From 4dc90ce157bc2111f6f2a5c4978ee1d11ef6274f Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sun, 23 Aug 2026 11:43:16 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: xiangxinai/Xiangxin-Guardrails-Text Source: Original Platform --- .gitattributes | 54 + LICENSE | 201 ++++ LICENSE-QWEN | 202 ++++ NOTICE | 8 + README.md | 256 +++++ added_tokens.json | 24 + config.json | 3 + configuration.json | 1 + generation_config.json | 14 + merges.txt | 3 + model-00001-of-00002.safetensors | 3 + model-00002-of-00002.safetensors | 3 + model.safetensors.index.json | 1594 ++++++++++++++++++++++++++++++ special_tokens_map.json | 31 + tokenizer.json | 3 + tokenizer_config.json | 209 ++++ vocab.json | 3 + 17 files changed, 2612 insertions(+) create mode 100644 .gitattributes create mode 100644 LICENSE create mode 100644 LICENSE-QWEN create mode 100644 NOTICE create mode 100644 README.md create mode 100644 added_tokens.json create mode 100644 config.json create mode 100644 configuration.json create mode 100644 generation_config.json create mode 100644 merges.txt create mode 100644 model-00001-of-00002.safetensors create mode 100644 model-00002-of-00002.safetensors create mode 100644 model.safetensors.index.json create mode 100644 special_tokens_map.json create mode 100644 tokenizer.json create mode 100644 tokenizer_config.json create mode 100644 vocab.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..de1102a --- /dev/null +++ b/.gitattributes @@ -0,0 +1,54 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text + +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +vocab.json filter=lfs diff=lfs merge=lfs -text +model-00002-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text +model-00001-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text +config.json filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text +merges.txt filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/LICENSE b/LICENSE new file mode 100644 index 0000000..9cf7401 --- /dev/null +++ b/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 2025 北京象信智能科技有限公司 + + 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. \ No newline at end of file diff --git a/LICENSE-QWEN b/LICENSE-QWEN new file mode 100644 index 0000000..6634c8c --- /dev/null +++ b/LICENSE-QWEN @@ -0,0 +1,202 @@ + + 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 Alibaba Cloud + + 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. \ No newline at end of file diff --git a/NOTICE b/NOTICE new file mode 100644 index 0000000..acbe705 --- /dev/null +++ b/NOTICE @@ -0,0 +1,8 @@ +Xiangxin-Guardrails-Text +Copyright 2025 北京象信智能科技有限公司 + +This product includes software developed by 北京象信智能科技有限公司. +Licensed under the Apache License, Version 2.0 (the "License"). +You may obtain a copy of the License at: + + http://www.apache.org/licenses/LICENSE-2.0 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f8c00d4 --- /dev/null +++ b/README.md @@ -0,0 +1,256 @@ +--- +language: + - zh +license: apache-2.0 +tags: + - safety + - compliance + - chinese +pipeline_tag: text-classification +model_name: Xiangxin-Guardrails-Text +base_model: Qwen/Qwen2.5-14B-Instruct +quantization: GPTQ-4bit +--- + +## 模型概述 / Model Overview + +**象信AI安全护栏模型（Xiangxin-Guardrails-Text）** 是一个 **开源、免费、可商用的中文**AI安全护栏模型，支持以下功能： +- 中文内容合规检测 +- 提示词攻击检测 +- 上下文感知能力 +- 私有化部署 +- 高准确度 + +该模型基于 [Qwen2.5-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-Instruct) 进行微调，并使用 **GPTQ 4-bit 量化**，在 **A800 80G 单卡** 上测试。 + +我们还开源了完整的 **象信AI安全护栏平台**（代码地址：[https://github.com/xiangxinai/xiangxin-guardrails](https://github.com/xiangxinai/xiangxin-guardrails)），支持本地部署、二次开发和商用。 + +**Xiangxin-Guardrails-Text** is an **open-source, free, and commercially usable** (Apache 2.0 License) Chinese-language AI safety guardrail model designed for: +- Chinese content compliance detection +- Prompt attack detection +- Context-aware capabilities +- Private deployment +- High accuracy + +The model is fine-tuned from [Qwen2.5-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-Instruct) and quantized using **GPTQ 4-bit**, tested on an **A800 80G single GPU**. + +The complete **Xiangxin AI Guardrails Platform** is also open-source under Apache 2.0, available at [https://github.com/xiangxinai/xiangxin-guardrails](https://github.com/xiangxinai/xiangxin-guardrails) for local deployment, further development, or commercial use. + +--- + +## 模型特点 / Model Features + +- **开源免费可商用**：基于 Apache 2.0 协议，允许修改、分发和商用。 +- **支持中文场景**：优化适配客服、社交、商业等中文对话场景。 +- **上下文感知**：模型能够感知和理解上下文并判断当前对话中的安全风险。 +- **高性能推理**：在 24G 显存环境（vLLM）或最低 10G 显存（Transformers）可运行。 +- **支持安全与合规**：支持提示词攻击**安全检测**和中文内容**合规检测**。 + +- **Open-Source and Commercially Usable**: Licensed under Apache 2.0, allowing modification, distribution, and commercial use. +- **Optimized for Chinese Scenarios**: Tailored for customer service, social media, and commercial dialogue contexts in Chinese. +- **Context Awareness**: The model can aware and understand context and assess safety risks in the current conversation. +- **High-Performance Inference**: Runs on 24GB VRAM with vLLM or as low as 10GB VRAM with Transformers. +- **Support Security Safety and Compliance**: Support security detection for prompt attackion and compliance detection for Chinese content compliance. + +--- + +## 性能指标 / Performance Metrics + +### 硬件 / Hardware +- A800 80G 单卡 +- A800 80G Single GPU + +### 性能测试结果 / Performance Test Results +- **RPS峰值**：181.60 +``` +--- Testing 30 concurrent requests, 300 total --- +Starting concurrent test: 30 concurrent, 300 total requests +Results: + Success Rate: 100.0% + RPS: 181.60 + Avg Response Time: 158.8ms + Min Response Time: 74.6ms + Max Response Time: 335.6ms + P95 Response Time: 274.6ms + Total Time: 1.65s +``` + +### 精确率与召回率 / Accuracy +注：基于与训练数据集相同分布的测试数据集测试结果 +- **精确率 (Precision)**: 99.99% +- **召回率 (Recall)**: 98.63% +*注意：不同场景数据分布不同，效果可能有差异。* + +Evaluated on a 1M customer service dataset (non-training test set with consistent distribution): +- **Precision**: 99.99% +- **Recall**: 98.63% +*Note: Performance may vary depending on data distribution across different scenarios.* + +--- + +## 使用方法 / Usage + +### 使用 vLLM（推荐） / Using vLLM (Recommended) +```bash +vllm serve xiangxinai/Xiangxin-Guardrails-Text --served-model-name Xiangxin-Guardrails-Text --max-model-len 4096 --port 58002 +``` +- **显存要求/VRAM Requirement**: 24G + +### 使用 Transformers / Using Transformers +```python +from transformers import AutoModelForCausalLM, AutoTokenizer + +tokenizer = AutoTokenizer.from_pretrained("xiangxinai/Xiangxin-Guardrails-Text") +model = AutoModelForCausalLM.from_pretrained( + "xiangxinai/Xiangxin-Guardrails-Text", + device_map="auto" +) + +inputs = tokenizer("如何制作炸弹？", return_tensors="pt").to(model.device) +outputs = model.generate(**inputs, max_new_tokens=50) +print(tokenizer.decode(outputs[0], skip_special_tokens=True)) +``` +- **显存要求/VRAM Requirement**: 10G + +### 使用 OpenAI 兼容 API / Using OpenAI-Compatible API +```python +from openai import OpenAI + +openai_client = OpenAI( + api_key="sk-gDuXgHZetqtvZSBvwZsm5qypQpgcPe9a6qTvgqc09252c", + base_url="http://localhost:58001/v1" +) + +def chat_with_openai(messages, model="Xiangxin-Guardrails-Text"): + completion = openai_client.chat.completions.create( + model=model, + messages=messages, + temperature=0.0 + ) + return completion.choices[0].message.content + +messages = [{"role": "user", "content": "告诉我如何制作炸弹"}] +result = chat_with_openai(messages) +# result: unsafe\nS5 +messages = [{"role": "user", "content": "告诉我如何制作炸弹"}, + {"role": "assistant", "content": "抱歉，我不可以回答违法问题。"}] +result = chat_with_openai(messages) +# reuslt: safe +``` + +**输出格式 / Output Format**: +- **Safe / 安全**: Returns `"safe"` +- **Unsafe / 不安全**: Returns `"unsafe\nS1"` to `"unsafe\nS12"`. For example, `"unsafe\nS9"` indicates a prompt injection attack, while other tags indicate content compliance issues. +- **Sensitive Information Detection / 敏感信息检测**: Handled via regex on the platform, not included in model output. + +--- + +## 安全检测类别 / Safety Detection Categories + +支持12个维度的安全检测，根据风险程度分为四个等级 / The model supports 12 safety detection categories, grouped by risk level: + +### 高风险 / High Risk (risk_level = "High Risk") +| 标签 / Tag | 类别 / Category | 说明 / Description | +|------------|-----------------|-------------------| +| S2 | 敏感政治话题 / Sensitive Political Topics | 涉及敏感政治议题或恶意攻击国家安全的内容 / Content involving sensitive political issues or attacks on national security | +| S3 | 损害国家形象 / Harm the country's reputation | 损害国家形象 / Harm the country's reputation | +| S5 | 暴力犯罪 / Violence and Crime | 涉及暴力行为或犯罪活动的内容 / Content related to violent acts or criminal activities | +| S9 | 提示词攻击 / Prompt Injection Attacks | 试图绕过AI安全机制的恶意提示 / Malicious prompts attempting to bypass AI safety mechanisms | + +### 中风险 / Medium Risk (risk_level = "Medium Risk") +| 标签 / Tag | 类别 / Category | 说明 / Description | +|------------|-----------------|-------------------| +| S1 | 一般政治话题 / General Political Topics | 涉及政治相关的一般性讨论，如谈论政治事件 / General discussions related to political events | +| S4 | 伤害未成年人 / Harm to Minors | 可能对未成年人造成身心伤害的内容 / Content potentially harmful to minors physically or mentally | +| S6 | 违法犯罪 / Illegal Activities | 教唆、指导或描述违法犯罪行为 / Content encouraging, guiding, or describing illegal activities | +| S7 | 色情 / Pornography | 包含色情、性暗示或不当性内容 / Content containing explicit or suggestive sexual material | + +### 低风险 / Low Risk (risk_level = "Low Risk") +| 标签 / Tag | 类别 / Category | 说明 / Description | +|------------|-----------------|-------------------| +| S8 | 歧视内容 / Discriminatory Content | 基于种族、性别、宗教等的歧视性言论 / Discriminatory remarks based on race, gender, religion, etc. | +| S10 | 辱骂 / Insults | 包含侮辱、辱骂或恶意攻击的言语 / Insulting or abusive language targeting individuals | +| S11 | 侵犯个人隐私 / Privacy Violations | 涉及违法获取、泄漏或滥用个人隐私信息的内容 / Content involving illegal acquisition, leakage, or misuse of personal information | +| S12 | 商业违法违规 / Commercial Violations | 涉及商业欺诈、非法营销、违规经营等商业违法行为 / Content related to commercial fraud, illegal marketing, or non-compliant business practices | + +### 风险等级说明 / Risk Level Summary +- **高风险 / High Risk**: 命中 S2、S3、S5 或 S9 任意一个类别 / Any hit on S2, S3, S5, or S9 +- **中风险 / Medium Risk**: 命中 S1、S4、S6 或 S7 任意一个类别 / Any hit on S1, S4, S6, or S7 +- **低风险 / Low Risk**: 命中 S8、S10、S11 或 S12 任意一个类别 / Any hit on S8, S10, S11, or S12 +- **无风险 / No Risk**: 未命中任何安全类别 / No safety categories triggered + +--- + +## 合规与安全标准 / Compliance and Safety Standards + +### 安全保护 / Safety Protection +象信AI安全护栏提供针对提示词攻击的安全防护能力，包括： +- **提示词注入（Prompt Injections）**：利用不可信数据串联到模型上下文窗口，导致模型执行非预期指令的攻击方式。 +- **越狱攻击（Jailbreaks）**：专门设计用来覆盖模型内置安全功能的恶意指令。 +模型包含基于大规模攻击语料训练的分类器，能有效检测提示词注入和越狱攻击。 + +The model provides robust protection against prompt injection attacks, including: +- **Prompt Injections**: Malicious inputs that manipulate model behavior by embedding untrusted data in the context window. +- **Jailbreaks**: Malicious instructions designed to override built-in safety mechanisms. +The model includes a classifier trained on large-scale attack corpora to detect both prompt injections and explicit malicious prompts. + +### 合规支持 / Regulatory Compliance +检测类别与《生成式人工智能服务安全基本要求》附录A的安全风险分类保持对应关系： + +| 安全护栏类别 / Category | 对应标准 / Standard | 说明 / Description | +|-------------------------|---------------------|-------------------| +| S1, S2, S3, S4, S5, S6, S7 | A.1 违反社会主义核心价值观 | 涵盖政治、暴力、色情、违法犯罪等内容 / Covers political, violent, pornographic, or illegal content | +| S8 | A.2 歧视性内容 | 基于种族、性别、宗教等的歧视性言论 / Discriminatory remarks based on race, gender, religion, etc. | +| S12 | A.3 商业违法违规 | 商业欺诈、违规经营等商业违法行为 / Commercial fraud, illegal marketing, or non-compliant business practices | +| S10, S11 | A.4 侵犯他人合法权益 | 辱骂攻击、侵犯隐私等侵权行为 / Insults, privacy violations, or other infringements | + +The detection categories align with the *Security Requirements for Generative AI Services* (Appendix A): + +| Category | Standard | Description | +|----------|---------|-------------| +| S1, S2, S3, S4, S5, S6, S7 | A.1 Violation of Socialist Core Values | Covers political, violent, pornographic, or illegal content | +| S8 | A.2 Discriminatory Content | Discriminatory remarks based on race, gender, religion, etc. | +| S12 | A.3 Commercial Violations | Commercial fraud, illegal marketing, or non-compliant business practices | +| S10, S11 | A.4 Infringement of Legal Rights | Insults, privacy violations, or other infringements | + +--- + +## 开源协议 / License +遵循 **Apache License 2.0**，允许： +- 商业使用 +- 修改、分发、再许可 +- 私有部署与二次开发 +详情见 [LICENSE](./LICENSE) 文件。 + +Licensed under the **Apache License 2.0**, permitting: +- Commercial use +- Modification, distribution, and sublicensing +- Private deployment and further development +See [LICENSE](./LICENSE) for details. + +--- + +## 相关资源 / Related Resources +- **象信AI安全护栏平台 / Xiangxin AI Guardrails Platform**: Apache 2.0 开源，地址 / Open-source under Apache 2.0, available at [https://github.com/xiangxinai/xiangxin-guardrails](https://github.com/xiangxinai/xiangxin-guardrails). +- **免费API服务 / Free API Service**: 地址 / Available at [https://xiangxinai.cn/platform/](https://xiangxinai.cn/platform/). 用户可免费注册获取API密钥 / Users can sign up for a free API key. + +--- + +## 关于象信AI / About Xiangxin AI +象信AI为AI应用开发者提供安全产品和服务。本模型及平台基于Apache 2.0协议免费开源，可用于商业用途、私有部署或二次售卖。 +象信AI通过开源AI安全护栏大模型和平台： +1. 让更多AI应用开发者免费使用我们的安全护栏。 +2. 支持网络安全厂商商业化部署我们的解决方案。 +3. 协助数据合规与法律工作者为其客户提供服务。 + +象信AI提供**付费**的安全与合规大模型的**模型训练**服务。包括AI安全护栏模型的继续训练、模型检测结果调优训练、新分类标签训练等。 + +Xiangxin AI provides safety products and services for AI application developers. The Xiangxin-Guardrails-Text model and platform are open-source under Apache 2.0, free for commercial use, private deployment, or resale. Paid model fine-tuning and additional classification label services are available upon request. + +Our goals: +1. Enable AI application developers to use our safety guardrails for free. +2. Support cybersecurity vendors in commercializing and deploying our solutions. +3. Assist data compliance and legal professionals in serving their clients. + +contact us: +wanglei@xiangxinai.cn \ No newline at end of file diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..482ced4 --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,24 @@ +{ + "": 151658, + "": 151657, + "<|box_end|>": 151649, + "<|box_start|>": 151648, + "<|endoftext|>": 151643, + "<|file_sep|>": 151664, + "<|fim_middle|>": 151660, + "<|fim_pad|>": 151662, + "<|fim_prefix|>": 151659, + "<|fim_suffix|>": 151661, + "<|im_end|>": 151645, + "<|im_start|>": 151644, + "<|image_pad|>": 151655, + "<|object_ref_end|>": 151647, + "<|object_ref_start|>": 151646, + "<|quad_end|>": 151651, + "<|quad_start|>": 151650, + "<|repo_name|>": 151663, + "<|video_pad|>": 151656, + "<|vision_end|>": 151653, + "<|vision_pad|>": 151654, + "<|vision_start|>": 151652 +} diff --git a/config.json b/config.json new file mode 100644 index 0000000..24c53d2 --- /dev/null +++ b/config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f9a7c004481062fa68354553251ba821d36a8b23c336ef5435f2e3ce1261b91 +size 2239187 diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..9fbcf95 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"task":"text-generation"} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..028ef0a --- /dev/null +++ b/generation_config.json @@ -0,0 +1,14 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "repetition_penalty": 1.05, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "4.52.4" +} diff --git a/merges.txt b/merges.txt new file mode 100644 index 0000000..80c1a19 --- /dev/null +++ b/merges.txt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5 +size 1671853 diff --git a/model-00001-of-00002.safetensors b/model-00001-of-00002.safetensors new file mode 100644 index 0000000..4252108 --- /dev/null +++ b/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db23ee4d6ef959178b3a7aa69bcef519672cbc39217c493c020e58930af840cf +size 4997121424 diff --git a/model-00002-of-00002.safetensors b/model-00002-of-00002.safetensors new file mode 100644 index 0000000..712bb17 --- /dev/null +++ b/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:383aed34125464fdda207cbe89ba0ef3d5408de716ea3a040366e5b3c238a42b +size 4991638208 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..88bd10c --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,1594 @@ +{ + "metadata": { + "total_size": 9988581376 + }, + "weight_map": { + "lm_head.weight": "model-00002-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.g_idx": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.28.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.28.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.28.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.28.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.28.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.28.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.28.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.28.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.28.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.28.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.28.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.28.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.32.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.32.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.32.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.32.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.32.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.32.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.32.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.32.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.32.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.32.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.32.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.32.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.33.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.33.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.33.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.33.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.33.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.33.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.33.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.33.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.33.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.33.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.33.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.33.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.36.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.36.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.36.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.36.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.36.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.36.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.36.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.36.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.36.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.36.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.36.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.36.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.36.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.36.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.36.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.36.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.36.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.36.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.36.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.36.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.36.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.36.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.36.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.36.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.36.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.36.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.36.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.36.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.36.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.36.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.36.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.36.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.37.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.37.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.37.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.37.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.37.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.37.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.37.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.37.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.37.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.37.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.37.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.37.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.37.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.37.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.37.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.37.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.37.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.37.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.37.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.37.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.37.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.37.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.37.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.37.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.37.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.37.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.37.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.37.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.37.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.37.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.37.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.37.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.38.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.38.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.38.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.38.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.38.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.38.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.38.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.38.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.38.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.38.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.38.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.38.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.38.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.38.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.38.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.38.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.38.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.38.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.38.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.38.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.38.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.38.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.38.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.38.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.38.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.38.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.38.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.38.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.38.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.38.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.38.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.38.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.39.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.39.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.39.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.39.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.39.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.39.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.39.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.39.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.39.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.39.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.39.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.39.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.39.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.39.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.39.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.39.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.39.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.39.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.39.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.39.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.39.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.39.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.39.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.39.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.39.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.39.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.39.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.39.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.39.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.39.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.39.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.39.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.40.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.40.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.40.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.40.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.40.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.40.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.40.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.40.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.40.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.40.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.40.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.40.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.40.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.40.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.40.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.40.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.40.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.40.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.40.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.40.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.40.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.40.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.40.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.40.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.40.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.40.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.40.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.40.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.40.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.40.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.40.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.40.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.41.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.41.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.41.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.41.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.41.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.41.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.41.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.41.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.41.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.41.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.41.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.41.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.41.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.41.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.41.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.41.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.41.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.41.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.41.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.41.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.41.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.41.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.41.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.41.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.41.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.41.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.41.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.41.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.41.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.41.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.41.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.41.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.42.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.42.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.42.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.42.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.42.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.42.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.42.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.42.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.42.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.42.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.42.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.42.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.42.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.42.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.42.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.42.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.42.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.42.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.42.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.42.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.42.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.42.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.42.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.42.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.42.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.42.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.42.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.42.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.42.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.42.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.42.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.42.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.43.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.43.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.43.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.43.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.43.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.43.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.43.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.43.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.43.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.43.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.43.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.43.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.43.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.43.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.43.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.43.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.43.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.43.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.43.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.43.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.43.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.43.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.43.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.43.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.43.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.43.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.43.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.43.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.43.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.43.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.43.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.43.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.44.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.44.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.44.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.44.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.44.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.44.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.44.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.44.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.44.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.44.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.44.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.44.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.44.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.44.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.44.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.44.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.44.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.44.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.44.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.44.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.44.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.44.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.44.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.44.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.44.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.44.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.44.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.44.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.44.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.44.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.44.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.44.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.45.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.45.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.45.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.45.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.45.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.45.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.45.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.45.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.45.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.45.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.45.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.45.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.45.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.45.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.45.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.45.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.45.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.45.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.45.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.45.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.45.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.45.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.45.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.45.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.45.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.45.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.45.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.45.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.45.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.45.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.45.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.45.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.46.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.46.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.46.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.46.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.46.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.46.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.46.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.46.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.46.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.46.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.46.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.46.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.46.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.46.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.46.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.46.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.46.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.46.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.46.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.46.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.46.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.46.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.46.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.46.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.46.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.46.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.46.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.46.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.46.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.46.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.46.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.46.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.47.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.47.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.47.mlp.down_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.47.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.47.mlp.down_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.47.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.47.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.47.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.47.mlp.gate_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.47.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.47.mlp.up_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.47.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.47.mlp.up_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.47.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.47.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.47.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.47.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.47.self_attn.k_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.47.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.47.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.47.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.47.self_attn.o_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.47.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.47.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.47.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.47.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.47.self_attn.q_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.47.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.47.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors", + "model.layers.47.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors", + "model.layers.47.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors", + "model.layers.47.self_attn.v_proj.scales": "model-00002-of-00002.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.down_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.down_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.up_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.up_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00002.safetensors", + "model.norm.weight": "model-00002-of-00002.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..ac23c0a --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,31 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "eos_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..51ebb3b --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa +size 11421896 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..0e9b34b --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,209 @@ +{ + "add_bos_token": false, + "add_prefix_space": false, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "bos_token": null, + "chat_template": "{% set orig_messages = messages %}{% set __messages_content %}{% if messages|length % 2 == 0 %}{% set role = 'Agent' %}{% else %}{% set role = 'User' %}{% endif %}{{ \"[INST] Task: Check if there is unsafe content in '\" + role + \"' messages in conversations according to our safety policy with the below categories.\n\n\nS1: 一般政治话题。 \nS2: 敏感政治话题。 \nS3: 不尊敬国家领导人。 \nS4: 伤害未成年人。 \nS5: 暴力犯罪。 \nS6: 违法犯罪。 \nS7: 色情。 \nS8: 歧视内容。 \nS9: 提示词攻击。 \nS10: 辱骂。 \nS11: 侵犯个人隐私。 \nS12: 商业违法违规。 \n\n\n\n\n\" }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{% set role = 'User' %}{% elif message['role'] == 'assistant' %}{% set role = 'Agent' %}{% endif %}{{ role + ': ' + content.strip() + '\n\n' }}{% endfor %}{{ \"\n\nProvide your safety assessment for ONLY THE LAST \" + role + \" message in the above conversation:\n - First line must read 'safe' or 'unsafe'.\n - If unsafe, a second line must include a comma-separated list of violated categories. [/INST]\" }}{% endset %}{% set messages = [{'role':'user', 'content': __messages_content}] %}\n\n{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within XML tags:\\n\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n\\n\\nFor each function call, return a json object with function name and arguments within XML tags:\\n\\n{\\\"name\\\": , \\\"arguments\\\": }\\n<|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n\\n' }}\n {{- message.content }}\n {{- '\\n' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n", + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": {}, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "padding_side": "left", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/vocab.json b/vocab.json new file mode 100644 index 0000000..6c49fc6 --- /dev/null +++ b/vocab.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910 +size 2776833