Upload folder using huggingface_hub

LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "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.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      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 conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2024 Granite Team, IBM
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

README.md

@@ -0,0 +1,42 @@
+---
+license: apache-2.0
+license_link: https://www.apache.org/licenses/LICENSE-2.0
+base_model: ibm-granite/granite-4.1-8b
+base_model_relation: quantized
+library_name: mlx
+pipeline_tag: text-generation
+language: [en, de, es, fr, ja, pt, ar, cs, it, ko, nl, zh]
+tags: [language, granite-4.1, mlx, apple-silicon]
+---
+
+# granite-4.1-8b-5bit-awq-mlx
+
+## Provenance
+
+Converted from [`ibm-granite/granite-4.1-8b`](https://huggingface.co/ibm-granite/granite-4.1-8b) using
+[mlx-lm](https://github.com/ml-explore/mlx-lm) 0.31.3.
+
+## Usage
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("salohcin714/granite-4.1-8b-5bit-awq-mlx")
+messages = [{"role": "user", "content": "Hello"}]
+prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True)
+text = generate(model, tokenizer, prompt=prompt, verbose=True)
+```
+
+## Modifications
+
+Weights converted to MLX safetensors layout and quantized (5-bit affine quantization, group size 64, via AWQ activation-aware calibration). Redundant tied `lm_head.weight` dropped where the model ties input/output embeddings. No fine-tuning; no added training data.
+
+## License and attribution
+
+Licensed under [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0). Original weights by the Granite Team, IBM. See the
+[upstream model card](https://huggingface.co/ibm-granite/granite-4.1-8b) and the included
+`LICENSE` file for the full text.
+
+## Disclaimer
+
+This repository is not affiliated with or endorsed by IBM. "Granite" is an IBM trademark, used here descriptively to identify the origin of the base model. IBM's published benchmarks describe the original weights, not this quantized/converted artifact, and must not be read as claims about this repo.

chat_template.jinja

@@ -0,0 +1,114 @@
+{%- set tools_system_message_prefix = 'You are a helpful assistant with access to the following tools. You may call one or more tools to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>'  %}
+{%- set tools_system_message_suffix = '\n</tools>\n\nFor each tool call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request.' %}
+{%- set documents_system_message_prefix = 'You are a helpful assistant with access to the following documents. You may use one or more documents to assist with the user query.\n\nYou are given a list of documents within <documents></documents> XML tags:\n<documents>' %}
+{%- set documents_system_message_suffix = '\n</documents>\n\nWrite the response to the user\'s input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data.' %}
+{%- if available_tools is defined and available_tools %}
+    {%- set tools = available_tools %}
+{%- endif %}
+{%- set ns = namespace(tools_system_message=tools_system_message_prefix,
+                       documents_system_message=documents_system_message_prefix,
+                       system_message=''
+                       ) %}
+{%- if tools %}
+    {%- for tool in tools %}
+        {%- set ns.tools_system_message = ns.tools_system_message + '\n' + (tool | tojson) %}
+    {%- endfor %}
+    {%- set ns.tools_system_message = ns.tools_system_message + tools_system_message_suffix %}
+{%- else %}
+    {%- set ns.tools_system_message = '' %}
+{%- endif %}
+{%- if documents %}
+    {%- for document in documents %}
+        {%- set ns.documents_system_message = ns.documents_system_message + '\n' + (document | tojson) %}
+    {%- endfor %}
+    {%- set ns.documents_system_message = ns.documents_system_message + documents_system_message_suffix %}
+{%- else %}
+    {%- set ns.documents_system_message = '' %}
+{%- endif %}
+{%- if messages[0].role == 'system' %}
+    {%- if messages[0].content is string %}
+        {%- set ns.system_message = messages[0].content %}
+    {%- elif messages[0].content is iterable %}
+        {%- for entry in messages[0].content %}
+            {%- if entry.type== 'text' %}
+                {%- if ns.system_message != '' %}
+                    {%- set ns.system_message = ns.system_message + '\n' %}
+                {%- endif %}
+                {%- set ns.system_message = ns.system_message + entry.text %}
+            {%- endif %}
+        {%- endfor %}
+    {%- endif %}
+    {%- if tools and documents %}
+        {%- set ns.system_message = ns.system_message + '\n\n' +  ns.tools_system_message + '\n\n' + ns.documents_system_message %}
+    {%- elif tools %}
+        {%- set ns.system_message = ns.system_message + '\n\n' + ns.tools_system_message %}
+    {%- elif documents %}
+        {%- set ns.system_message = ns.system_message + '\n\n' + ns.documents_system_message %}
+    {%- endif %}
+{%- else %}
+    {%- if tools and documents %}
+        {%- set ns.system_message = ns.tools_system_message + '\n\n' + ns.documents_system_message  %}
+    {%- elif tools %}
+        {%- set ns.system_message = ns.tools_system_message %}
+    {%- elif documents %}
+        {%- set ns.system_message = ns.documents_system_message %}
+    {%- endif %}
+{%- endif %}
+{%- if ns.system_message %}
+    {{- '<|start_of_role|>system<|end_of_role|>' + ns.system_message + '<|end_of_text|>\n' }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = namespace(val='') %}
+    {%- if message.content is string %}
+        {%- set content.val = message.content %}
+    {%- else %}
+        {%- if message.content is iterable %}
+            {%- for entry in message.content %}
+                {%- if entry.type== 'text' %}
+                    {%- if content.val != '' %}
+                        {%- set content.val = content.val + '\n' %}
+                    {%- endif %}
+                    {%- set content.val = content.val + entry.text %}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+    {%- endif %}
+    {%- if (message.role == 'user') or (message.role == 'system' and not loop.first) %}
+        {{- '<|start_of_role|>' + message.role + '<|end_of_role|>' + content.val + '<|end_of_text|>\n' }}
+    {%- elif message.role == 'assistant' %}
+        {{- '<|start_of_role|>' + message.role + '<|end_of_role|>' + content.val }}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content.val) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|end_of_text|>\n' }}
+    {%- elif message.role == 'tool' %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != 'tool') %}
+            {{- '<|start_of_role|>user<|end_of_role|>' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content.val }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != 'tool') %}
+            {{- '<|end_of_text|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|start_of_role|>assistant<|end_of_role|>' }}
+{%- endif %}

config.json

@@ -0,0 +1,2530 @@
+{
+    "architectures": [
+        "GraniteForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attention_multiplier": 0.0078125,
+    "bos_token_id": 100257,
+    "embedding_multiplier": 12.0,
+    "eos_token_id": 100257,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "initializer_range": 0.1,
+    "intermediate_size": 12800,
+    "logits_scaling": 16.0,
+    "max_position_embeddings": 131072,
+    "mlp_bias": false,
+    "model_type": "granite",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 40,
+    "num_key_value_heads": 8,
+    "pad_token_id": 100256,
+    "quantization": {
+        "group_size": 64,
+        "bits": 4,
+        "model.embed_tokens": {
+            "group_size": 32,
+            "bits": 4
+        },
+        "model.layers.0.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.0.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.0.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.0.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.0.self_attn.rope": false,
+        "model.layers.0.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.0.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.0.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.0.input_layernorm": false,
+        "model.layers.0.post_attention_layernorm": false,
+        "model.layers.1.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.1.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.1.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.1.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.1.self_attn.rope": false,
+        "model.layers.1.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.1.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.1.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.1.input_layernorm": false,
+        "model.layers.1.post_attention_layernorm": false,
+        "model.layers.2.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.2.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.2.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.2.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.2.self_attn.rope": false,
+        "model.layers.2.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.2.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.2.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.2.input_layernorm": false,
+        "model.layers.2.post_attention_layernorm": false,
+        "model.layers.3.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.3.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.3.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.3.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.3.self_attn.rope": false,
+        "model.layers.3.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.3.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.3.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.3.input_layernorm": false,
+        "model.layers.3.post_attention_layernorm": false,
+        "model.layers.4.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.4.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.4.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.4.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.4.self_attn.rope": false,
+        "model.layers.4.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.4.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.4.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.4.input_layernorm": false,
+        "model.layers.4.post_attention_layernorm": false,
+        "model.layers.5.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.5.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.5.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.5.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.5.self_attn.rope": false,
+        "model.layers.5.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.5.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.5.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.5.input_layernorm": false,
+        "model.layers.5.post_attention_layernorm": false,
+        "model.layers.6.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.6.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.6.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.6.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.6.self_attn.rope": false,
+        "model.layers.6.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.6.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.6.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.6.input_layernorm": false,
+        "model.layers.6.post_attention_layernorm": false,
+        "model.layers.7.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.7.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.7.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.7.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.7.self_attn.rope": false,
+        "model.layers.7.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.7.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.7.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.7.input_layernorm": false,
+        "model.layers.7.post_attention_layernorm": false,
+        "model.layers.8.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.8.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.8.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.8.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.8.self_attn.rope": false,
+        "model.layers.8.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.8.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.8.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.8.input_layernorm": false,
+        "model.layers.8.post_attention_layernorm": false,
+        "model.layers.9.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.9.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.9.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.9.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.9.self_attn.rope": false,
+        "model.layers.9.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.9.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.9.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.9.input_layernorm": false,
+        "model.layers.9.post_attention_layernorm": false,
+        "model.layers.10.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.10.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.10.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.10.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.10.self_attn.rope": false,
+        "model.layers.10.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.10.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.10.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.10.input_layernorm": false,
+        "model.layers.10.post_attention_layernorm": false,
+        "model.layers.11.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.11.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.11.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.11.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.11.self_attn.rope": false,
+        "model.layers.11.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.11.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.11.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.11.input_layernorm": false,
+        "model.layers.11.post_attention_layernorm": false,
+        "model.layers.12.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.12.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.12.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.12.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.12.self_attn.rope": false,
+        "model.layers.12.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.12.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.12.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.12.input_layernorm": false,
+        "model.layers.12.post_attention_layernorm": false,
+        "model.layers.13.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.13.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.13.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.13.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.13.self_attn.rope": false,
+        "model.layers.13.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.13.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.13.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.13.input_layernorm": false,
+        "model.layers.13.post_attention_layernorm": false,
+        "model.layers.14.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.14.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.14.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.14.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.14.self_attn.rope": false,
+        "model.layers.14.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.14.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.14.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.14.input_layernorm": false,
+        "model.layers.14.post_attention_layernorm": false,
+        "model.layers.15.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.15.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.15.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.15.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.15.self_attn.rope": false,
+        "model.layers.15.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.15.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.15.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.15.input_layernorm": false,
+        "model.layers.15.post_attention_layernorm": false,
+        "model.layers.16.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.16.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.16.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.16.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.16.self_attn.rope": false,
+        "model.layers.16.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.16.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.16.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.16.input_layernorm": false,
+        "model.layers.16.post_attention_layernorm": false,
+        "model.layers.17.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.17.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.17.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.17.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.17.self_attn.rope": false,
+        "model.layers.17.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.17.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.17.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.17.input_layernorm": false,
+        "model.layers.17.post_attention_layernorm": false,
+        "model.layers.18.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.18.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.18.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.18.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.18.self_attn.rope": false,
+        "model.layers.18.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.18.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.18.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.18.input_layernorm": false,
+        "model.layers.18.post_attention_layernorm": false,
+        "model.layers.19.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.19.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.19.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.19.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.19.self_attn.rope": false,
+        "model.layers.19.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.19.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.19.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.19.input_layernorm": false,
+        "model.layers.19.post_attention_layernorm": false,
+        "model.layers.20.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.20.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.20.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.20.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.20.self_attn.rope": false,
+        "model.layers.20.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.20.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.20.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.20.input_layernorm": false,
+        "model.layers.20.post_attention_layernorm": false,
+        "model.layers.21.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.21.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.21.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.21.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.21.self_attn.rope": false,
+        "model.layers.21.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.21.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.21.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.21.input_layernorm": false,
+        "model.layers.21.post_attention_layernorm": false,
+        "model.layers.22.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.22.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.22.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.22.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.22.self_attn.rope": false,
+        "model.layers.22.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.22.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.22.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.22.input_layernorm": false,
+        "model.layers.22.post_attention_layernorm": false,
+        "model.layers.23.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.23.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.23.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.23.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.23.self_attn.rope": false,
+        "model.layers.23.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.23.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.23.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.23.input_layernorm": false,
+        "model.layers.23.post_attention_layernorm": false,
+        "model.layers.24.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.24.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.24.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.24.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.24.self_attn.rope": false,
+        "model.layers.24.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.24.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.24.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.24.input_layernorm": false,
+        "model.layers.24.post_attention_layernorm": false,
+        "model.layers.25.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.25.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.25.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.25.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.25.self_attn.rope": false,
+        "model.layers.25.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.25.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.25.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.25.input_layernorm": false,
+        "model.layers.25.post_attention_layernorm": false,
+        "model.layers.26.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.26.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.26.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.26.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.26.self_attn.rope": false,
+        "model.layers.26.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.26.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.26.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.26.input_layernorm": false,
+        "model.layers.26.post_attention_layernorm": false,
+        "model.layers.27.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.27.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.27.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.27.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.27.self_attn.rope": false,
+        "model.layers.27.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.27.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.27.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.27.input_layernorm": false,
+        "model.layers.27.post_attention_layernorm": false,
+        "model.layers.28.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.28.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.28.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.28.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.28.self_attn.rope": false,
+        "model.layers.28.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.28.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.28.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.28.input_layernorm": false,
+        "model.layers.28.post_attention_layernorm": false,
+        "model.layers.29.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.29.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.29.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.29.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.29.self_attn.rope": false,
+        "model.layers.29.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.29.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.29.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.29.input_layernorm": false,
+        "model.layers.29.post_attention_layernorm": false,
+        "model.layers.30.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.30.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.30.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.30.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.30.self_attn.rope": false,
+        "model.layers.30.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.30.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.30.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.30.input_layernorm": false,
+        "model.layers.30.post_attention_layernorm": false,
+        "model.layers.31.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.31.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.31.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.31.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.31.self_attn.rope": false,
+        "model.layers.31.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.31.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.31.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.31.input_layernorm": false,
+        "model.layers.31.post_attention_layernorm": false,
+        "model.layers.32.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.32.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.32.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.32.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.32.self_attn.rope": false,
+        "model.layers.32.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.32.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.32.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.32.input_layernorm": false,
+        "model.layers.32.post_attention_layernorm": false,
+        "model.layers.33.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.33.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.33.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.33.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.33.self_attn.rope": false,
+        "model.layers.33.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.33.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.33.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.33.input_layernorm": false,
+        "model.layers.33.post_attention_layernorm": false,
+        "model.layers.34.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.34.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.34.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.34.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.34.self_attn.rope": false,
+        "model.layers.34.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.34.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.34.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.34.input_layernorm": false,
+        "model.layers.34.post_attention_layernorm": false,
+        "model.layers.35.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.35.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.35.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.35.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.35.self_attn.rope": false,
+        "model.layers.35.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.35.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.35.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.35.input_layernorm": false,
+        "model.layers.35.post_attention_layernorm": false,
+        "model.layers.36.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.36.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.36.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.36.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.36.self_attn.rope": false,
+        "model.layers.36.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.36.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.36.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.36.input_layernorm": false,
+        "model.layers.36.post_attention_layernorm": false,
+        "model.layers.37.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.37.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.37.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.37.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.37.self_attn.rope": false,
+        "model.layers.37.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.37.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.37.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.37.input_layernorm": false,
+        "model.layers.37.post_attention_layernorm": false,
+        "model.layers.38.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.38.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.38.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.38.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.38.self_attn.rope": false,
+        "model.layers.38.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.38.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.38.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.38.input_layernorm": false,
+        "model.layers.38.post_attention_layernorm": false,
+        "model.layers.39.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.39.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.39.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.39.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.39.self_attn.rope": false,
+        "model.layers.39.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.39.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.39.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.39.input_layernorm": false,
+        "model.layers.39.post_attention_layernorm": false,
+        "model.norm": false
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 4,
+        "model.embed_tokens": {
+            "group_size": 32,
+            "bits": 4
+        },
+        "model.layers.0.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.0.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.0.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.0.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.0.self_attn.rope": false,
+        "model.layers.0.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.0.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.0.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.0.input_layernorm": false,
+        "model.layers.0.post_attention_layernorm": false,
+        "model.layers.1.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.1.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.1.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.1.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.1.self_attn.rope": false,
+        "model.layers.1.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.1.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.1.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.1.input_layernorm": false,
+        "model.layers.1.post_attention_layernorm": false,
+        "model.layers.2.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.2.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.2.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.2.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.2.self_attn.rope": false,
+        "model.layers.2.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.2.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.2.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.2.input_layernorm": false,
+        "model.layers.2.post_attention_layernorm": false,
+        "model.layers.3.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.3.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.3.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.3.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.3.self_attn.rope": false,
+        "model.layers.3.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.3.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.3.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.3.input_layernorm": false,
+        "model.layers.3.post_attention_layernorm": false,
+        "model.layers.4.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.4.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.4.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.4.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.4.self_attn.rope": false,
+        "model.layers.4.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.4.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.4.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.4.input_layernorm": false,
+        "model.layers.4.post_attention_layernorm": false,
+        "model.layers.5.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.5.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.5.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.5.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.5.self_attn.rope": false,
+        "model.layers.5.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.5.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.5.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.5.input_layernorm": false,
+        "model.layers.5.post_attention_layernorm": false,
+        "model.layers.6.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.6.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.6.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.6.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.6.self_attn.rope": false,
+        "model.layers.6.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.6.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.6.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.6.input_layernorm": false,
+        "model.layers.6.post_attention_layernorm": false,
+        "model.layers.7.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.7.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.7.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.7.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.7.self_attn.rope": false,
+        "model.layers.7.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.7.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.7.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.7.input_layernorm": false,
+        "model.layers.7.post_attention_layernorm": false,
+        "model.layers.8.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.8.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.8.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.8.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.8.self_attn.rope": false,
+        "model.layers.8.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.8.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.8.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.8.input_layernorm": false,
+        "model.layers.8.post_attention_layernorm": false,
+        "model.layers.9.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.9.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.9.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.9.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.9.self_attn.rope": false,
+        "model.layers.9.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.9.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.9.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.9.input_layernorm": false,
+        "model.layers.9.post_attention_layernorm": false,
+        "model.layers.10.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.10.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.10.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.10.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.10.self_attn.rope": false,
+        "model.layers.10.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.10.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.10.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.10.input_layernorm": false,
+        "model.layers.10.post_attention_layernorm": false,
+        "model.layers.11.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.11.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.11.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.11.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.11.self_attn.rope": false,
+        "model.layers.11.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.11.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.11.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.11.input_layernorm": false,
+        "model.layers.11.post_attention_layernorm": false,
+        "model.layers.12.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.12.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.12.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.12.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.12.self_attn.rope": false,
+        "model.layers.12.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.12.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.12.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.12.input_layernorm": false,
+        "model.layers.12.post_attention_layernorm": false,
+        "model.layers.13.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.13.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.13.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.13.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.13.self_attn.rope": false,
+        "model.layers.13.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.13.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.13.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.13.input_layernorm": false,
+        "model.layers.13.post_attention_layernorm": false,
+        "model.layers.14.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.14.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.14.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.14.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.14.self_attn.rope": false,
+        "model.layers.14.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.14.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.14.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.14.input_layernorm": false,
+        "model.layers.14.post_attention_layernorm": false,
+        "model.layers.15.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.15.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.15.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.15.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.15.self_attn.rope": false,
+        "model.layers.15.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.15.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.15.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.15.input_layernorm": false,
+        "model.layers.15.post_attention_layernorm": false,
+        "model.layers.16.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.16.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.16.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.16.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.16.self_attn.rope": false,
+        "model.layers.16.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.16.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.16.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.16.input_layernorm": false,
+        "model.layers.16.post_attention_layernorm": false,
+        "model.layers.17.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.17.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.17.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.17.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.17.self_attn.rope": false,
+        "model.layers.17.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.17.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.17.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.17.input_layernorm": false,
+        "model.layers.17.post_attention_layernorm": false,
+        "model.layers.18.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.18.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.18.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.18.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.18.self_attn.rope": false,
+        "model.layers.18.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.18.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.18.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.18.input_layernorm": false,
+        "model.layers.18.post_attention_layernorm": false,
+        "model.layers.19.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.19.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.19.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.19.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.19.self_attn.rope": false,
+        "model.layers.19.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.19.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.19.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.19.input_layernorm": false,
+        "model.layers.19.post_attention_layernorm": false,
+        "model.layers.20.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.20.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.20.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.20.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.20.self_attn.rope": false,
+        "model.layers.20.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.20.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.20.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.20.input_layernorm": false,
+        "model.layers.20.post_attention_layernorm": false,
+        "model.layers.21.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.21.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.21.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.21.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.21.self_attn.rope": false,
+        "model.layers.21.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.21.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.21.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.21.input_layernorm": false,
+        "model.layers.21.post_attention_layernorm": false,
+        "model.layers.22.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.22.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.22.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.22.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.22.self_attn.rope": false,
+        "model.layers.22.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.22.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.22.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.22.input_layernorm": false,
+        "model.layers.22.post_attention_layernorm": false,
+        "model.layers.23.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.23.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.23.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.23.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.23.self_attn.rope": false,
+        "model.layers.23.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.23.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.23.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.23.input_layernorm": false,
+        "model.layers.23.post_attention_layernorm": false,
+        "model.layers.24.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.24.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.24.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.24.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.24.self_attn.rope": false,
+        "model.layers.24.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.24.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.24.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.24.input_layernorm": false,
+        "model.layers.24.post_attention_layernorm": false,
+        "model.layers.25.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.25.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.25.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.25.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.25.self_attn.rope": false,
+        "model.layers.25.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.25.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.25.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.25.input_layernorm": false,
+        "model.layers.25.post_attention_layernorm": false,
+        "model.layers.26.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.26.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.26.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.26.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.26.self_attn.rope": false,
+        "model.layers.26.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.26.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.26.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.26.input_layernorm": false,
+        "model.layers.26.post_attention_layernorm": false,
+        "model.layers.27.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.27.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.27.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.27.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.27.self_attn.rope": false,
+        "model.layers.27.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.27.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.27.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.27.input_layernorm": false,
+        "model.layers.27.post_attention_layernorm": false,
+        "model.layers.28.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.28.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.28.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.28.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.28.self_attn.rope": false,
+        "model.layers.28.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.28.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.28.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.28.input_layernorm": false,
+        "model.layers.28.post_attention_layernorm": false,
+        "model.layers.29.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.29.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.29.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.29.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.29.self_attn.rope": false,
+        "model.layers.29.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.29.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.29.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.29.input_layernorm": false,
+        "model.layers.29.post_attention_layernorm": false,
+        "model.layers.30.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.30.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.30.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.30.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.30.self_attn.rope": false,
+        "model.layers.30.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.30.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.30.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.30.input_layernorm": false,
+        "model.layers.30.post_attention_layernorm": false,
+        "model.layers.31.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.31.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.31.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.31.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.31.self_attn.rope": false,
+        "model.layers.31.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.31.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.31.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.31.input_layernorm": false,
+        "model.layers.31.post_attention_layernorm": false,
+        "model.layers.32.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.32.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.32.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.32.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.32.self_attn.rope": false,
+        "model.layers.32.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.32.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.32.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.32.input_layernorm": false,
+        "model.layers.32.post_attention_layernorm": false,
+        "model.layers.33.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.33.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.33.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.33.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.33.self_attn.rope": false,
+        "model.layers.33.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.33.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.33.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.33.input_layernorm": false,
+        "model.layers.33.post_attention_layernorm": false,
+        "model.layers.34.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.34.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.34.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.34.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.34.self_attn.rope": false,
+        "model.layers.34.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.34.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.34.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.34.input_layernorm": false,
+        "model.layers.34.post_attention_layernorm": false,
+        "model.layers.35.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.35.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.35.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.35.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.35.self_attn.rope": false,
+        "model.layers.35.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.35.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.35.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.35.input_layernorm": false,
+        "model.layers.35.post_attention_layernorm": false,
+        "model.layers.36.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.36.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.36.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.36.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.36.self_attn.rope": false,
+        "model.layers.36.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.36.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.36.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.36.input_layernorm": false,
+        "model.layers.36.post_attention_layernorm": false,
+        "model.layers.37.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.37.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.37.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.37.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.37.self_attn.rope": false,
+        "model.layers.37.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.37.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.37.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.37.input_layernorm": false,
+        "model.layers.37.post_attention_layernorm": false,
+        "model.layers.38.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.38.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.38.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.38.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.38.self_attn.rope": false,
+        "model.layers.38.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.38.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.38.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.38.input_layernorm": false,
+        "model.layers.38.post_attention_layernorm": false,
+        "model.layers.39.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.39.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.39.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.39.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.39.self_attn.rope": false,
+        "model.layers.39.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.39.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.39.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 5
+        },
+        "model.layers.39.input_layernorm": false,
+        "model.layers.39.post_attention_layernorm": false,
+        "model.norm": false
+    },
+    "residual_multiplier": 0.22,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": null,
+    "rope_theta": 10000000,
+    "tie_word_embeddings": true,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.53.3",
+    "use_cache": true,
+    "vocab_size": 100352
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 100257,
+  "eos_token_id": 100257,
+  "pad_token_id": 100256,
+  "transformers_version": "4.53.3"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:659a2488d8f91e523330e12d184888cf63c8c50ec030eb3b54114c2eda1bd1f7
+size 5354341095

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b79f828134726c1a056547658a7255807aa1c47a0b4d7a83eee3030143137e0
+size 382138735

model.safetensors.index.json

@@ -0,0 +1,932 @@
+{
+    "metadata": {
+        "total_size": 5736374272,
+        "total_parameters": 8380551168
+    },
+    "weight_map": {
+        "model.embed_tokens.biases": "model-00001-of-00002.safetensors",
+        "model.embed_tokens.scales": "model-00001-of-00002.safetensors",
+        "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.k_proj.biases": "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.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.q_proj.biases": "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.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.v_proj.biases": "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.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.k_proj.biases": "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.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.q_proj.biases": "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.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.v_proj.biases": "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.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.k_proj.biases": "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.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.q_proj.biases": "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.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.v_proj.biases": "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.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.k_proj.biases": "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.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.q_proj.biases": "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.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.v_proj.biases": "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.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.k_proj.biases": "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.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.q_proj.biases": "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.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.v_proj.biases": "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.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.k_proj.biases": "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.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.q_proj.biases": "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.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.v_proj.biases": "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.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.22.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.22.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.22.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.23.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.23.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.23.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.23.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.23.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.23.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.24.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.24.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.24.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.24.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.24.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.24.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.25.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.25.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.25.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.25.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.25.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.25.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.26.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.26.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.26.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.26.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.26.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.26.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.27.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.27.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.27.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.27.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.27.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.27.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.28.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.28.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.28.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.28.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.28.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.28.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.28.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.28.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.28.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.28.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.28.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.28.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.28.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.28.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.29.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.29.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.29.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.29.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.29.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.29.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.29.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.29.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.29.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.29.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.29.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.29.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.29.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.29.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.k_proj.biases": "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.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.q_proj.biases": "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.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.v_proj.biases": "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.weight": "model-00001-of-00002.safetensors",
+        "model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.30.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.30.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.30.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.30.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.30.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.30.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.30.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.30.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.30.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.30.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.30.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.30.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.30.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.30.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.31.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.31.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.31.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.31.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.31.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.31.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.31.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.31.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.31.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.31.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.31.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.31.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.31.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.31.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.32.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.32.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.32.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.32.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.32.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.32.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.32.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.32.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.32.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.32.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.32.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.32.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.32.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.32.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.32.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.32.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.32.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.32.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.32.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.32.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.32.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.33.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.33.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.33.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.33.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.33.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.33.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.33.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.33.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.33.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.33.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.33.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.33.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.33.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.33.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.33.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.33.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.33.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.33.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.33.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.34.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.34.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.34.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.34.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.34.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.34.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.34.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.34.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.34.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.34.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.34.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.34.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.34.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.34.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.34.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.34.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.34.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.34.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.34.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.34.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.35.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.35.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.35.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.35.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.35.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.35.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.35.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.35.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.35.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.35.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.35.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.35.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.35.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.35.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.35.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.35.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.35.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.35.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.35.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.35.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.36.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.36.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.36.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.36.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.36.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.36.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.36.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.36.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.36.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.36.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.36.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.36.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.36.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.36.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.36.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.36.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.36.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.36.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.36.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.36.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.36.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.36.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.36.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.37.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.37.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.37.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.37.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.37.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.37.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.37.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.37.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.37.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.37.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.37.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.37.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.37.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.37.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.37.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.37.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.37.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.37.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.37.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.37.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.37.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.37.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.38.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.38.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.38.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.38.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.38.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.38.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.38.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.38.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.38.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.38.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.38.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.38.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.38.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.38.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.38.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.38.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.38.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.38.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.38.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.38.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.38.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.38.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.38.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.39.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.39.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.39.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.39.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.39.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.39.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.39.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.39.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.39.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.39.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.39.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.39.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.39.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.39.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.39.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.39.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.39.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.39.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.39.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.39.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.39.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.39.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.k_proj.biases": "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.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.q_proj.biases": "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.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.v_proj.biases": "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.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.k_proj.biases": "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.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.q_proj.biases": "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.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.v_proj.biases": "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.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.k_proj.biases": "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.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.q_proj.biases": "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.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.v_proj.biases": "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.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.k_proj.biases": "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.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.q_proj.biases": "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.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.v_proj.biases": "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.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.k_proj.biases": "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.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.q_proj.biases": "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.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.v_proj.biases": "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.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.k_proj.biases": "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.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.q_proj.biases": "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.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.v_proj.biases": "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.weight": "model-00001-of-00002.safetensors",
+        "model.norm.weight": "model-00002-of-00002.safetensors"
+    }
+}

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|end_of_text|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|end_of_text|>",
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|pad|>",
+  "padding_side": "left",
+  "tokenizer_class": "TokenizersBackend",
+  "tool_parser_type": "json_tools",
+  "unk_token": "<|unk|>"
+}