias": "model-00006-of-00011.safetensors",
-    "model.layers.37.self_attn.v_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.37.self_attn.v_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.37.self_attn.v_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.37.self_attn.v_proj.bias": "model-00006-of-00011.safetensors",
-    "model.layers.37.self_attn.o_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.37.self_attn.o_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.37.self_attn.o_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.37.mlp.gate_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.37.mlp.gate_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.37.mlp.gate_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.37.mlp.up_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.37.mlp.up_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.37.mlp.up_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.37.mlp.down_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.37.mlp.down_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.37.mlp.down_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.37.input_layernorm.weight": "model-00006-of-00011.safetensors",
-    "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
-    "model.layers.38.self_attn.q_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.38.self_attn.q_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.38.self_attn.q_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.38.self_attn.q_proj.bias": "model-00006-of-00011.safetensors",
-    "model.layers.38.self_attn.k_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.38.self_attn.k_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.38.self_attn.k_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.38.self_attn.k_proj.bias": "model-00006-of-00011.safetensors",
-    "model.layers.38.self_attn.v_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.38.self_attn.v_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.38.self_attn.v_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.38.self_attn.v_proj.bias": "model-00006-of-00011.safetensors",
-    "model.layers.38.self_attn.o_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.38.self_attn.o_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.38.self_attn.o_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.38.mlp.gate_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.38.mlp.gate_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.38.mlp.gate_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.38.mlp.up_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.38.mlp.up_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.38.mlp.up_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.38.mlp.down_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.38.mlp.down_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.38.mlp.down_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.38.input_layernorm.weight": "model-00006-of-00011.safetensors",
-    "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
-    "model.layers.39.self_attn.q_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.39.self_attn.q_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.39.self_attn.q_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.39.self_attn.q_proj.bias": "model-00006-of-00011.safetensors",
-    "model.layers.39.self_attn.k_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.39.self_attn.k_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.39.self_attn.k_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.39.self_attn.k_proj.bias": "model-00006-of-00011.safetensors",
-    "model.layers.39.self_attn.v_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.39.self_attn.v_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.39.self_attn.v_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.39.self_attn.v_proj.bias": "model-00006-of-00011.safetensors",
-    "model.layers.39.self_attn.o_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.39.self_attn.o_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.39.self_attn.o_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.39.mlp.gate_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.39.mlp.gate_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.39.mlp.gate_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.39.mlp.up_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.39.mlp.up_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.39.mlp.up_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.39.mlp.down_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.39.mlp.down_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.39.mlp.down_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.39.input_layernorm.weight": "model-00006-of-00011.safetensors",
-    "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
-    "model.layers.40.self_attn.q_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.40.self_attn.q_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.40.self_attn.q_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.40.self_attn.q_proj.bias": "model-00006-of-00011.safetensors",
-    "model.layers.40.self_attn.k_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.40.self_attn.k_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.40.self_attn.k_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.40.self_attn.k_proj.bias": "model-00006-of-00011.safetensors",
-    "model.layers.40.self_attn.v_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.40.self_attn.v_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.40.self_attn.v_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.40.self_attn.v_proj.bias": "model-00006-of-00011.safetensors",
-    "model.layers.40.self_attn.o_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.40.self_attn.o_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.40.self_attn.o_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.40.mlp.gate_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.40.mlp.gate_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.40.mlp.gate_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.40.mlp.up_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.40.mlp.up_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.40.mlp.up_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.40.mlp.down_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.40.mlp.down_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.40.mlp.down_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.40.input_layernorm.weight": "model-00006-of-00011.safetensors",
-    "model.layers.40.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
-    "model.layers.41.self_attn.q_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.41.self_attn.q_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.41.self_attn.q_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.41.self_attn.q_proj.bias": "model-00006-of-00011.safetensors",
-    "model.layers.41.self_attn.k_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.41.self_attn.k_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.41.self_attn.k_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.41.self_attn.k_proj.bias": "model-00006-of-00011.safetensors",
-    "model.layers.41.self_attn.v_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.41.self_attn.v_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.41.self_attn.v_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.41.self_attn.v_proj.bias": "model-00006-of-00011.safetensors",
-    "model.layers.41.self_attn.o_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.41.self_attn.o_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.41.self_attn.o_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.41.mlp.gate_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.41.mlp.gate_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.41.mlp.gate_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.41.mlp.up_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.41.mlp.up_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.41.mlp.up_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.41.mlp.down_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.41.mlp.down_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.41.mlp.down_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.41.input_layernorm.weight": "model-00006-of-00011.safetensors",
-    "model.layers.41.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
-    "model.layers.42.self_attn.q_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.42.self_attn.q_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.42.self_attn.q_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.42.self_attn.q_proj.bias": "model-00006-of-00011.safetensors",
-    "model.layers.42.self_attn.k_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.42.self_attn.k_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.42.self_attn.k_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.42.self_attn.k_proj.bias": "model-00006-of-00011.safetensors",
-    "model.layers.42.self_attn.v_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.42.self_attn.v_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.42.self_attn.v_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.42.self_attn.v_proj.bias": "model-00006-of-00011.safetensors",
-    "model.layers.42.self_attn.o_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.42.self_attn.o_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.42.self_attn.o_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.42.mlp.gate_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.42.mlp.gate_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.42.mlp.gate_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.42.mlp.up_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.42.mlp.up_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.42.mlp.up_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.42.mlp.down_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.42.mlp.down_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.42.mlp.down_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.42.input_layernorm.weight": "model-00006-of-00011.safetensors",
-    "model.layers.42.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
-    "model.layers.43.self_attn.q_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.43.self_attn.q_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.43.self_attn.q_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.43.self_attn.q_proj.bias": "model-00006-of-00011.safetensors",
-    "model.layers.43.self_attn.k_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.43.self_attn.k_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.43.self_attn.k_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.43.self_attn.k_proj.bias": "model-00006-of-00011.safetensors",
-    "model.layers.43.self_attn.v_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.43.self_attn.v_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.43.self_attn.v_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.43.self_attn.v_proj.bias": "model-00006-of-00011.safetensors",
-    "model.layers.43.self_attn.o_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.43.self_attn.o_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.43.self_attn.o_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.43.mlp.gate_proj.qweight": "model-00006-of-00011.safetensors",
-    "model.layers.43.mlp.gate_proj.qzeros": "model-00006-of-00011.safetensors",
-    "model.layers.43.mlp.gate_proj.scales": "model-00006-of-00011.safetensors",
-    "model.layers.43.mlp.up_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.43.mlp.up_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.43.mlp.up_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.43.mlp.down_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.43.mlp.down_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.43.mlp.down_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.43.input_layernorm.weight": "model-00007-of-00011.safetensors",
-    "model.layers.43.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
-    "model.layers.44.self_attn.q_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.44.self_attn.q_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.44.self_attn.q_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.44.self_attn.q_proj.bias": "model-00007-of-00011.safetensors",
-    "model.layers.44.self_attn.k_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.44.self_attn.k_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.44.self_attn.k_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.44.self_attn.k_proj.bias": "model-00007-of-00011.safetensors",
-    "model.layers.44.self_attn.v_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.44.self_attn.v_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.44.self_attn.v_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.44.self_attn.v_proj.bias": "model-00007-of-00011.safetensors",
-    "model.layers.44.self_attn.o_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.44.self_attn.o_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.44.self_attn.o_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.44.mlp.gate_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.44.mlp.gate_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.44.mlp.gate_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.44.mlp.up_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.44.mlp.up_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.44.mlp.up_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.44.mlp.down_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.44.mlp.down_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.44.mlp.down_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.44.input_layernorm.weight": "model-00007-of-00011.safetensors",
-    "model.layers.44.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
-    "model.layers.45.self_attn.q_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.45.self_attn.q_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.45.self_attn.q_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.45.self_attn.q_proj.bias": "model-00007-of-00011.safetensors",
-    "model.layers.45.self_attn.k_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.45.self_attn.k_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.45.self_attn.k_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.45.self_attn.k_proj.bias": "model-00007-of-00011.safetensors",
-    "model.layers.45.self_attn.v_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.45.self_attn.v_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.45.self_attn.v_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.45.self_attn.v_proj.bias": "model-00007-of-00011.safetensors",
-    "model.layers.45.self_attn.o_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.45.self_attn.o_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.45.self_attn.o_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.45.mlp.gate_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.45.mlp.gate_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.45.mlp.gate_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.45.mlp.up_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.45.mlp.up_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.45.mlp.up_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.45.mlp.down_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.45.mlp.down_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.45.mlp.down_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.45.input_layernorm.weight": "model-00007-of-00011.safetensors",
-    "model.layers.45.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
-    "model.layers.46.self_attn.q_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.46.self_attn.q_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.46.self_attn.q_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.46.self_attn.q_proj.bias": "model-00007-of-00011.safetensors",
-    "model.layers.46.self_attn.k_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.46.self_attn.k_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.46.self_attn.k_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.46.self_attn.k_proj.bias": "model-00007-of-00011.safetensors",
-    "model.layers.46.self_attn.v_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.46.self_attn.v_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.46.self_attn.v_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.46.self_attn.v_proj.bias": "model-00007-of-00011.safetensors",
-    "model.layers.46.self_attn.o_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.46.self_attn.o_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.46.self_attn.o_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.46.mlp.gate_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.46.mlp.gate_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.46.mlp.gate_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.46.mlp.up_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.46.mlp.up_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.46.mlp.up_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.46.mlp.down_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.46.mlp.down_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.46.mlp.down_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.46.input_layernorm.weight": "model-00007-of-00011.safetensors",
-    "model.layers.46.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
-    "model.layers.47.self_attn.q_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.47.self_attn.q_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.47.self_attn.q_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.47.self_attn.q_proj.bias": "model-00007-of-00011.safetensors",
-    "model.layers.47.self_attn.k_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.47.self_attn.k_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.47.self_attn.k_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.47.self_attn.k_proj.bias": "model-00007-of-00011.safetensors",
-    "model.layers.47.self_attn.v_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.47.self_attn.v_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.47.self_attn.v_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.47.self_attn.v_proj.bias": "model-00007-of-00011.safetensors",
-    "model.layers.47.self_attn.o_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.47.self_attn.o_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.47.self_attn.o_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.47.mlp.gate_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.47.mlp.gate_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.47.mlp.gate_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.47.mlp.up_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.47.mlp.up_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.47.mlp.up_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.47.mlp.down_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.47.mlp.down_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.47.mlp.down_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.47.input_layernorm.weight": "model-00007-of-00011.safetensors",
-    "model.layers.47.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
-    "model.layers.48.self_attn.q_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.48.self_attn.q_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.48.self_attn.q_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.48.self_attn.q_proj.bias": "model-00007-of-00011.safetensors",
-    "model.layers.48.self_attn.k_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.48.self_attn.k_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.48.self_attn.k_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.48.self_attn.k_proj.bias": "model-00007-of-00011.safetensors",
-    "model.layers.48.self_attn.v_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.48.self_attn.v_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.48.self_attn.v_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.48.self_attn.v_proj.bias": "model-00007-of-00011.safetensors",
-    "model.layers.48.self_attn.o_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.48.self_attn.o_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.48.self_attn.o_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.48.mlp.gate_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.48.mlp.gate_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.48.mlp.gate_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.48.mlp.up_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.48.mlp.up_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.48.mlp.up_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.48.mlp.down_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.48.mlp.down_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.48.mlp.down_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.48.input_layernorm.weight": "model-00007-of-00011.safetensors",
-    "model.layers.48.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
-    "model.layers.49.self_attn.q_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.49.self_attn.q_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.49.self_attn.q_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.49.self_attn.q_proj.bias": "model-00007-of-00011.safetensors",
-    "model.layers.49.self_attn.k_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.49.self_attn.k_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.49.self_attn.k_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.49.self_attn.k_proj.bias": "model-00007-of-00011.safetensors",
-    "model.layers.49.self_attn.v_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.49.self_attn.v_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.49.self_attn.v_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.49.self_attn.v_proj.bias": "model-00007-of-00011.safetensors",
-    "model.layers.49.self_attn.o_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.49.self_attn.o_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.49.self_attn.o_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.49.mlp.gate_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.49.mlp.gate_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.49.mlp.gate_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.49.mlp.up_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.49.mlp.up_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.49.mlp.up_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.49.mlp.down_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.49.mlp.down_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.49.mlp.down_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.49.input_layernorm.weight": "model-00007-of-00011.safetensors",
-    "model.layers.49.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
-    "model.layers.50.self_attn.q_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.50.self_attn.q_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.50.self_attn.q_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.50.self_attn.q_proj.bias": "model-00007-of-00011.safetensors",
-    "model.layers.50.self_attn.k_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.50.self_attn.k_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.50.self_attn.k_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.50.self_attn.k_proj.bias": "model-00007-of-00011.safetensors",
-    "model.layers.50.self_attn.v_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.50.self_attn.v_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.50.self_attn.v_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.50.self_attn.v_proj.bias": "model-00007-of-00011.safetensors",
-    "model.layers.50.self_attn.o_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.50.self_attn.o_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.50.self_attn.o_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.50.mlp.gate_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.50.mlp.gate_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.50.mlp.gate_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.50.mlp.up_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.50.mlp.up_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.50.mlp.up_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.50.mlp.down_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.50.mlp.down_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.50.mlp.down_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.50.input_layernorm.weight": "model-00007-of-00011.safetensors",
-    "model.layers.50.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
-    "model.layers.51.self_attn.q_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.51.self_attn.q_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.51.self_attn.q_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.51.self_attn.q_proj.bias": "model-00007-of-00011.safetensors",
-    "model.layers.51.self_attn.k_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.51.self_attn.k_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.51.self_attn.k_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.51.self_attn.k_proj.bias": "model-00007-of-00011.safetensors",
-    "model.layers.51.self_attn.v_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.51.self_attn.v_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.51.self_attn.v_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.51.self_attn.v_proj.bias": "model-00007-of-00011.safetensors",
-    "model.layers.51.self_attn.o_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.51.self_attn.o_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.51.self_attn.o_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.51.mlp.gate_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.51.mlp.gate_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.51.mlp.gate_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.51.mlp.up_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.51.mlp.up_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.51.mlp.up_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.51.mlp.down_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.51.mlp.down_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.51.mlp.down_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.51.input_layernorm.weight": "model-00007-of-00011.safetensors",
-    "model.layers.51.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
-    "model.layers.52.self_attn.q_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.52.self_attn.q_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.52.self_attn.q_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.52.self_attn.q_proj.bias": "model-00007-of-00011.safetensors",
-    "model.layers.52.self_attn.k_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.52.self_attn.k_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.52.self_attn.k_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.52.self_attn.k_proj.bias": "model-00007-of-00011.safetensors",
-    "model.layers.52.self_attn.v_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.52.self_attn.v_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.52.self_attn.v_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.52.self_attn.v_proj.bias": "model-00007-of-00011.safetensors",
-    "model.layers.52.self_attn.o_proj.qweight": "model-00007-of-00011.safetensors",
-    "model.layers.52.self_attn.o_proj.qzeros": "model-00007-of-00011.safetensors",
-    "model.layers.52.self_attn.o_proj.scales": "model-00007-of-00011.safetensors",
-    "model.layers.52.mlp.gate_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.52.mlp.gate_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.52.mlp.gate_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.52.mlp.up_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.52.mlp.up_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.52.mlp.up_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.52.mlp.down_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.52.mlp.down_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.52.mlp.down_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.52.input_layernorm.weight": "model-00008-of-00011.safetensors",
-    "model.layers.52.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
-    "model.layers.53.self_attn.q_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.53.self_attn.q_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.53.self_attn.q_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.53.self_attn.q_proj.bias": "model-00008-of-00011.safetensors",
-    "model.layers.53.self_attn.k_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.53.self_attn.k_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.53.self_attn.k_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.53.self_attn.k_proj.bias": "model-00008-of-00011.safetensors",
-    "model.layers.53.self_attn.v_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.53.self_attn.v_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.53.self_attn.v_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.53.self_attn.v_proj.bias": "model-00008-of-00011.safetensors",
-    "model.layers.53.self_attn.o_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.53.self_attn.o_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.53.self_attn.o_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.53.mlp.gate_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.53.mlp.gate_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.53.mlp.gate_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.53.mlp.up_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.53.mlp.up_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.53.mlp.up_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.53.mlp.down_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.53.mlp.down_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.53.mlp.down_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.53.input_layernorm.weight": "model-00008-of-00011.safetensors",
-    "model.layers.53.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
-    "model.layers.54.self_attn.q_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.54.self_attn.q_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.54.self_attn.q_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.54.self_attn.q_proj.bias": "model-00008-of-00011.safetensors",
-    "model.layers.54.self_attn.k_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.54.self_attn.k_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.54.self_attn.k_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.54.self_attn.k_proj.bias": "model-00008-of-00011.safetensors",
-    "model.layers.54.self_attn.v_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.54.self_attn.v_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.54.self_attn.v_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.54.self_attn.v_proj.bias": "model-00008-of-00011.safetensors",
-    "model.layers.54.self_attn.o_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.54.self_attn.o_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.54.self_attn.o_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.54.mlp.gate_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.54.mlp.gate_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.54.mlp.gate_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.54.mlp.up_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.54.mlp.up_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.54.mlp.up_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.54.mlp.down_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.54.mlp.down_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.54.mlp.down_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.54.input_layernorm.weight": "model-00008-of-00011.safetensors",
-    "model.layers.54.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
-    "model.layers.55.self_attn.q_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.55.self_attn.q_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.55.self_attn.q_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.55.self_attn.q_proj.bias": "model-00008-of-00011.safetensors",
-    "model.layers.55.self_attn.k_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.55.self_attn.k_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.55.self_attn.k_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.55.self_attn.k_proj.bias": "model-00008-of-00011.safetensors",
-    "model.layers.55.self_attn.v_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.55.self_attn.v_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.55.self_attn.v_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.55.self_attn.v_proj.bias": "model-00008-of-00011.safetensors",
-    "model.layers.55.self_attn.o_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.55.self_attn.o_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.55.self_attn.o_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.55.mlp.gate_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.55.mlp.gate_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.55.mlp.gate_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.55.mlp.up_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.55.mlp.up_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.55.mlp.up_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.55.mlp.down_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.55.mlp.down_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.55.mlp.down_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.55.input_layernorm.weight": "model-00008-of-00011.safetensors",
-    "model.layers.55.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
-    "model.layers.56.self_attn.q_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.56.self_attn.q_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.56.self_attn.q_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.56.self_attn.q_proj.bias": "model-00008-of-00011.safetensors",
-    "model.layers.56.self_attn.k_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.56.self_attn.k_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.56.self_attn.k_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.56.self_attn.k_proj.bias": "model-00008-of-00011.safetensors",
-    "model.layers.56.self_attn.v_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.56.self_attn.v_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.56.self_attn.v_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.56.self_attn.v_proj.bias": "model-00008-of-00011.safetensors",
-    "model.layers.56.self_attn.o_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.56.self_attn.o_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.56.self_attn.o_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.56.mlp.gate_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.56.mlp.gate_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.56.mlp.gate_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.56.mlp.up_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.56.mlp.up_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.56.mlp.up_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.56.mlp.down_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.56.mlp.down_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.56.mlp.down_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.56.input_layernorm.weight": "model-00008-of-00011.safetensors",
-    "model.layers.56.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
-    "model.layers.57.self_attn.q_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.57.self_attn.q_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.57.self_attn.q_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.57.self_attn.q_proj.bias": "model-00008-of-00011.safetensors",
-    "model.layers.57.self_attn.k_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.57.self_attn.k_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.57.self_attn.k_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.57.self_attn.k_proj.bias": "model-00008-of-00011.safetensors",
-    "model.layers.57.self_attn.v_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.57.self_attn.v_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.57.self_attn.v_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.57.self_attn.v_proj.bias": "model-00008-of-00011.safetensors",
-    "model.layers.57.self_attn.o_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.57.self_attn.o_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.57.self_attn.o_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.57.mlp.gate_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.57.mlp.gate_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.57.mlp.gate_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.57.mlp.up_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.57.mlp.up_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.57.mlp.up_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.57.mlp.down_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.57.mlp.down_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.57.mlp.down_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.57.input_layernorm.weight": "model-00008-of-00011.safetensors",
-    "model.layers.57.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
-    "model.layers.58.self_attn.q_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.58.self_attn.q_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.58.self_attn.q_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.58.self_attn.q_proj.bias": "model-00008-of-00011.safetensors",
-    "model.layers.58.self_attn.k_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.58.self_attn.k_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.58.self_attn.k_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.58.self_attn.k_proj.bias": "model-00008-of-00011.safetensors",
-    "model.layers.58.self_attn.v_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.58.self_attn.v_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.58.self_attn.v_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.58.self_attn.v_proj.bias": "model-00008-of-00011.safetensors",
-    "model.layers.58.self_attn.o_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.58.self_attn.o_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.58.self_attn.o_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.58.mlp.gate_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.58.mlp.gate_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.58.mlp.gate_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.58.mlp.up_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.58.mlp.up_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.58.mlp.up_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.58.mlp.down_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.58.mlp.down_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.58.mlp.down_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.58.input_layernorm.weight": "model-00008-of-00011.safetensors",
-    "model.layers.58.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
-    "model.layers.59.self_attn.q_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.59.self_attn.q_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.59.self_attn.q_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.59.self_attn.q_proj.bias": "model-00008-of-00011.safetensors",
-    "model.layers.59.self_attn.k_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.59.self_attn.k_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.59.self_attn.k_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.59.self_attn.k_proj.bias": "model-00008-of-00011.safetensors",
-    "model.layers.59.self_attn.v_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.59.self_attn.v_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.59.self_attn.v_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.59.self_attn.v_proj.bias": "model-00008-of-00011.safetensors",
-    "model.layers.59.self_attn.o_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.59.self_attn.o_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.59.self_attn.o_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.59.mlp.gate_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.59.mlp.gate_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.59.mlp.gate_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.59.mlp.up_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.59.mlp.up_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.59.mlp.up_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.59.mlp.down_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.59.mlp.down_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.59.mlp.down_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.59.input_layernorm.weight": "model-00008-of-00011.safetensors",
-    "model.layers.59.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
-    "model.layers.60.self_attn.q_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.60.self_attn.q_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.60.self_attn.q_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.60.self_attn.q_proj.bias": "model-00008-of-00011.safetensors",
-    "model.layers.60.self_attn.k_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.60.self_attn.k_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.60.self_attn.k_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.60.self_attn.k_proj.bias": "model-00008-of-00011.safetensors",
-    "model.layers.60.self_attn.v_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.60.self_attn.v_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.60.self_attn.v_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.60.self_attn.v_proj.bias": "model-00008-of-00011.safetensors",
-    "model.layers.60.self_attn.o_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.60.self_attn.o_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.60.self_attn.o_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.60.mlp.gate_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.60.mlp.gate_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.60.mlp.gate_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.60.mlp.up_proj.qweight": "model-00008-of-00011.safetensors",
-    "model.layers.60.mlp.up_proj.qzeros": "model-00008-of-00011.safetensors",
-    "model.layers.60.mlp.up_proj.scales": "model-00008-of-00011.safetensors",
-    "model.layers.60.mlp.down_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.60.mlp.down_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.60.mlp.down_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.60.input_layernorm.weight": "model-00009-of-00011.safetensors",
-    "model.layers.60.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
-    "model.layers.61.self_attn.q_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.61.self_attn.q_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.61.self_attn.q_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.61.self_attn.q_proj.bias": "model-00009-of-00011.safetensors",
-    "model.layers.61.self_attn.k_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.61.self_attn.k_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.61.self_attn.k_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.61.self_attn.k_proj.bias": "model-00009-of-00011.safetensors",
-    "model.layers.61.self_attn.v_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.61.self_attn.v_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.61.self_attn.v_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.61.self_attn.v_proj.bias": "model-00009-of-00011.safetensors",
-    "model.layers.61.self_attn.o_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.61.self_attn.o_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.61.self_attn.o_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.61.mlp.gate_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.61.mlp.gate_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.61.mlp.gate_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.61.mlp.up_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.61.mlp.up_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.61.mlp.up_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.61.mlp.down_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.61.mlp.down_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.61.mlp.down_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.61.input_layernorm.weight": "model-00009-of-00011.safetensors",
-    "model.layers.61.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
-    "model.layers.62.self_attn.q_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.62.self_attn.q_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.62.self_attn.q_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.62.self_attn.q_proj.bias": "model-00009-of-00011.safetensors",
-    "model.layers.62.self_attn.k_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.62.self_attn.k_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.62.self_attn.k_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.62.self_attn.k_proj.bias": "model-00009-of-00011.safetensors",
-    "model.layers.62.self_attn.v_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.62.self_attn.v_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.62.self_attn.v_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.62.self_attn.v_proj.bias": "model-00009-of-00011.safetensors",
-    "model.layers.62.self_attn.o_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.62.self_attn.o_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.62.self_attn.o_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.62.mlp.gate_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.62.mlp.gate_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.62.mlp.gate_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.62.mlp.up_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.62.mlp.up_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.62.mlp.up_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.62.mlp.down_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.62.mlp.down_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.62.mlp.down_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.62.input_layernorm.weight": "model-00009-of-00011.safetensors",
-    "model.layers.62.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
-    "model.layers.63.self_attn.q_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.63.self_attn.q_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.63.self_attn.q_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.63.self_attn.q_proj.bias": "model-00009-of-00011.safetensors",
-    "model.layers.63.self_attn.k_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.63.self_attn.k_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.63.self_attn.k_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.63.self_attn.k_proj.bias": "model-00009-of-00011.safetensors",
-    "model.layers.63.self_attn.v_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.63.self_attn.v_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.63.self_attn.v_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.63.self_attn.v_proj.bias": "model-00009-of-00011.safetensors",
-    "model.layers.63.self_attn.o_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.63.self_attn.o_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.63.self_attn.o_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.63.mlp.gate_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.63.mlp.gate_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.63.mlp.gate_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.63.mlp.up_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.63.mlp.up_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.63.mlp.up_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.63.mlp.down_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.63.mlp.down_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.63.mlp.down_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.63.input_layernorm.weight": "model-00009-of-00011.safetensors",
-    "model.layers.63.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
-    "model.layers.64.self_attn.q_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.64.self_attn.q_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.64.self_attn.q_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.64.self_attn.q_proj.bias": "model-00009-of-00011.safetensors",
-    "model.layers.64.self_attn.k_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.64.self_attn.k_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.64.self_attn.k_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.64.self_attn.k_proj.bias": "model-00009-of-00011.safetensors",
-    "model.layers.64.self_attn.v_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.64.self_attn.v_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.64.self_attn.v_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.64.self_attn.v_proj.bias": "model-00009-of-00011.safetensors",
-    "model.layers.64.self_attn.o_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.64.self_attn.o_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.64.self_attn.o_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.64.mlp.gate_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.64.mlp.gate_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.64.mlp.gate_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.64.mlp.up_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.64.mlp.up_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.64.mlp.up_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.64.mlp.down_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.64.mlp.down_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.64.mlp.down_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.64.input_layernorm.weight": "model-00009-of-00011.safetensors",
-    "model.layers.64.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
-    "model.layers.65.self_attn.q_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.65.self_attn.q_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.65.self_attn.q_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.65.self_attn.q_proj.bias": "model-00009-of-00011.safetensors",
-    "model.layers.65.self_attn.k_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.65.self_attn.k_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.65.self_attn.k_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.65.self_attn.k_proj.bias": "model-00009-of-00011.safetensors",
-    "model.layers.65.self_attn.v_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.65.self_attn.v_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.65.self_attn.v_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.65.self_attn.v_proj.bias": "model-00009-of-00011.safetensors",
-    "model.layers.65.self_attn.o_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.65.self_attn.o_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.65.self_attn.o_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.65.mlp.gate_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.65.mlp.gate_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.65.mlp.gate_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.65.mlp.up_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.65.mlp.up_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.65.mlp.up_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.65.mlp.down_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.65.mlp.down_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.65.mlp.down_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.65.input_layernorm.weight": "model-00009-of-00011.safetensors",
-    "model.layers.65.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
-    "model.layers.66.self_attn.q_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.66.self_attn.q_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.66.self_attn.q_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.66.self_attn.q_proj.bias": "model-00009-of-00011.safetensors",
-    "model.layers.66.self_attn.k_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.66.self_attn.k_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.66.self_attn.k_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.66.self_attn.k_proj.bias": "model-00009-of-00011.safetensors",
-    "model.layers.66.self_attn.v_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.66.self_attn.v_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.66.self_attn.v_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.66.self_attn.v_proj.bias": "model-00009-of-00011.safetensors",
-    "model.layers.66.self_attn.o_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.66.self_attn.o_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.66.self_attn.o_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.66.mlp.gate_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.66.mlp.gate_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.66.mlp.gate_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.66.mlp.up_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.66.mlp.up_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.66.mlp.up_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.66.mlp.down_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.66.mlp.down_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.66.mlp.down_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.66.input_layernorm.weight": "model-00009-of-00011.safetensors",
-    "model.layers.66.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
-    "model.layers.67.self_attn.q_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.67.self_attn.q_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.67.self_attn.q_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.67.self_attn.q_proj.bias": "model-00009-of-00011.safetensors",
-    "model.layers.67.self_attn.k_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.67.self_attn.k_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.67.self_attn.k_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.67.self_attn.k_proj.bias": "model-00009-of-00011.safetensors",
-    "model.layers.67.self_attn.v_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.67.self_attn.v_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.67.self_attn.v_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.67.self_attn.v_proj.bias": "model-00009-of-00011.safetensors",
-    "model.layers.67.self_attn.o_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.67.self_attn.o_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.67.self_attn.o_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.67.mlp.gate_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.67.mlp.gate_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.67.mlp.gate_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.67.mlp.up_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.67.mlp.up_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.67.mlp.up_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.67.mlp.down_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.67.mlp.down_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.67.mlp.down_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.67.input_layernorm.weight": "model-00009-of-00011.safetensors",
-    "model.layers.67.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
-    "model.layers.68.self_attn.q_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.68.self_attn.q_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.68.self_attn.q_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.68.self_attn.q_proj.bias": "model-00009-of-00011.safetensors",
-    "model.layers.68.self_attn.k_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.68.self_attn.k_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.68.self_attn.k_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.68.self_attn.k_proj.bias": "model-00009-of-00011.safetensors",
-    "model.layers.68.self_attn.v_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.68.self_attn.v_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.68.self_attn.v_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.68.self_attn.v_proj.bias": "model-00009-of-00011.safetensors",
-    "model.layers.68.self_attn.o_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.68.self_attn.o_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.68.self_attn.o_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.68.mlp.gate_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.68.mlp.gate_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.68.mlp.gate_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.68.mlp.up_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.68.mlp.up_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.68.mlp.up_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.68.mlp.down_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.68.mlp.down_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.68.mlp.down_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.68.input_layernorm.weight": "model-00009-of-00011.safetensors",
-    "model.layers.68.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
-    "model.layers.69.self_attn.q_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.69.self_attn.q_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.69.self_attn.q_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.69.self_attn.q_proj.bias": "model-00009-of-00011.safetensors",
-    "model.layers.69.self_attn.k_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.69.self_attn.k_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.69.self_attn.k_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.69.self_attn.k_proj.bias": "model-00009-of-00011.safetensors",
-    "model.layers.69.self_attn.v_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.69.self_attn.v_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.69.self_attn.v_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.69.self_attn.v_proj.bias": "model-00009-of-00011.safetensors",
-    "model.layers.69.self_attn.o_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.69.self_attn.o_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.69.self_attn.o_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.69.mlp.gate_proj.qweight": "model-00009-of-00011.safetensors",
-    "model.layers.69.mlp.gate_proj.qzeros": "model-00009-of-00011.safetensors",
-    "model.layers.69.mlp.gate_proj.scales": "model-00009-of-00011.safetensors",
-    "model.layers.69.mlp.up_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.69.mlp.up_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.69.mlp.up_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.69.mlp.down_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.69.mlp.down_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.69.mlp.down_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.69.input_layernorm.weight": "model-00010-of-00011.safetensors",
-    "model.layers.69.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
-    "model.layers.70.self_attn.q_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.70.self_attn.q_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.70.self_attn.q_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.70.self_attn.q_proj.bias": "model-00010-of-00011.safetensors",
-    "model.layers.70.self_attn.k_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.70.self_attn.k_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.70.self_attn.k_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.70.self_attn.k_proj.bias": "model-00010-of-00011.safetensors",
-    "model.layers.70.self_attn.v_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.70.self_attn.v_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.70.self_attn.v_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.70.self_attn.v_proj.bias": "model-00010-of-00011.safetensors",
-    "model.layers.70.self_attn.o_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.70.self_attn.o_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.70.self_attn.o_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.70.mlp.gate_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.70.mlp.gate_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.70.mlp.gate_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.70.mlp.up_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.70.mlp.up_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.70.mlp.up_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.70.mlp.down_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.70.mlp.down_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.70.mlp.down_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.70.input_layernorm.weight": "model-00010-of-00011.safetensors",
-    "model.layers.70.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
-    "model.layers.71.self_attn.q_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.71.self_attn.q_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.71.self_attn.q_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.71.self_attn.q_proj.bias": "model-00010-of-00011.safetensors",
-    "model.layers.71.self_attn.k_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.71.self_attn.k_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.71.self_attn.k_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.71.self_attn.k_proj.bias": "model-00010-of-00011.safetensors",
-    "model.layers.71.self_attn.v_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.71.self_attn.v_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.71.self_attn.v_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.71.self_attn.v_proj.bias": "model-00010-of-00011.safetensors",
-    "model.layers.71.self_attn.o_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.71.self_attn.o_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.71.self_attn.o_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.71.mlp.gate_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.71.mlp.gate_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.71.mlp.gate_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.71.mlp.up_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.71.mlp.up_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.71.mlp.up_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.71.mlp.down_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.71.mlp.down_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.71.mlp.down_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.71.input_layernorm.weight": "model-00010-of-00011.safetensors",
-    "model.layers.71.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
-    "model.layers.72.self_attn.q_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.72.self_attn.q_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.72.self_attn.q_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.72.self_attn.q_proj.bias": "model-00010-of-00011.safetensors",
-    "model.layers.72.self_attn.k_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.72.self_attn.k_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.72.self_attn.k_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.72.self_attn.k_proj.bias": "model-00010-of-00011.safetensors",
-    "model.layers.72.self_attn.v_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.72.self_attn.v_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.72.self_attn.v_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.72.self_attn.v_proj.bias": "model-00010-of-00011.safetensors",
-    "model.layers.72.self_attn.o_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.72.self_attn.o_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.72.self_attn.o_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.72.mlp.gate_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.72.mlp.gate_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.72.mlp.gate_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.72.mlp.up_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.72.mlp.up_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.72.mlp.up_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.72.mlp.down_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.72.mlp.down_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.72.mlp.down_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.72.input_layernorm.weight": "model-00010-of-00011.safetensors",
-    "model.layers.72.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
-    "model.layers.73.self_attn.q_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.73.self_attn.q_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.73.self_attn.q_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.73.self_attn.q_proj.bias": "model-00010-of-00011.safetensors",
-    "model.layers.73.self_attn.k_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.73.self_attn.k_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.73.self_attn.k_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.73.self_attn.k_proj.bias": "model-00010-of-00011.safetensors",
-    "model.layers.73.self_attn.v_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.73.self_attn.v_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.73.self_attn.v_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.73.self_attn.v_proj.bias": "model-00010-of-00011.safetensors",
-    "model.layers.73.self_attn.o_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.73.self_attn.o_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.73.self_attn.o_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.73.mlp.gate_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.73.mlp.gate_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.73.mlp.gate_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.73.mlp.up_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.73.mlp.up_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.73.mlp.up_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.73.mlp.down_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.73.mlp.down_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.73.mlp.down_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.73.input_layernorm.weight": "model-00010-of-00011.safetensors",
-    "model.layers.73.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
-    "model.layers.74.self_attn.q_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.74.self_attn.q_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.74.self_attn.q_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.74.self_attn.q_proj.bias": "model-00010-of-00011.safetensors",
-    "model.layers.74.self_attn.k_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.74.self_attn.k_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.74.self_attn.k_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.74.self_attn.k_proj.bias": "model-00010-of-00011.safetensors",
-    "model.layers.74.self_attn.v_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.74.self_attn.v_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.74.self_attn.v_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.74.self_attn.v_proj.bias": "model-00010-of-00011.safetensors",
-    "model.layers.74.self_attn.o_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.74.self_attn.o_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.74.self_attn.o_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.74.mlp.gate_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.74.mlp.gate_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.74.mlp.gate_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.74.mlp.up_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.74.mlp.up_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.74.mlp.up_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.74.mlp.down_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.74.mlp.down_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.74.mlp.down_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.74.input_layernorm.weight": "model-00010-of-00011.safetensors",
-    "model.layers.74.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
-    "model.layers.75.self_attn.q_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.75.self_attn.q_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.75.self_attn.q_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.75.self_attn.q_proj.bias": "model-00010-of-00011.safetensors",
-    "model.layers.75.self_attn.k_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.75.self_attn.k_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.75.self_attn.k_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.75.self_attn.k_proj.bias": "model-00010-of-00011.safetensors",
-    "model.layers.75.self_attn.v_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.75.self_attn.v_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.75.self_attn.v_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.75.self_attn.v_proj.bias": "model-00010-of-00011.safetensors",
-    "model.layers.75.self_attn.o_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.75.self_attn.o_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.75.self_attn.o_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.75.mlp.gate_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.75.mlp.gate_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.75.mlp.gate_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.75.mlp.up_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.75.mlp.up_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.75.mlp.up_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.75.mlp.down_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.75.mlp.down_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.75.mlp.down_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.75.input_layernorm.weight": "model-00010-of-00011.safetensors",
-    "model.layers.75.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
-    "model.layers.76.self_attn.q_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.76.self_attn.q_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.76.self_attn.q_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.76.self_attn.q_proj.bias": "model-00010-of-00011.safetensors",
-    "model.layers.76.self_attn.k_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.76.self_attn.k_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.76.self_attn.k_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.76.self_attn.k_proj.bias": "model-00010-of-00011.safetensors",
-    "model.layers.76.self_attn.v_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.76.self_attn.v_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.76.self_attn.v_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.76.self_attn.v_proj.bias": "model-00010-of-00011.safetensors",
-    "model.layers.76.self_attn.o_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.76.self_attn.o_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.76.self_attn.o_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.76.mlp.gate_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.76.mlp.gate_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.76.mlp.gate_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.76.mlp.up_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.76.mlp.up_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.76.mlp.up_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.76.mlp.down_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.76.mlp.down_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.76.mlp.down_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.76.input_layernorm.weight": "model-00010-of-00011.safetensors",
-    "model.layers.76.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
-    "model.layers.77.self_attn.q_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.77.self_attn.q_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.77.self_attn.q_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.77.self_attn.q_proj.bias": "model-00010-of-00011.safetensors",
-    "model.layers.77.self_attn.k_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.77.self_attn.k_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.77.self_attn.k_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.77.self_attn.k_proj.bias": "model-00010-of-00011.safetensors",
-    "model.layers.77.self_attn.v_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.77.self_attn.v_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.77.self_attn.v_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.77.self_attn.v_proj.bias": "model-00010-of-00011.safetensors",
-    "model.layers.77.self_attn.o_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.77.self_attn.o_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.77.self_attn.o_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.77.mlp.gate_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.77.mlp.gate_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.77.mlp.gate_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.77.mlp.up_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.77.mlp.up_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.77.mlp.up_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.77.mlp.down_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.77.mlp.down_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.77.mlp.down_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.77.input_layernorm.weight": "model-00010-of-00011.safetensors",
-    "model.layers.77.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
-    "model.layers.78.self_attn.q_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.78.self_attn.q_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.78.self_attn.q_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.78.self_attn.q_proj.bias": "model-00010-of-00011.safetensors",
-    "model.layers.78.self_attn.k_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.78.self_attn.k_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.78.self_attn.k_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.78.self_attn.k_proj.bias": "model-00010-of-00011.safetensors",
-    "model.layers.78.self_attn.v_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.78.self_attn.v_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.78.self_attn.v_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.78.self_attn.v_proj.bias": "model-00010-of-00011.safetensors",
-    "model.layers.78.self_attn.o_proj.qweight": "model-00010-of-00011.safetensors",
-    "model.layers.78.self_attn.o_proj.qzeros": "model-00010-of-00011.safetensors",
-    "model.layers.78.self_attn.o_proj.scales": "model-00010-of-00011.safetensors",
-    "model.layers.78.mlp.gate_proj.qweight": "model-00011-of-00011.safetensors",
-    "model.layers.78.mlp.gate_proj.qzeros": "model-00011-of-00011.safetensors",
-    "model.layers.78.mlp.gate_proj.scales": "model-00011-of-00011.safetensors",
-    "model.layers.78.mlp.up_proj.qweight": "model-00011-of-00011.safetensors",
-    "model.layers.78.mlp.up_proj.qzeros": "model-00011-of-00011.safetensors",
-    "model.layers.78.mlp.up_proj.scales": "model-00011-of-00011.safetensors",
-    "model.layers.78.mlp.down_proj.qweight": "model-00011-of-00011.safetensors",
-    "model.layers.78.mlp.down_proj.qzeros": "model-00011-of-00011.safetensors",
-    "model.layers.78.mlp.down_proj.scales": "model-00011-of-00011.safetensors",
-    "model.layers.78.input_layernorm.weight": "model-00011-of-00011.safetensors",
-    "model.layers.78.post_attention_layernorm.weight": "model-00011-of-00011.safetensors",
-    "model.layers.79.self_attn.q_proj.qweight": "model-00011-of-00011.safetensors",
-    "model.layers.79.self_attn.q_proj.qzeros": "model-00011-of-00011.safetensors",
-    "model.layers.79.self_attn.q_proj.scales": "model-00011-of-00011.safetensors",
-    "model.layers.79.self_attn.q_proj.bias": "model-00011-of-00011.safetensors",
-    "model.layers.79.self_attn.k_proj.qweight": "model-00011-of-00011.safetensors",
-    "model.layers.79.self_attn.k_proj.qzeros": "model-00011-of-00011.safetensors",
-    "model.layers.79.self_attn.k_proj.scales": "model-00011-of-00011.safetensors",
-    "model.layers.79.self_attn.k_proj.bias": "model-00011-of-00011.safetensors",
-    "model.layers.79.self_attn.v_proj.qweight": "model-00011-of-00011.safetensors",
-    "model.layers.79.self_attn.v_proj.qzeros": "model-00011-of-00011.safetensors",
-    "model.layers.79.self_attn.v_proj.scales": "model-00011-of-00011.safetensors",
-    "model.layers.79.self_attn.v_proj.bias": "model-00011-of-00011.safetensors",
-    "model.layers.79.self_attn.o_proj.qweight": "model-00011-of-00011.safetensors",
-    "model.layers.79.self_attn.o_proj.qzeros": "model-00011-of-00011.safetensors",
-    "model.layers.79.self_attn.o_proj.scales": "model-00011-of-00011.safetensors",
-    "model.layers.79.mlp.gate_proj.qweight": "model-00011-of-00011.safetensors",
-    "model.layers.79.mlp.gate_proj.qzeros": "model-00011-of-00011.safetensors",
-    "model.layers.79.mlp.gate_proj.scales": "model-00011-of-00011.safetensors",
-    "model.layers.79.mlp.up_proj.qweight": "model-00011-of-00011.safetensors",
-    "model.layers.79.mlp.up_proj.qzeros": "model-00011-of-00011.safetensors",
-    "model.layers.79.mlp.up_proj.scales": "model-00011-of-00011.safetensors",
-    "model.layers.79.mlp.down_proj.qweight": "model-00011-of-00011.safetensors",
-    "model.layers.79.mlp.down_proj.qzeros": "model-00011-of-00011.safetensors",
-    "model.layers.79.mlp.down_proj.scales": "model-00011-of-00011.safetensors",
-    "model.layers.79.input_layernorm.weight": "model-00011-of-00011.safetensors",
-    "model.layers.79.post_attention_layernorm.weight": "model-00011-of-00011.safetensors",
-    "model.norm.weight": "model-00011-of-00011.safetensors",
-    "lm_head.weight": "model-00011-of-00011.safetensors"
+    "visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
+    "visual.merger.ln_q.weight": "model-00001-of-00002.safetensors",
+    "visual.merger.mlp.0.weight": "model-00001-of-00002.safetensors",
+    "visual.merger.mlp.0.bias": "model-00001-of-00002.safetensors",
+    "visual.merger.mlp.2.weight": "model-00001-of-00002.safetensors",
+    "visual.merger.mlp.2.bias": "model-00001-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors",
+    "lm_head.weight": "model-00002-of-00002.safetensors"
   }
 }
\ No newline at end of file