Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,94 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+inference/.venv/bin/python filter=lfs diff=lfs merge=lfs -text
+inference/.venv/bin/python3 filter=lfs diff=lfs merge=lfs -text
+inference/.venv/bin/python3.10 filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib/python3.10/site-packages/numpy/_core/_multiarray_umath.cpython-310-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib/python3.10/site-packages/numpy/_core/_simd.cpython-310-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib/python3.10/site-packages/numpy/random/_generator.cpython-310-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib/python3.10/site-packages/numpy.libs/libgfortran-040039e1-0352e75f.so.5.0.0 filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib/python3.10/site-packages/numpy.libs/libscipy_openblas64_-6bb31eeb.so filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib/python3.10/site-packages/nvidia/cublas/lib/libcublas.so.12 filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib/python3.10/site-packages/nvidia/cublas/lib/libcublasLt.so.12 filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib/python3.10/site-packages/nvidia/cuda_cupti/lib/libcheckpoint.so filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib/python3.10/site-packages/nvidia/cuda_cupti/lib/libcupti.so.12 filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib/python3.10/site-packages/nvidia/cuda_cupti/lib/libnvperf_host.so filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib/python3.10/site-packages/nvidia/cuda_cupti/lib/libnvperf_target.so filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib/python3.10/site-packages/nvidia/cuda_nvrtc/lib/libnvrtc-builtins.so.12.1 filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib/python3.10/site-packages/nvidia/cuda_nvrtc/lib/libnvrtc.so.12 filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib/python3.10/site-packages/nvidia/cudnn/lib/libcudnn_adv.so.9 filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib/python3.10/site-packages/nvidia/cudnn/lib/libcudnn_cnn.so.9 filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib/python3.10/site-packages/nvidia/cudnn/lib/libcudnn_engines_precompiled.so.9 filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib/python3.10/site-packages/nvidia/cudnn/lib/libcudnn_engines_runtime_compiled.so.9 filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib/python3.10/site-packages/nvidia/cudnn/lib/libcudnn_graph.so.9 filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib/python3.10/site-packages/nvidia/cudnn/lib/libcudnn_heuristic.so.9 filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib/python3.10/site-packages/nvidia/cudnn/lib/libcudnn_ops.so.9 filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib/python3.10/site-packages/nvidia/cufft/lib/libcufft.so.11 filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib/python3.10/site-packages/nvidia/cufft/lib/libcufftw.so.11 filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib/python3.10/site-packages/nvidia/curand/lib/libcurand.so.10 filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib/python3.10/site-packages/nvidia/cusolver/lib/libcusolver.so.11 filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib/python3.10/site-packages/nvidia/cusolver/lib/libcusolverMg.so.11 filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib/python3.10/site-packages/nvidia/cusparse/lib/libcusparse.so.12 filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib/python3.10/site-packages/nvidia/nccl/lib/libnccl.so.2 filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib/python3.10/site-packages/nvidia/nvjitlink/lib/libnvJitLink.so.12 filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib/python3.10/site-packages/regex/_regex.cpython-310-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib/python3.10/site-packages/safetensors/_safetensors_rust.cpython-310-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib/python3.10/site-packages/tokenizers/tokenizers.cpython-310-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib/python3.10/site-packages/torch/bin/protoc filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib/python3.10/site-packages/torch/bin/protoc-3.13.0.0 filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib/python3.10/site-packages/torch/lib/libc10.so filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib/python3.10/site-packages/torch/lib/libcusparseLt-f80c68d1.so.0 filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib/python3.10/site-packages/torch/lib/libtorch_cpu.so filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib/python3.10/site-packages/torch/lib/libtorch_cuda.so filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib/python3.10/site-packages/torch/lib/libtorch_cuda_linalg.so filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib/python3.10/site-packages/torch/lib/libtorch_python.so filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib/python3.10/site-packages/triton/_C/libproton.so filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib/python3.10/site-packages/triton/_C/libtriton.so filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib/python3.10/site-packages/triton/backends/nvidia/bin/nvdisasm filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib/python3.10/site-packages/triton/backends/nvidia/bin/ptxas filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib/python3.10/site-packages/yaml/_yaml.cpython-310-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib64/python3.10/site-packages/numpy/_core/_multiarray_umath.cpython-310-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib64/python3.10/site-packages/numpy/_core/_simd.cpython-310-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib64/python3.10/site-packages/numpy/random/_generator.cpython-310-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib64/python3.10/site-packages/numpy.libs/libgfortran-040039e1-0352e75f.so.5.0.0 filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib64/python3.10/site-packages/numpy.libs/libscipy_openblas64_-6bb31eeb.so filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib64/python3.10/site-packages/nvidia/cublas/lib/libcublas.so.12 filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib64/python3.10/site-packages/nvidia/cublas/lib/libcublasLt.so.12 filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib64/python3.10/site-packages/nvidia/cuda_cupti/lib/libcheckpoint.so filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib64/python3.10/site-packages/nvidia/cuda_cupti/lib/libcupti.so.12 filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib64/python3.10/site-packages/nvidia/cuda_cupti/lib/libnvperf_host.so filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib64/python3.10/site-packages/nvidia/cuda_cupti/lib/libnvperf_target.so filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib64/python3.10/site-packages/nvidia/cuda_nvrtc/lib/libnvrtc-builtins.so.12.1 filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib64/python3.10/site-packages/nvidia/cuda_nvrtc/lib/libnvrtc.so.12 filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib64/python3.10/site-packages/nvidia/cudnn/lib/libcudnn_adv.so.9 filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib64/python3.10/site-packages/nvidia/cudnn/lib/libcudnn_cnn.so.9 filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib64/python3.10/site-packages/nvidia/cudnn/lib/libcudnn_engines_precompiled.so.9 filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib64/python3.10/site-packages/nvidia/cudnn/lib/libcudnn_engines_runtime_compiled.so.9 filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib64/python3.10/site-packages/nvidia/cudnn/lib/libcudnn_graph.so.9 filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib64/python3.10/site-packages/nvidia/cudnn/lib/libcudnn_heuristic.so.9 filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib64/python3.10/site-packages/nvidia/cudnn/lib/libcudnn_ops.so.9 filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib64/python3.10/site-packages/nvidia/cufft/lib/libcufft.so.11 filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib64/python3.10/site-packages/nvidia/cufft/lib/libcufftw.so.11 filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib64/python3.10/site-packages/nvidia/curand/lib/libcurand.so.10 filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib64/python3.10/site-packages/nvidia/cusolver/lib/libcusolver.so.11 filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib64/python3.10/site-packages/nvidia/cusolver/lib/libcusolverMg.so.11 filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib64/python3.10/site-packages/nvidia/cusparse/lib/libcusparse.so.12 filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib64/python3.10/site-packages/nvidia/nccl/lib/libnccl.so.2 filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib64/python3.10/site-packages/nvidia/nvjitlink/lib/libnvJitLink.so.12 filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib64/python3.10/site-packages/regex/_regex.cpython-310-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib64/python3.10/site-packages/safetensors/_safetensors_rust.cpython-310-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib64/python3.10/site-packages/tokenizers/tokenizers.cpython-310-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib64/python3.10/site-packages/torch/bin/protoc filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib64/python3.10/site-packages/torch/bin/protoc-3.13.0.0 filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib64/python3.10/site-packages/torch/lib/libc10.so filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib64/python3.10/site-packages/torch/lib/libcusparseLt-f80c68d1.so.0 filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib64/python3.10/site-packages/torch/lib/libtorch_cpu.so filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib64/python3.10/site-packages/torch/lib/libtorch_cuda.so filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib64/python3.10/site-packages/torch/lib/libtorch_cuda_linalg.so filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib64/python3.10/site-packages/torch/lib/libtorch_python.so filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib64/python3.10/site-packages/triton/_C/libproton.so filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib64/python3.10/site-packages/triton/_C/libtriton.so filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib64/python3.10/site-packages/triton/backends/nvidia/bin/nvdisasm filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib64/python3.10/site-packages/triton/backends/nvidia/bin/ptxas filter=lfs diff=lfs merge=lfs -text
+inference/.venv/lib64/python3.10/site-packages/yaml/_yaml.cpython-310-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text

LICENSE-CODE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 DeepSeek
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

LICENSE-MODEL

@@ -0,0 +1,91 @@
+DEEPSEEK LICENSE AGREEMENT
+
+Version 1.0, 23 October 2023
+
+Copyright (c) 2023 DeepSeek
+
+Section I: PREAMBLE 
+
+Large generative models are being widely adopted and used, and have the potential to transform the way individuals conceive and benefit from AI or ML technologies. 
+
+Notwithstanding the current and potential benefits that these artifacts can bring to society at large, there are also concerns about potential misuses of them, either due to their technical limitations or ethical considerations. 
+
+In short, this license strives for both the open and responsible downstream use of the accompanying model. When it comes to the open character, we took inspiration from open source permissive licenses regarding the grant of IP rights. Referring to the downstream responsible use, we added use-based restrictions not permitting the use of the model in very specific scenarios, in order for the licensor to be able to enforce the license in case potential misuses of the Model may occur. At the same time, we strive to promote open and responsible research on generative models for content generation. 
+
+Even though downstream derivative versions of the model could be released under different licensing terms, the latter will always have to include - at minimum - the same use-based restrictions as the ones in the original license (this license). We believe in the intersection between open and responsible AI development; thus, this agreement aims to strike a balance between both in order to enable responsible open-science in the field of AI. 
+
+This License governs the use of the model (and its derivatives) and is informed by the model card associated with the model. 
+
+NOW THEREFORE, You and DeepSeek agree as follows: 
+
+1. Definitions 
+"License" means the terms and conditions for use, reproduction, and Distribution as defined in this document. 
+"Data" means a collection of information and/or content extracted from the dataset used with the Model, including to train, pretrain, or otherwise evaluate the Model. The Data is not licensed under this License.
+"Output" means the results of operating a Model as embodied in informational content resulting therefrom. 
+"Model" means any accompanying machine-learning based assemblies (including checkpoints), consisting of learnt weights, parameters (including optimizer states), corresponding to the model architecture as embodied in the Complementary Material, that have been trained or tuned, in whole or in part on the Data, using the Complementary Material. 
+"Derivatives of the Model" means all modifications to the Model, works based on the Model, or any other model which is created or initialized by transfer of patterns of the weights, parameters, activations or output of the Model, to the other model, in order to cause the other model to perform similarly to the Model, including - but not limited to - distillation methods entailing the use of intermediate data representations or methods based on the generation of synthetic data by the Model for training the other model. 
+"Complementary Material" means the accompanying source code and scripts used to define, run, load, benchmark or evaluate the Model, and used to prepare data for training or evaluation, if any. This includes any accompanying documentation, tutorials, examples, etc, if any. 
+"Distribution" means any transmission, reproduction, publication or other sharing of the Model or Derivatives of the Model to a third party, including providing the Model as a hosted service made available by electronic or other remote means - e.g. API-based or web access. 
+"DeepSeek" (or "we") means Beijing DeepSeek Artificial Intelligence Fundamental Technology Research Co., Ltd., Hangzhou DeepSeek Artificial Intelligence Fundamental Technology Research Co., Ltd. and/or any of their affiliates.
+"You" (or "Your") means an individual or Legal Entity exercising permissions granted by this License and/or making use of the Model for whichever purpose and in any field of use, including usage of the Model in an end-use application - e.g. chatbot, translator, etc. 
+"Third Parties" means individuals or legal entities that are not under common control with DeepSeek or You. 
+
+Section II: INTELLECTUAL PROPERTY RIGHTS 
+
+Both copyright and patent grants apply to the Model, Derivatives of the Model and Complementary Material. The Model and Derivatives of the Model are subject to additional terms as described in Section III. 
+
+2. Grant of Copyright License. Subject to the terms and conditions of this License, DeepSeek hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable copyright license to reproduce, prepare, publicly display, publicly perform, sublicense, and distribute the Complementary Material, the Model, and Derivatives of the Model. 
+
+3. Grant of Patent License. Subject to the terms and conditions of this License and where and as applicable, DeepSeek hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable (except as stated in this paragraph) patent license to make, have made, use, offer to sell, sell, import, and otherwise transfer the Model and the Complementary Material, where such license applies only to those patent claims licensable by DeepSeek that are necessarily infringed by its contribution(s). If You institute patent litigation against any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Model and/or Complementary Material constitutes direct or contributory patent infringement, then any patent licenses granted to You under this License for the Model and/or works shall terminate as of the date such litigation is asserted or filed. 
+
+
+Section III: CONDITIONS OF USAGE, DISTRIBUTION AND REDISTRIBUTION
+
+4. Distribution and Redistribution. You may host for Third Party remote access purposes (e.g. software-as-a-service), reproduce and distribute copies of the Model or Derivatives of the Model thereof in any medium, with or without modifications, provided that You meet the following conditions: 
+a. Use-based restrictions as referenced in paragraph 5 MUST be included as an enforceable provision by You in any type of legal agreement (e.g. a license) governing the use and/or distribution of the Model or Derivatives of the Model, and You shall give notice to subsequent users You Distribute to, that the Model or Derivatives of the Model are subject to paragraph 5. This provision does not apply to the use of Complementary Material. 
+b. You must give any Third Party recipients of the Model or Derivatives of the Model a copy of this License; 
+c. You must cause any modified files to carry prominent notices stating that You changed the files; 
+d. You must retain all copyright, patent, trademark, and attribution notices excluding those notices that do not pertain to any part of the Model, Derivatives of the Model. 
+e. You may add Your own copyright statement to Your modifications and may provide additional or different license terms and conditions - respecting paragraph 4.a. – for use, reproduction, or Distribution of Your modifications, or for any such Derivatives of the Model as a whole, provided Your use, reproduction, and Distribution of the Model otherwise complies with the conditions stated in this License. 
+
+5. Use-based restrictions. The restrictions set forth in Attachment A are considered Use-based restrictions. Therefore You cannot use the Model and the Derivatives of the Model for the specified restricted uses. You may use the Model subject to this License, including only for lawful purposes and in accordance with the License. Use may include creating any content with, finetuning, updating, running, training, evaluating and/or reparametrizing the Model. You shall require all of Your users who use the Model or a Derivative of the Model to comply with the terms of this paragraph (paragraph 5). 
+
+6. The Output You Generate. Except as set forth herein, DeepSeek claims no rights in the Output You generate using the Model. You are accountable for the Output you generate and its subsequent uses. No use of the output can contravene any provision as stated in the License.
+
+Section IV: OTHER PROVISIONS 
+
+7. Updates and Runtime Restrictions. To the maximum extent permitted by law, DeepSeek reserves the right to restrict (remotely or otherwise) usage of the Model in violation of this License. 
+
+8. Trademarks and related. Nothing in this License permits You to make use of DeepSeek’ trademarks, trade names, logos or to otherwise suggest endorsement or misrepresent the relationship between the parties; and any rights not expressly granted herein are reserved by DeepSeek. 
+
+9. Personal information, IP rights and related. This Model may contain personal information and works with IP rights. You commit to complying with applicable laws and regulations in the handling of personal information and the use of such works. Please note that DeepSeek's license granted to you to use the Model does not imply that you have obtained a legitimate basis for processing the related information or works. As an independent personal information processor and IP rights user, you need to ensure full compliance with relevant legal and regulatory requirements when handling personal information and works with IP rights that may be contained in the Model, and are willing to assume solely any risks and consequences that may arise from that.
+
+10. Disclaimer of Warranty. Unless required by applicable law or agreed to in writing, DeepSeek provides the Model and the Complementary Material 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 Model, Derivatives of the Model, and the Complementary Material and assume any risks associated with Your exercise of permissions under this License. 
+
+11. 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 DeepSeek 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 Model and the Complementary Material (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 DeepSeek has been advised of the possibility of such damages. 
+
+12. Accepting Warranty or Additional Liability. While redistributing the Model, Derivatives of the Model and the Complementary Material 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 DeepSeek, and only if You agree to indemnify, defend, and hold DeepSeek harmless for any liability incurred by, or claims asserted against, DeepSeek by reason of your accepting any such warranty or additional liability. 
+
+13. If any provision of this License is held to be invalid, illegal or unenforceable, the remaining provisions shall be unaffected thereby and remain valid as if such provision had not been set forth herein.
+
+14. Governing Law and Jurisdiction. This agreement will be governed and construed under PRC laws without regard to choice of law principles, and the UN Convention on Contracts for the International Sale of Goods does not apply to this agreement. The courts located in the domicile of Hangzhou DeepSeek Artificial Intelligence Fundamental Technology Research Co., Ltd. shall have exclusive jurisdiction of any dispute arising out of this agreement.
+
+END OF TERMS AND CONDITIONS
+
+Attachment A 
+
+Use Restrictions
+
+You agree not to use the Model or Derivatives of the Model:
+
+-	In any way that violates any applicable national or international law or regulation or infringes upon the lawful rights and interests of any third party; 
+-	For military use in any way;
+-	For the purpose of exploiting, harming or attempting to exploit or harm minors in any way; 
+-	To generate or disseminate verifiably false information and/or content with the purpose of harming others; 
+-	To generate or disseminate inappropriate content subject to applicable regulatory requirements;
+-	To generate or disseminate personal identifiable information without due authorization or for unreasonable use; 
+-	To defame, disparage or otherwise harass others; 
+-	For fully automated decision making that adversely impacts an individual’s legal rights or otherwise creates or modifies a binding, enforceable obligation; 
+-	For any use intended to or which has the effect of discriminating against or harming individuals or groups based on online or offline social behavior or known or predicted personal or personality characteristics; 
+-	To exploit any of the vulnerabilities of a specific group of persons based on their age, social, physical or mental characteristics, in order to materially distort the behavior of a person pertaining to that group in a manner that causes or is likely to cause that person or another person physical or psychological harm; 
+-	For any use intended to or which has the effect of discriminating against individuals or groups based on legally protected characteristics or categories.

README.md

@@ -0,0 +1,336 @@
+<!-- markdownlint-disable first-line-h1 -->
+<!-- markdownlint-disable html -->
+<!-- markdownlint-disable no-duplicate-header -->
+
+<div align="center">
+  <img src="https://github.com/deepseek-ai/DeepSeek-V2/blob/main/figures/logo.svg?raw=true" width="60%" alt="DeepSeek-V3" />
+</div>
+<hr>
+<div align="center" style="line-height: 1;">
+  <a href="https://www.deepseek.com/" target="_blank" style="margin: 2px;">
+    <img alt="Homepage" src="https://github.com/deepseek-ai/DeepSeek-V2/blob/main/figures/badge.svg?raw=true" style="display: inline-block; vertical-align: middle;"/>
+  </a>
+  <a href="https://chat.deepseek.com/" target="_blank" style="margin: 2px;">
+    <img alt="Chat" src="https://img.shields.io/badge/🤖%20Chat-DeepSeek%20V3-536af5?color=536af5&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
+  </a>
+  <a href="https://huggingface.co/deepseek-ai" target="_blank" style="margin: 2px;">
+    <img alt="Hugging Face" src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-DeepSeek%20AI-ffc107?color=ffc107&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
+  </a>
+</div>
+
+<div align="center" style="line-height: 1;">
+  <a href="https://discord.gg/Tc7c45Zzu5" target="_blank" style="margin: 2px;">
+    <img alt="Discord" src="https://img.shields.io/badge/Discord-DeepSeek%20AI-7289da?logo=discord&logoColor=white&color=7289da" style="display: inline-block; vertical-align: middle;"/>
+  </a>
+  <a href="https://github.com/deepseek-ai/DeepSeek-V2/blob/main/figures/qr.jpeg?raw=true" target="_blank" style="margin: 2px;">
+    <img alt="Wechat" src="https://img.shields.io/badge/WeChat-DeepSeek%20AI-brightgreen?logo=wechat&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
+  </a>
+  <a href="https://twitter.com/deepseek_ai" target="_blank" style="margin: 2px;">
+    <img alt="Twitter Follow" src="https://img.shields.io/badge/Twitter-deepseek_ai-white?logo=x&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
+  </a>
+</div>
+
+<div align="center" style="line-height: 1;">
+  <a href="https://github.com/deepseek-ai/DeepSeek-V3/blob/main/LICENSE-CODE" style="margin: 2px;">
+    <img alt="Code License" src="https://img.shields.io/badge/Code_License-MIT-f5de53?&color=f5de53" style="display: inline-block; vertical-align: middle;"/>
+  </a>
+  <a href="https://github.com/deepseek-ai/DeepSeek-V3/blob/main/LICENSE-MODEL" style="margin: 2px;">
+    <img alt="Model License" src="https://img.shields.io/badge/Model_License-Model_Agreement-f5de53?&color=f5de53" style="display: inline-block; vertical-align: middle;"/>
+  </a>
+</div>
+
+
+<p align="center">
+  <a href="https://github.com/deepseek-ai/DeepSeek-V3/blob/main/DeepSeek_V3.pdf"><b>Paper Link</b>👁️</a>
+</p>
+
+
+## 1. Introduction
+
+We present DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token. 
+To achieve efficient inference and cost-effective training, DeepSeek-V3 adopts Multi-head Latent Attention (MLA) and DeepSeekMoE architectures, which were thoroughly validated in DeepSeek-V2. 
+Furthermore, DeepSeek-V3 pioneers an auxiliary-loss-free strategy for load balancing and sets a multi-token prediction training objective for stronger performance. 
+We pre-train DeepSeek-V3 on 14.8 trillion diverse and high-quality tokens, followed by Supervised Fine-Tuning and Reinforcement Learning stages to fully harness its capabilities. 
+Comprehensive evaluations reveal that DeepSeek-V3 outperforms other open-source models and achieves performance comparable to leading closed-source models.
+Despite its excellent performance, DeepSeek-V3 requires only 2.788M H800 GPU hours for its full training.
+In addition, its training process is remarkably stable. 
+Throughout the entire training process, we did not experience any irrecoverable loss spikes or perform any rollbacks. 
+<p align="center">
+  <img width="80%" src="figures/benchmark.png">
+</p>
+
+## 2. Model Summary
+
+---
+
+**Architecture: Innovative Load Balancing Strategy and Training Objective**
+
+- On top of the efficient architecture of DeepSeek-V2, we pioneer an auxiliary-loss-free strategy for load balancing, which minimizes the performance degradation that arises from encouraging load balancing.
+-  We investigate a Multi-Token Prediction (MTP) objective and prove it beneficial to model performance. 
+    It can also be used for speculative decoding for inference acceleration. 
+
+---
+
+**Pre-Training: Towards Ultimate Training Efficiency**
+
+- We design an FP8 mixed precision training framework and, for the first time, validate the feasibility and effectiveness of FP8 training on an extremely large-scale model.  
+- Through co-design of algorithms, frameworks, and hardware, we overcome the communication bottleneck in cross-node MoE training, nearly achieving full computation-communication overlap.  
+  This significantly enhances our training efficiency and reduces the training costs, enabling us to further scale up the model size without additional overhead.  
+- At an economical cost of only 2.664M H800 GPU hours, we complete the pre-training of DeepSeek-V3 on 14.8T tokens, producing the currently strongest open-source base model. The subsequent training stages after pre-training require only 0.1M GPU hours.
+
+---
+
+**Post-Training: Knowledge Distillation from DeepSeek-R1**
+
+-   We introduce an innovative methodology to distill reasoning capabilities from the long-Chain-of-Thought (CoT) model, specifically from one of the DeepSeek R1 series models, into standard LLMs, particularly DeepSeek-V3. Our pipeline elegantly incorporates the verification and reflection patterns of R1 into DeepSeek-V3 and notably improves its reasoning performance. Meanwhile, we also maintain a control over the output style and length of DeepSeek-V3.
+
+---
+
+
+## 3. Model Downloads
+
+<div align="center">
+
+| **Model** | **#Total Params** | **#Activated Params** | **Context Length** | **Download** |
+| :------------: | :------------: | :------------: | :------------: | :------------: |
+| DeepSeek-V3-Base | 671B | 37B | 128K   | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-V3-Base)   |
+| DeepSeek-V3   | 671B | 37B |  128K   | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-V3)   |
+
+</div>
+
+**NOTE: The total size of DeepSeek-V3 models on HuggingFace is 685B, which includes 671B of the Main Model weights and 14B of the Multi-Token Prediction (MTP) Module weights.**
+
+To ensure optimal performance and flexibility, we have partnered with open-source communities and hardware vendors to provide multiple ways to run the model locally. For step-by-step guidance, check out Section 6: [How_to Run_Locally](#6-how-to-run-locally).
+
+For developers looking to dive deeper, we recommend exploring [README_WEIGHTS.md](./README_WEIGHTS.md) for details on the Main Model weights and the Multi-Token Prediction (MTP) Modules. Please note that MTP support is currently under active development within the community, and we welcome your contributions and feedback.
+
+## 4. Evaluation Results
+### Base Model
+#### Standard Benchmarks
+
+<div align="center">
+
+
+|  | Benchmark (Metric) | # Shots | DeepSeek-V2 | Qwen2.5 72B | LLaMA3.1 405B | DeepSeek-V3 |
+|---|-------------------|----------|--------|-------------|---------------|---------|
+| | Architecture | - | MoE | Dense | Dense | MoE |
+| | # Activated Params | - | 21B | 72B | 405B | 37B |
+| | # Total Params | - | 236B | 72B | 405B | 671B |
+| English | Pile-test (BPB) | - | 0.606 | 0.638 | **0.542** | 0.548 |
+| | BBH (EM) | 3-shot | 78.8 | 79.8 | 82.9 | **87.5** |
+| | MMLU (Acc.) | 5-shot | 78.4 | 85.0 | 84.4 | **87.1** |
+| | MMLU-Redux (Acc.) | 5-shot | 75.6 | 83.2 | 81.3 | **86.2** |
+| | MMLU-Pro (Acc.) | 5-shot | 51.4 | 58.3 | 52.8 | **64.4** |
+| | DROP (F1) | 3-shot | 80.4 | 80.6 | 86.0 | **89.0** |
+| | ARC-Easy (Acc.) | 25-shot | 97.6 | 98.4 | 98.4 | **98.9** |
+| | ARC-Challenge (Acc.) | 25-shot | 92.2 | 94.5 | **95.3** | **95.3** |
+| | HellaSwag (Acc.) | 10-shot | 87.1 | 84.8 | **89.2** | 88.9 |
+| | PIQA (Acc.) | 0-shot | 83.9 | 82.6 | **85.9** | 84.7 |
+| | WinoGrande (Acc.) | 5-shot | **86.3** | 82.3 | 85.2 | 84.9 |
+| | RACE-Middle (Acc.) | 5-shot | 73.1 | 68.1 | **74.2** | 67.1 |
+| | RACE-High (Acc.) | 5-shot | 52.6 | 50.3 | **56.8** | 51.3 |
+| | TriviaQA (EM) | 5-shot | 80.0 | 71.9 | **82.7** | **82.9** |
+| | NaturalQuestions (EM) | 5-shot | 38.6 | 33.2 | **41.5** | 40.0 |
+| | AGIEval (Acc.) | 0-shot | 57.5 | 75.8 | 60.6 | **79.6** |
+| Code | HumanEval (Pass@1) | 0-shot | 43.3 | 53.0 | 54.9 | **65.2** |
+| | MBPP (Pass@1) | 3-shot | 65.0 | 72.6 | 68.4 | **75.4** |
+| | LiveCodeBench-Base (Pass@1) | 3-shot | 11.6 | 12.9 | 15.5 | **19.4** |
+| | CRUXEval-I (Acc.) | 2-shot | 52.5 | 59.1 | 58.5 | **67.3** |
+| | CRUXEval-O (Acc.) | 2-shot | 49.8 | 59.9 | 59.9 | **69.8** |
+| Math | GSM8K (EM) | 8-shot | 81.6 | 88.3 | 83.5 | **89.3** |
+| | MATH (EM) | 4-shot | 43.4 | 54.4 | 49.0 | **61.6** |
+| | MGSM (EM) | 8-shot | 63.6 | 76.2 | 69.9 | **79.8** |
+| | CMath (EM) | 3-shot | 78.7 | 84.5 | 77.3 | **90.7** |
+| Chinese | CLUEWSC (EM) | 5-shot | 82.0 | 82.5 | **83.0** | 82.7 |
+| | C-Eval (Acc.) | 5-shot | 81.4 | 89.2 | 72.5 | **90.1** |
+| | CMMLU (Acc.) | 5-shot | 84.0 | **89.5** | 73.7 | 88.8 |
+| | CMRC (EM) | 1-shot | **77.4** | 75.8 | 76.0 | 76.3 |
+| | C3 (Acc.) | 0-shot | 77.4 | 76.7 | **79.7** | 78.6 |
+| | CCPM (Acc.) | 0-shot | **93.0** | 88.5 | 78.6 | 92.0 |
+| Multilingual | MMMLU-non-English (Acc.) | 5-shot | 64.0 | 74.8 | 73.8 | **79.4** |
+
+</div>
+
+Note: Best results are shown in bold. Scores with a gap not exceeding 0.3 are considered to be at the same level. DeepSeek-V3 achieves the best performance on most benchmarks, especially on math and code tasks.
+For more evaluation details, please check our paper. 
+
+#### Context Window
+<p align="center">
+  <img width="80%" src="figures/niah.png">
+</p>
+
+Evaluation results on the ``Needle In A Haystack`` (NIAH) tests.  DeepSeek-V3 performs well across all context window lengths up to **128K**. 
+
+### Chat Model
+#### Standard Benchmarks (Models larger than 67B)
+<div align="center">
+
+| | **Benchmark (Metric)** | **DeepSeek V2-0506** | **DeepSeek V2.5-0905** | **Qwen2.5 72B-Inst.** | **Llama3.1 405B-Inst.** | **Claude-3.5-Sonnet-1022** | **GPT-4o 0513** | **DeepSeek V3** |
+|---|---------------------|---------------------|----------------------|---------------------|----------------------|---------------------------|----------------|----------------|
+| | Architecture | MoE | MoE | Dense | Dense | - | - | MoE |
+| | # Activated Params | 21B | 21B | 72B | 405B | - | - | 37B |
+| | # Total Params | 236B | 236B | 72B | 405B | - | - | 671B |
+| English | MMLU (EM) | 78.2 | 80.6 | 85.3 | **88.6** | **88.3** | 87.2 | **88.5** |
+| | MMLU-Redux (EM) | 77.9 | 80.3 | 85.6 | 86.2 | **88.9** | 88.0 | **89.1** |
+| | MMLU-Pro (EM) | 58.5 | 66.2 | 71.6 | 73.3 | **78.0** | 72.6 | 75.9 |
+| | DROP (3-shot F1) | 83.0 | 87.8 | 76.7 | 88.7 | 88.3 | 83.7 | **91.6** |
+| | IF-Eval (Prompt Strict) | 57.7 | 80.6 | 84.1 | 86.0 | **86.5** | 84.3 | 86.1 |
+| | GPQA-Diamond (Pass@1) | 35.3 | 41.3 | 49.0 | 51.1 | **65.0** | 49.9 | 59.1 |
+| | SimpleQA (Correct) | 9.0 | 10.2 | 9.1 | 17.1 | 28.4 | **38.2** | 24.9 |
+| | FRAMES (Acc.) | 66.9 | 65.4 | 69.8 | 70.0 | 72.5 | **80.5** | 73.3 |
+| | LongBench v2 (Acc.) | 31.6 | 35.4 | 39.4 | 36.1 | 41.0 | 48.1 | **48.7** |
+| Code | HumanEval-Mul (Pass@1) | 69.3 | 77.4 | 77.3 | 77.2 | 81.7 | 80.5 | **82.6** |
+| | LiveCodeBench (Pass@1-COT) | 18.8 | 29.2 | 31.1 | 28.4 | 36.3 | 33.4 | **40.5** |
+| | LiveCodeBench (Pass@1) | 20.3 | 28.4 | 28.7 | 30.1 | 32.8 | 34.2 | **37.6** |
+| | Codeforces (Percentile) | 17.5 | 35.6 | 24.8 | 25.3 | 20.3 | 23.6 | **51.6** |
+| | SWE Verified (Resolved) | - | 22.6 | 23.8 | 24.5 | **50.8** | 38.8 | 42.0 |
+| | Aider-Edit (Acc.) | 60.3 | 71.6 | 65.4 | 63.9 | **84.2** | 72.9 | 79.7 |
+| | Aider-Polyglot (Acc.) | - | 18.2 | 7.6 | 5.8 | 45.3 | 16.0 | **49.6** |
+| Math | AIME 2024 (Pass@1) | 4.6 | 16.7 | 23.3 | 23.3 | 16.0 | 9.3 | **39.2** |
+| | MATH-500 (EM) | 56.3 | 74.7 | 80.0 | 73.8 | 78.3 | 74.6 | **90.2** |
+| | CNMO 2024 (Pass@1) | 2.8 | 10.8 | 15.9 | 6.8 | 13.1 | 10.8 | **43.2** |
+| Chinese | CLUEWSC (EM) | 89.9 | 90.4 | **91.4** | 84.7 | 85.4 | 87.9 | 90.9 |
+| | C-Eval (EM) | 78.6 | 79.5 | 86.1 | 61.5 | 76.7 | 76.0 | **86.5** |
+| | C-SimpleQA (Correct) | 48.5 | 54.1 | 48.4 | 50.4 | 51.3 | 59.3 | **64.8** |
+
+Note: All models are evaluated in a configuration that limits the output length to 8K. Benchmarks containing fewer than 1000 samples are tested multiple times using varying temperature settings to derive robust final results. DeepSeek-V3 stands as the best-performing open-source model, and also exhibits competitive performance against frontier closed-source models.
+
+</div>
+
+
+####  Open Ended Generation Evaluation
+
+<div align="center">
+
+
+
+| Model | Arena-Hard | AlpacaEval 2.0 |
+|-------|------------|----------------|
+| DeepSeek-V2.5-0905 | 76.2 | 50.5 |
+| Qwen2.5-72B-Instruct | 81.2 | 49.1 |
+| LLaMA-3.1 405B | 69.3 | 40.5 |
+| GPT-4o-0513 | 80.4 | 51.1 |
+| Claude-Sonnet-3.5-1022 | 85.2 | 52.0 |
+| DeepSeek-V3 | **85.5** | **70.0** |
+
+Note: English open-ended conversation evaluations. For AlpacaEval 2.0, we use the length-controlled win rate as the metric.
+</div>
+
+
+## 5. Chat Website & API Platform
+You can chat with DeepSeek-V3 on DeepSeek's official website: [chat.deepseek.com](https://chat.deepseek.com/sign_in)
+
+We also provide OpenAI-Compatible API at DeepSeek Platform: [platform.deepseek.com](https://platform.deepseek.com/)
+
+## 6. How to Run Locally
+
+DeepSeek-V3 can be deployed locally using the following hardware and open-source community software:
+
+1. **DeepSeek-Infer Demo**: We provide a simple and lightweight demo for FP8 and BF16 inference.
+2. **SGLang**: Fully support the DeepSeek-V3 model in both BF16 and FP8 inference modes.
+3. **LMDeploy**: Enables efficient FP8 and BF16 inference for local and cloud deployment.
+4. **TensorRT-LLM**: Currently supports BF16 inference and INT4/8 quantization, with FP8 support coming soon.
+5. **vLLM**: Support DeekSeek-V3 model with FP8 and BF16 modes for tensor parallelism and pipeline parallelism.
+6. **AMD GPU**: Enables running the DeepSeek-V3 model on AMD GPUs via SGLang in both BF16 and FP8 modes.
+7. **Huawei Ascend NPU**: Supports running DeepSeek-V3 on Huawei Ascend devices.
+
+Since FP8 training is natively adopted in our framework, we only provide FP8 weights. If you require BF16 weights for experimentation, you can use the provided conversion script to perform the transformation.
+
+Here is an example of converting FP8 weights to BF16:
+
+```shell
+cd inference
+python fp8_cast_bf16.py --input-fp8-hf-path /path/to/fp8_weights --output-bf16-hf-path /path/to/bf16_weights
+```
+
+**NOTE: Huggingface's Transformers has not been directly supported yet.**
+
+### 6.1 Inference with DeepSeek-Infer Demo (example only)
+
+#### Model Weights & Demo Code Preparation
+
+First, clone our DeepSeek-V3 GitHub repository:
+
+```shell
+git clone https://github.com/deepseek-ai/DeepSeek-V3.git
+```
+
+Navigate to the `inference` folder and install dependencies listed in `requirements.txt`.
+
+```shell
+cd DeepSeek-V3/inference
+pip install -r requirements.txt
+```
+
+Download the model weights from HuggingFace, and put them into `/path/to/DeepSeek-V3` folder.
+
+#### Model Weights Conversion
+
+Convert HuggingFace model weights to a specific format:
+
+```shell
+python convert.py --hf-ckpt-path /path/to/DeepSeek-V3 --save-path /path/to/DeepSeek-V3-Demo --n-experts 256 --model-parallel 16
+```
+
+#### Run
+
+Then you can chat with DeepSeek-V3:
+
+```shell
+torchrun --nnodes 2 --nproc-per-node 8 generate.py --node-rank $RANK --master-addr $ADDR --ckpt-path /path/to/DeepSeek-V3-Demo --config configs/config_671B.json --interactive --temperature 0.7 --max-new-tokens 200
+```
+
+Or batch inference on a given file:
+
+```shell
+torchrun --nnodes 2 --nproc-per-node 8 generate.py --node-rank $RANK --master-addr $ADDR --ckpt-path /path/to/DeepSeek-V3-Demo --config configs/config_671B.json --input-file $FILE
+```
+
+### 6.2 Inference with SGLang (recommended)
+
+[SGLang](https://github.com/sgl-project/sglang) currently supports MLA optimizations, FP8 (W8A8), FP8 KV Cache, and Torch Compile, delivering state-of-the-art latency and throughput performance among open-source frameworks.
+
+Notably, [SGLang v0.4.1](https://github.com/sgl-project/sglang/releases/tag/v0.4.1) fully supports running DeepSeek-V3 on both **NVIDIA and AMD GPUs**, making it a highly versatile and robust solution.
+
+Here are the launch instructions from the SGLang team: https://github.com/sgl-project/sglang/tree/main/benchmark/deepseek_v3
+
+### 6.3 Inference with LMDeploy (recommended)
+[LMDeploy](https://github.com/InternLM/lmdeploy), a flexible and high-performance inference and serving framework tailored for large language models, now supports DeepSeek-V3. It offers both offline pipeline processing and online deployment capabilities, seamlessly integrating with PyTorch-based workflows.
+
+For comprehensive step-by-step instructions on running DeepSeek-V3 with LMDeploy, please refer to here: https://github.com/InternLM/lmdeploy/issues/2960
+
+
+### 6.4 Inference with TRT-LLM (recommended)
+
+[TensorRT-LLM](https://github.com/NVIDIA/TensorRT-LLM) now supports the DeepSeek-V3 model, offering precision options such as BF16 and INT4/INT8 weight-only. Support for FP8 is currently in progress and will be released soon. You can access the custom branch of TRTLLM specifically for DeepSeek-V3 support through the following link to experience the new features directly: https://github.com/NVIDIA/TensorRT-LLM/tree/deepseek/examples/deepseek_v3. 
+
+### 6.5 Inference with vLLM (recommended)
+
+[vLLM](https://github.com/vllm-project/vllm) v0.6.6 supports DeepSeek-V3 inference for FP8 and BF16 modes on both NVIDIA and AMD GPUs. Aside from standard techniques, vLLM offers _pipeline parallelism_ allowing you to run this model on multiple machines connected by networks. For detailed guidance, please refer to the [vLLM instructions](https://docs.vllm.ai/en/latest/serving/distributed_serving.html). Please feel free to follow [the enhancement plan](https://github.com/vllm-project/vllm/issues/11539) as well.
+
+### 6.6 Recommended Inference Functionality with AMD GPUs
+
+In collaboration with the AMD team, we have achieved Day-One support for AMD GPUs using SGLang, with full compatibility for both FP8 and BF16 precision. For detailed guidance, please refer to the [SGLang instructions](#63-inference-with-lmdeploy-recommended).
+
+### 6.7 Recommended Inference Functionality with Huawei Ascend NPUs
+The [MindIE](https://www.hiascend.com/en/software/mindie) framework from the Huawei Ascend community has successfully adapted the BF16 version of DeepSeek-V3. For step-by-step guidance on Ascend NPUs, please follow the [instructions here](https://modelers.cn/models/MindIE/deepseekv3).
+
+
+## 7. License
+This code repository is licensed under [the MIT License](LICENSE-CODE). The use of DeepSeek-V3 Base/Chat models is subject to [the Model License](LICENSE-MODEL). DeepSeek-V3 series (including Base and Chat) supports commercial use.
+
+## 8. Citation
+```
+@misc{deepseekai2024deepseekv3technicalreport,
+      title={DeepSeek-V3 Technical Report}, 
+      author={DeepSeek-AI and Aixin Liu and Bei Feng and Bing Xue and Bingxuan Wang and Bochao Wu and Chengda Lu and Chenggang Zhao and Chengqi Deng and Chenyu Zhang and Chong Ruan and Damai Dai and Daya Guo and Dejian Yang and Deli Chen and Dongjie Ji and Erhang Li and Fangyun Lin and Fucong Dai and Fuli Luo and Guangbo Hao and Guanting Chen and Guowei Li and H. Zhang and Han Bao and Hanwei Xu and Haocheng Wang and Haowei Zhang and Honghui Ding and Huajian Xin and Huazuo Gao and Hui Li and Hui Qu and J. L. Cai and Jian Liang and Jianzhong Guo and Jiaqi Ni and Jiashi Li and Jiawei Wang and Jin Chen and Jingchang Chen and Jingyang Yuan and Junjie Qiu and Junlong Li and Junxiao Song and Kai Dong and Kai Hu and Kaige Gao and Kang Guan and Kexin Huang and Kuai Yu and Lean Wang and Lecong Zhang and Lei Xu and Leyi Xia and Liang Zhao and Litong Wang and Liyue Zhang and Meng Li and Miaojun Wang and Mingchuan Zhang and Minghua Zhang and Minghui Tang and Mingming Li and Ning Tian and Panpan Huang and Peiyi Wang and Peng Zhang and Qiancheng Wang and Qihao Zhu and Qinyu Chen and Qiushi Du and R. J. Chen and R. L. Jin and Ruiqi Ge and Ruisong Zhang and Ruizhe Pan and Runji Wang and Runxin Xu and Ruoyu Zhang and Ruyi Chen and S. S. Li and Shanghao Lu and Shangyan Zhou and Shanhuang Chen and Shaoqing Wu and Shengfeng Ye and Shengfeng Ye and Shirong Ma and Shiyu Wang and Shuang Zhou and Shuiping Yu and Shunfeng Zhou and Shuting Pan and T. Wang and Tao Yun and Tian Pei and Tianyu Sun and W. L. Xiao and Wangding Zeng and Wanjia Zhao and Wei An and Wen Liu and Wenfeng Liang and Wenjun Gao and Wenqin Yu and Wentao Zhang and X. Q. Li and Xiangyue Jin and Xianzu Wang and Xiao Bi and Xiaodong Liu and Xiaohan Wang and Xiaojin Shen and Xiaokang Chen and Xiaokang Zhang and Xiaosha Chen and Xiaotao Nie and Xiaowen Sun and Xiaoxiang Wang and Xin Cheng and Xin Liu and Xin Xie and Xingchao Liu and Xingkai Yu and Xinnan Song and Xinxia Shan and Xinyi Zhou and Xinyu Yang and Xinyuan Li and Xuecheng Su and Xuheng Lin and Y. K. Li and Y. Q. Wang and Y. X. Wei and Y. X. Zhu and Yang Zhang and Yanhong Xu and Yanhong Xu and Yanping Huang and Yao Li and Yao Zhao and Yaofeng Sun and Yaohui Li and Yaohui Wang and Yi Yu and Yi Zheng and Yichao Zhang and Yifan Shi and Yiliang Xiong and Ying He and Ying Tang and Yishi Piao and Yisong Wang and Yixuan Tan and Yiyang Ma and Yiyuan Liu and Yongqiang Guo and Yu Wu and Yuan Ou and Yuchen Zhu and Yuduan Wang and Yue Gong and Yuheng Zou and Yujia He and Yukun Zha and Yunfan Xiong and Yunxian Ma and Yuting Yan and Yuxiang Luo and Yuxiang You and Yuxuan Liu and Yuyang Zhou and Z. F. Wu and Z. Z. Ren and Zehui Ren and Zhangli Sha and Zhe Fu and Zhean Xu and Zhen Huang and Zhen Zhang and Zhenda Xie and Zhengyan Zhang and Zhewen Hao and Zhibin Gou and Zhicheng Ma and Zhigang Yan and Zhihong Shao and Zhipeng Xu and Zhiyu Wu and Zhongyu Zhang and Zhuoshu Li and Zihui Gu and Zijia Zhu and Zijun Liu and Zilin Li and Ziwei Xie and Ziyang Song and Ziyi Gao and Zizheng Pan},
+      year={2024},
+      eprint={2412.19437},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2412.19437}, 
+}
+```
+
+## 9. Contact
+If you have any questions, please raise an issue or contact us at [[email protected]]([email protected]).

README_WEIGHTS.md

@@ -0,0 +1,94 @@
+# DeepSeek-V3 Weight File Documentation
+
+## New Fields in `config.json`
+
+- **model_type**: Specifies the model type, which is updated to `deepseek_v3` in this release.
+- **num_nextn_predict_layers**: Indicates the number of Multi-Token Prediction (MTP) Modules. The open-sourced V3 weights include **1 MTP Module** .
+- **quantization_config**: Describes the configuration for FP8 quantization.
+
+---
+
+## Weight Structure Overview
+
+The DeepSeek-V3 weight file consists of two main components: **Main Model Weights** and **MTP Modules**.
+
+### 1. Main Model Weights
+
+- **Composition**:
+  - Input/output embedding layers and a complete set of 61 Transformer hidden layers.
+- **Parameter Count**:
+  - Total parameters: **671B**
+  - Activation parameters: **36.7B** (including 0.9B for Embedding and 0.9B for the output Head).
+
+#### Structural Details
+
+- **Embedding Layer**:
+  - `model.embed_tokens.weight`
+- **Transformer Hidden Layers**:
+  - `model.layers.0` to `model.layers.60`, totaling `num_hidden_layers` layers.
+- **Output Layer**:
+  - `model.norm.weight`
+  - `lm_head.weight`
+
+### 2. Multi-Token Prediction (MTP) Modules
+
+- **Composition**:
+  - Additional MTP Modules defined by the `num_nextn_predict_layers` field. In this model, the value is set to 1.
+- **Parameter Count**:
+  - Parameters: **11.5B unique parameters**, excluding the shared 0.9B Embedding and 0.9B output Head).
+  - Activation parameters: **2.4B** (including the shared 0.9B Embedding and 0.9B output Head).
+
+#### Structural Details
+
+- **embed_tokens**: **Shares parameters** with the Embedding layer of the Main Model weights.
+- **enorm & hnorm**: RMSNorm parameters required for speculative decoding.
+- **eh_proj**: Parameters for dimensionality reduction projection on the norm results.
+- **Additional Transformer Hidden Layer**:
+  - `model.layers.61.self_attn & mlp` (structure identical to the Main Model hidden layers).
+- **shared_head**: **Shares parameters** with the output Head of the Main Model weights.
+
+---
+
+### Loading Rules
+
+- **Main Model Weights**: Loaded via the `num_hidden_layers` parameter in `config.json`.
+- **MTP Modules**: Loaded via the `num_nextn_predict_layers` parameter, with layer IDs appended immediately after the Main Model hidden layers. For example:
+  - If `num_hidden_layers = 61` and `num_nextn_predict_layers = 1`, the MTP Module's layer ID is `61`.
+
+---
+
+## FP8 Weight Documentation
+
+DeepSeek-V3 natively supports FP8 weight format with 128x128 block scaling.
+
+### FP8 Configuration
+
+The FP8 weight file introduces a `quantization_config` field to describe the quantization method. Below is an example configuration:
+
+```json
+"quantization_config": {
+  "activation_scheme": "dynamic",
+  "fmt": "e4m3",
+  "quant_method": "fp8",
+  "weight_block_size": [128, 128]
+}
+```
+
+- **Quantization Format**:
+  - Format type: `fp8` and `e4m3` (corresponding to `torch.float8_e4m3fn`).
+  - Weight block size: `128x128`.
+- **Activation Quantization Scheme**:
+  - Utilizes dynamic activation quantization (`dynamic`).
+
+### Dequantization Method
+
+The FP8 weight file includes a `weight_scale_inv` field, which stores the dequantization scale for each weight block.
+
+- **Storage Format**: `float32 Tensor`, stored alongside the weight data.
+- **Dequantization Formula**:
+  - If the weight block is not aligned to 128, it is zero-padded to 128 before calculating the scale. After quantization, the padded portion is removed.
+  - The dequantization process is performed as: `(128x128 weight block) * weight_scale_inv`.
+
+Through dequantization of the FP8 weights, runtime operations enable online quantization at a granularity of `per-token-per-128-channel`.
+
+---

config.json

@@ -0,0 +1,70 @@
+{
+  "architectures": [
+    "DeepseekV3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_deepseek.DeepseekV3Config",
+    "AutoModel": "modeling_deepseek.DeepseekV3Model",
+    "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
+  },
+  "aux_loss_alpha": 0.001,
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "ep_size": 1,
+  "first_k_dense_replace": 3,
+  "hidden_act": "silu",
+  "hidden_size": 7168,
+  "initializer_range": 0.02,
+  "intermediate_size": 18432,
+  "kv_lora_rank": 512,
+  "max_position_embeddings": 163840,
+  "model_type": "deepseek_v3",
+  "moe_intermediate_size": 2048,
+  "moe_layer_freq": 1,
+  "n_group": 8,
+  "n_routed_experts": 256,
+  "n_shared_experts": 1,
+  "norm_topk_prob": true,
+  "num_attention_heads": 128,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 61,
+  "num_key_value_heads": 128,
+  "num_nextn_predict_layers": 1,
+  "pretraining_tp": 1,
+  "q_lora_rank": 1536,
+  "qk_nope_head_dim": 128,
+  "qk_rope_head_dim": 64,
+  "quantization_config": {
+    "activation_scheme": "dynamic",
+    "fmt": "e4m3",
+    "quant_method": "fp8",
+    "weight_block_size": [
+      128,
+      128
+    ]
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "beta_fast": 32,
+    "beta_slow": 1,
+    "factor": 40,
+    "mscale": 1.0,
+    "mscale_all_dim": 1.0,
+    "original_max_position_embeddings": 4096,
+    "type": "yarn"
+  },
+  "rope_theta": 10000,
+  "routed_scaling_factor": 2.5,
+  "scoring_func": "sigmoid",
+  "seq_aux": true,
+  "tie_word_embeddings": false,
+  "topk_group": 4,
+  "topk_method": "noaux_tc",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.33.1",
+  "use_cache": true,
+  "v_head_dim": 128,
+  "vocab_size": 129280
+}

configuration_deepseek.py

@@ -0,0 +1,210 @@
+from transformers.configuration_utils import PretrainedConfig
+from transformers.utils import logging
+
+logger = logging.get_logger(__name__)
+
+DEEPSEEK_PRETRAINED_CONFIG_ARCHIVE_MAP = {}
+class DeepseekV3Config(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a [`DeepseekV3Model`]. It is used to instantiate an DeepSeek
+    model according to the specified arguments, defining the model architecture. Instantiating a configuration with the
+    defaults will yield a similar configuration to that of the DeepSeek-V3.
+
+    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
+    documentation from [`PretrainedConfig`] for more information.
+
+
+    Args:
+        vocab_size (`int`, *optional*, defaults to 129280):
+            Vocabulary size of the Deep model. Defines the number of different tokens that can be represented by the
+            `inputs_ids` passed when calling [`DeepseekV3Model`]
+        hidden_size (`int`, *optional*, defaults to 4096):
+            Dimension of the hidden representations.
+        intermediate_size (`int`, *optional*, defaults to 11008):
+            Dimension of the MLP representations.
+        moe_intermediate_size (`int`, *optional*, defaults to 1407):
+            Dimension of the MoE representations.
+        num_hidden_layers (`int`, *optional*, defaults to 32):
+            Number of hidden layers in the Transformer decoder.
+        num_nextn_predict_layers (`int`, *optional*, defaults to 1):
+            Number of nextn predict layers in the DeepSeekV3 Model.
+        num_attention_heads (`int`, *optional*, defaults to 32):
+            Number of attention heads for each attention layer in the Transformer decoder.
+        n_shared_experts (`int`, *optional*, defaults to None):
+            Number of shared experts, None means dense model.
+        n_routed_experts (`int`, *optional*, defaults to None):
+            Number of routed experts, None means dense model.
+        routed_scaling_factor (`float`, *optional*, defaults to 1.0):
+            Scaling factor or routed experts.
+        topk_method (`str`, *optional*, defaults to `gready`):
+            Topk method used in routed gate.
+        n_group (`int`, *optional*, defaults to None):
+            Number of groups for routed experts.
+        topk_group (`int`, *optional*, defaults to None):
+            Number of selected groups for each token(for each token, ensuring the selected experts is only within `topk_group` groups).
+        num_experts_per_tok (`int`, *optional*, defaults to None):
+            Number of selected experts, None means dense model.
+        moe_layer_freq (`int`, *optional*, defaults to 1):
+            The frequency of the MoE layer: one expert layer for every `moe_layer_freq - 1` dense layers.
+        first_k_dense_replace (`int`, *optional*, defaults to 0):
+            Number of dense layers in shallow layers(embed->dense->dense->...->dense->moe->moe...->lm_head).
+                                                            \--k dense layers--/
+        norm_topk_prob (`bool`, *optional*, defaults to False):
+            Whether to normalize the weights of the routed experts.
+        scoring_func (`str`, *optional*, defaults to 'softmax'):
+            Method of computing expert weights.
+        aux_loss_alpha (`float`, *optional*, defaults to 0.001):
+            Auxiliary loss weight coefficient.
+        seq_aux = (`bool`, *optional*, defaults to True):
+            Whether to compute the auxiliary loss for each individual sample.
+        num_key_value_heads (`int`, *optional*):
+            This is the number of key_value heads that should be used to implement Grouped Query Attention. If
+            `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
+            `num_key_value_heads=1 the model will use Multi Query Attention (MQA) otherwise GQA is used. When
+            converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
+            by meanpooling all the original heads within that group. For more details checkout [this
+            paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to
+            `num_attention_heads`.
+        hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
+            The non-linear activation function (function or string) in the decoder.
+        max_position_embeddings (`int`, *optional*, defaults to 2048):
+            The maximum sequence length that this model might ever be used with.
+        initializer_range (`float`, *optional*, defaults to 0.02):
+            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
+        rms_norm_eps (`float`, *optional*, defaults to 1e-06):
+            The epsilon used by the rms normalization layers.
+        use_cache (`bool`, *optional*, defaults to `True`):
+            Whether or not the model should return the last key/values attentions (not used by all models). Only
+            relevant if `config.is_decoder=True`.
+        pad_token_id (`int`, *optional*):
+            Padding token id.
+        bos_token_id (`int`, *optional*, defaults to 1):
+            Beginning of stream token id.
+        eos_token_id (`int`, *optional*, defaults to 2):
+            End of stream token id.
+        pretraining_tp (`int`, *optional*, defaults to 1):
+            Experimental feature. Tensor parallelism rank used during pretraining. Please refer to [this
+            document](https://huggingface.co/docs/transformers/parallelism) to understand more about it. This value is
+            necessary to ensure exact reproducibility of the pretraining results. Please refer to [this
+            issue](https://github.com/pytorch/pytorch/issues/76232).
+        tie_word_embeddings (`bool`, *optional*, defaults to `False`):
+            Whether to tie weight embeddings
+        rope_theta (`float`, *optional*, defaults to 10000.0):
+            The base period of the RoPE embeddings.
+        rope_scaling (`Dict`, *optional*):
+            Dictionary containing the scaling configuration for the RoPE embeddings. Currently supports two scaling
+            strategies: linear and dynamic. Their scaling factor must be a float greater than 1. The expected format is
+            `{"type": strategy name, "factor": scaling factor}`. When using this flag, don't update
+            `max_position_embeddings` to the expected new maximum.
+        attention_bias (`bool`, defaults to `False`, *optional*, defaults to `False`):
+            Whether to use a bias in the query, key, value and output projection layers during self-attention.
+        attention_dropout (`float`, *optional*, defaults to 0.0):
+            The dropout ratio for the attention probabilities.
+
+    ```python
+    >>> from transformers import DeepseekV3Model, DeepseekV3Config
+
+    >>> # Initializing a Deepseek-V3 style configuration
+    >>> configuration = DeepseekV3Config()
+
+    >>> # Accessing the model configuration
+    >>> configuration = model.config
+    ```"""
+
+    model_type = "deepseek_v3"
+    keys_to_ignore_at_inference = ["past_key_values"]
+
+    def __init__(
+        self,
+        vocab_size=129280,
+        hidden_size=7168,
+        intermediate_size=18432,
+        moe_intermediate_size = 2048,
+        num_hidden_layers=61,
+        num_nextn_predict_layers=1,
+        num_attention_heads=128,
+        num_key_value_heads=128,
+        n_shared_experts = 1,
+        n_routed_experts = 256,
+        ep_size = 1,
+        routed_scaling_factor = 2.5,
+        kv_lora_rank = 512,
+        q_lora_rank = 1536,
+        qk_rope_head_dim = 64,
+        v_head_dim = 128,
+        qk_nope_head_dim = 128,
+        topk_method = 'noaux_tc',
+        n_group = 8,
+        topk_group = 4,
+        num_experts_per_tok = 8,
+        moe_layer_freq = 1,
+        first_k_dense_replace = 3,
+        norm_topk_prob = True,
+        scoring_func = 'sigmoid',
+        aux_loss_alpha = 0.001,
+        seq_aux = True,
+        hidden_act="silu",
+        max_position_embeddings=4096,
+        initializer_range=0.02,
+        rms_norm_eps=1e-6,
+        use_cache=True,
+        pad_token_id=None,
+        bos_token_id=0,
+        eos_token_id=1,
+        pretraining_tp=1,
+        tie_word_embeddings=False,
+        rope_theta=10000.0,
+        rope_scaling=None,
+        attention_bias=False,
+        attention_dropout=0.0,
+        **kwargs,
+    ):
+        self.vocab_size = vocab_size
+        self.max_position_embeddings = max_position_embeddings
+        self.hidden_size = hidden_size
+        self.intermediate_size = intermediate_size
+        self.moe_intermediate_size = moe_intermediate_size
+        self.num_hidden_layers = num_hidden_layers
+        self.num_nextn_predict_layers = num_nextn_predict_layers
+        self.num_attention_heads = num_attention_heads
+        self.n_shared_experts = n_shared_experts
+        self.n_routed_experts = n_routed_experts
+        self.ep_size = ep_size
+        self.routed_scaling_factor = routed_scaling_factor
+        self.kv_lora_rank = kv_lora_rank
+        self.q_lora_rank = q_lora_rank
+        self.qk_rope_head_dim = qk_rope_head_dim
+        self.v_head_dim = v_head_dim
+        self.qk_nope_head_dim = qk_nope_head_dim
+        self.topk_method = topk_method
+        self.n_group = n_group
+        self.topk_group = topk_group
+        self.num_experts_per_tok = num_experts_per_tok
+        self.moe_layer_freq = moe_layer_freq
+        self.first_k_dense_replace = first_k_dense_replace
+        self.norm_topk_prob = norm_topk_prob
+        self.scoring_func = scoring_func
+        self.aux_loss_alpha = aux_loss_alpha
+        self.seq_aux = seq_aux
+        # for backward compatibility
+        if num_key_value_heads is None:
+            num_key_value_heads = num_attention_heads
+
+        self.num_key_value_heads = num_key_value_heads
+        self.hidden_act = hidden_act
+        self.initializer_range = initializer_range
+        self.rms_norm_eps = rms_norm_eps
+        self.pretraining_tp = pretraining_tp
+        self.use_cache = use_cache
+        self.rope_theta = rope_theta
+        self.rope_scaling = rope_scaling
+        self.attention_bias = attention_bias
+        self.attention_dropout = attention_dropout
+
+        super().__init__(
+            pad_token_id=pad_token_id,
+            bos_token_id=bos_token_id,
+            eos_token_id=eos_token_id,
+            tie_word_embeddings=tie_word_embeddings,
+            **kwargs,
+        )

inference/.venv/bin/Activate.ps1

@@ -0,0 +1,247 @@
+<#
+.Synopsis
+Activate a Python virtual environment for the current PowerShell session.
+
+.Description
+Pushes the python executable for a virtual environment to the front of the
+$Env:PATH environment variable and sets the prompt to signify that you are
+in a Python virtual environment. Makes use of the command line switches as
+well as the `pyvenv.cfg` file values present in the virtual environment.
+
+.Parameter VenvDir
+Path to the directory that contains the virtual environment to activate. The
+default value for this is the parent of the directory that the Activate.ps1
+script is located within.
+
+.Parameter Prompt
+The prompt prefix to display when this virtual environment is activated. By
+default, this prompt is the name of the virtual environment folder (VenvDir)
+surrounded by parentheses and followed by a single space (ie. '(.venv) ').
+
+.Example
+Activate.ps1
+Activates the Python virtual environment that contains the Activate.ps1 script.
+
+.Example
+Activate.ps1 -Verbose
+Activates the Python virtual environment that contains the Activate.ps1 script,
+and shows extra information about the activation as it executes.
+
+.Example
+Activate.ps1 -VenvDir C:\Users\MyUser\Common\.venv
+Activates the Python virtual environment located in the specified location.
+
+.Example
+Activate.ps1 -Prompt "MyPython"
+Activates the Python virtual environment that contains the Activate.ps1 script,
+and prefixes the current prompt with the specified string (surrounded in
+parentheses) while the virtual environment is active.
+
+.Notes
+On Windows, it may be required to enable this Activate.ps1 script by setting the
+execution policy for the user. You can do this by issuing the following PowerShell
+command:
+
+PS C:\> Set-ExecutionPolicy -ExecutionPolicy RemoteSigned -Scope CurrentUser
+
+For more information on Execution Policies: 
+https://go.microsoft.com/fwlink/?LinkID=135170
+
+#>
+Param(
+    [Parameter(Mandatory = $false)]
+    [String]
+    $VenvDir,
+    [Parameter(Mandatory = $false)]
+    [String]
+    $Prompt
+)
+
+<# Function declarations --------------------------------------------------- #>
+
+<#
+.Synopsis
+Remove all shell session elements added by the Activate script, including the
+addition of the virtual environment's Python executable from the beginning of
+the PATH variable.
+
+.Parameter NonDestructive
+If present, do not remove this function from the global namespace for the
+session.
+
+#>
+function global:deactivate ([switch]$NonDestructive) {
+    # Revert to original values
+
+    # The prior prompt:
+    if (Test-Path -Path Function:_OLD_VIRTUAL_PROMPT) {
+        Copy-Item -Path Function:_OLD_VIRTUAL_PROMPT -Destination Function:prompt
+        Remove-Item -Path Function:_OLD_VIRTUAL_PROMPT
+    }
+
+    # The prior PYTHONHOME:
+    if (Test-Path -Path Env:_OLD_VIRTUAL_PYTHONHOME) {
+        Copy-Item -Path Env:_OLD_VIRTUAL_PYTHONHOME -Destination Env:PYTHONHOME
+        Remove-Item -Path Env:_OLD_VIRTUAL_PYTHONHOME
+    }
+
+    # The prior PATH:
+    if (Test-Path -Path Env:_OLD_VIRTUAL_PATH) {
+        Copy-Item -Path Env:_OLD_VIRTUAL_PATH -Destination Env:PATH
+        Remove-Item -Path Env:_OLD_VIRTUAL_PATH
+    }
+
+    # Just remove the VIRTUAL_ENV altogether:
+    if (Test-Path -Path Env:VIRTUAL_ENV) {
+        Remove-Item -Path env:VIRTUAL_ENV
+    }
+
+    # Just remove VIRTUAL_ENV_PROMPT altogether.
+    if (Test-Path -Path Env:VIRTUAL_ENV_PROMPT) {
+        Remove-Item -Path env:VIRTUAL_ENV_PROMPT
+    }
+
+    # Just remove the _PYTHON_VENV_PROMPT_PREFIX altogether:
+    if (Get-Variable -Name "_PYTHON_VENV_PROMPT_PREFIX" -ErrorAction SilentlyContinue) {
+        Remove-Variable -Name _PYTHON_VENV_PROMPT_PREFIX -Scope Global -Force
+    }
+
+    # Leave deactivate function in the global namespace if requested:
+    if (-not $NonDestructive) {
+        Remove-Item -Path function:deactivate
+    }
+}
+
+<#
+.Description
+Get-PyVenvConfig parses the values from the pyvenv.cfg file located in the
+given folder, and returns them in a map.
+
+For each line in the pyvenv.cfg file, if that line can be parsed into exactly
+two strings separated by `=` (with any amount of whitespace surrounding the =)
+then it is considered a `key = value` line. The left hand string is the key,
+the right hand is the value.
+
+If the value starts with a `'` or a `"` then the first and last character is
+stripped from the value before being captured.
+
+.Parameter ConfigDir
+Path to the directory that contains the `pyvenv.cfg` file.
+#>
+function Get-PyVenvConfig(
+    [String]
+    $ConfigDir
+) {
+    Write-Verbose "Given ConfigDir=$ConfigDir, obtain values in pyvenv.cfg"
+
+    # Ensure the file exists, and issue a warning if it doesn't (but still allow the function to continue).
+    $pyvenvConfigPath = Join-Path -Resolve -Path $ConfigDir -ChildPath 'pyvenv.cfg' -ErrorAction Continue
+
+    # An empty map will be returned if no config file is found.
+    $pyvenvConfig = @{ }
+
+    if ($pyvenvConfigPath) {
+
+        Write-Verbose "File exists, parse `key = value` lines"
+        $pyvenvConfigContent = Get-Content -Path $pyvenvConfigPath
+
+        $pyvenvConfigContent | ForEach-Object {
+            $keyval = $PSItem -split "\s*=\s*", 2
+            if ($keyval[0] -and $keyval[1]) {
+                $val = $keyval[1]
+
+                # Remove extraneous quotations around a string value.
+                if ("'""".Contains($val.Substring(0, 1))) {
+                    $val = $val.Substring(1, $val.Length - 2)
+                }
+
+                $pyvenvConfig[$keyval[0]] = $val
+                Write-Verbose "Adding Key: '$($keyval[0])'='$val'"
+            }
+        }
+    }
+    return $pyvenvConfig
+}
+
+
+<# Begin Activate script --------------------------------------------------- #>
+
+# Determine the containing directory of this script
+$VenvExecPath = Split-Path -Parent $MyInvocation.MyCommand.Definition
+$VenvExecDir = Get-Item -Path $VenvExecPath
+
+Write-Verbose "Activation script is located in path: '$VenvExecPath'"
+Write-Verbose "VenvExecDir Fullname: '$($VenvExecDir.FullName)"
+Write-Verbose "VenvExecDir Name: '$($VenvExecDir.Name)"
+
+# Set values required in priority: CmdLine, ConfigFile, Default
+# First, get the location of the virtual environment, it might not be
+# VenvExecDir if specified on the command line.
+if ($VenvDir) {
+    Write-Verbose "VenvDir given as parameter, using '$VenvDir' to determine values"
+}
+else {
+    Write-Verbose "VenvDir not given as a parameter, using parent directory name as VenvDir."
+    $VenvDir = $VenvExecDir.Parent.FullName.TrimEnd("\\/")
+    Write-Verbose "VenvDir=$VenvDir"
+}
+
+# Next, read the `pyvenv.cfg` file to determine any required value such
+# as `prompt`.
+$pyvenvCfg = Get-PyVenvConfig -ConfigDir $VenvDir
+
+# Next, set the prompt from the command line, or the config file, or
+# just use the name of the virtual environment folder.
+if ($Prompt) {
+    Write-Verbose "Prompt specified as argument, using '$Prompt'"
+}
+else {
+    Write-Verbose "Prompt not specified as argument to script, checking pyvenv.cfg value"
+    if ($pyvenvCfg -and $pyvenvCfg['prompt']) {
+        Write-Verbose "  Setting based on value in pyvenv.cfg='$($pyvenvCfg['prompt'])'"
+        $Prompt = $pyvenvCfg['prompt'];
+    }
+    else {
+        Write-Verbose "  Setting prompt based on parent's directory's name. (Is the directory name passed to venv module when creating the virtual environment)"
+        Write-Verbose "  Got leaf-name of $VenvDir='$(Split-Path -Path $venvDir -Leaf)'"
+        $Prompt = Split-Path -Path $venvDir -Leaf
+    }
+}
+
+Write-Verbose "Prompt = '$Prompt'"
+Write-Verbose "VenvDir='$VenvDir'"
+
+# Deactivate any currently active virtual environment, but leave the
+# deactivate function in place.
+deactivate -nondestructive
+
+# Now set the environment variable VIRTUAL_ENV, used by many tools to determine
+# that there is an activated venv.
+$env:VIRTUAL_ENV = $VenvDir
+
+if (-not $Env:VIRTUAL_ENV_DISABLE_PROMPT) {
+
+    Write-Verbose "Setting prompt to '$Prompt'"
+
+    # Set the prompt to include the env name
+    # Make sure _OLD_VIRTUAL_PROMPT is global
+    function global:_OLD_VIRTUAL_PROMPT { "" }
+    Copy-Item -Path function:prompt -Destination function:_OLD_VIRTUAL_PROMPT
+    New-Variable -Name _PYTHON_VENV_PROMPT_PREFIX -Description "Python virtual environment prompt prefix" -Scope Global -Option ReadOnly -Visibility Public -Value $Prompt
+
+    function global:prompt {
+        Write-Host -NoNewline -ForegroundColor Green "($_PYTHON_VENV_PROMPT_PREFIX) "
+        _OLD_VIRTUAL_PROMPT
+    }
+    $env:VIRTUAL_ENV_PROMPT = $Prompt
+}
+
+# Clear PYTHONHOME
+if (Test-Path -Path Env:PYTHONHOME) {
+    Copy-Item -Path Env:PYTHONHOME -Destination Env:_OLD_VIRTUAL_PYTHONHOME
+    Remove-Item -Path Env:PYTHONHOME
+}
+
+# Add the venv to the PATH
+Copy-Item -Path Env:PATH -Destination Env:_OLD_VIRTUAL_PATH
+$Env:PATH = "$VenvExecDir$([System.IO.Path]::PathSeparator)$Env:PATH"

inference/.venv/bin/activate

@@ -0,0 +1,69 @@
+# This file must be used with "source bin/activate" *from bash*
+# you cannot run it directly
+
+deactivate () {
+    # reset old environment variables
+    if [ -n "${_OLD_VIRTUAL_PATH:-}" ] ; then
+        PATH="${_OLD_VIRTUAL_PATH:-}"
+        export PATH
+        unset _OLD_VIRTUAL_PATH
+    fi
+    if [ -n "${_OLD_VIRTUAL_PYTHONHOME:-}" ] ; then
+        PYTHONHOME="${_OLD_VIRTUAL_PYTHONHOME:-}"
+        export PYTHONHOME
+        unset _OLD_VIRTUAL_PYTHONHOME
+    fi
+
+    # This should detect bash and zsh, which have a hash command that must
+    # be called to get it to forget past commands.  Without forgetting
+    # past commands the $PATH changes we made may not be respected
+    if [ -n "${BASH:-}" -o -n "${ZSH_VERSION:-}" ] ; then
+        hash -r 2> /dev/null
+    fi
+
+    if [ -n "${_OLD_VIRTUAL_PS1:-}" ] ; then
+        PS1="${_OLD_VIRTUAL_PS1:-}"
+        export PS1
+        unset _OLD_VIRTUAL_PS1
+    fi
+
+    unset VIRTUAL_ENV
+    unset VIRTUAL_ENV_PROMPT
+    if [ ! "${1:-}" = "nondestructive" ] ; then
+    # Self destruct!
+        unset -f deactivate
+    fi
+}
+
+# unset irrelevant variables
+deactivate nondestructive
+
+VIRTUAL_ENV=/home/ubuntuai/models/DeepSeek-V3/inference/.venv
+export VIRTUAL_ENV
+
+_OLD_VIRTUAL_PATH="$PATH"
+PATH="$VIRTUAL_ENV/"bin":$PATH"
+export PATH
+
+# unset PYTHONHOME if set
+# this will fail if PYTHONHOME is set to the empty string (which is bad anyway)
+# could use `if (set -u; : $PYTHONHOME) ;` in bash
+if [ -n "${PYTHONHOME:-}" ] ; then
+    _OLD_VIRTUAL_PYTHONHOME="${PYTHONHOME:-}"
+    unset PYTHONHOME
+fi
+
+if [ -z "${VIRTUAL_ENV_DISABLE_PROMPT:-}" ] ; then
+    _OLD_VIRTUAL_PS1="${PS1:-}"
+    PS1='(.venv) '"${PS1:-}"
+    export PS1
+    VIRTUAL_ENV_PROMPT='(.venv) '
+    export VIRTUAL_ENV_PROMPT
+fi
+
+# This should detect bash and zsh, which have a hash command that must
+# be called to get it to forget past commands.  Without forgetting
+# past commands the $PATH changes we made may not be respected
+if [ -n "${BASH:-}" -o -n "${ZSH_VERSION:-}" ] ; then
+    hash -r 2> /dev/null
+fi

inference/.venv/bin/activate.csh

@@ -0,0 +1,26 @@
+# This file must be used with "source bin/activate.csh" *from csh*.
+# You cannot run it directly.
+# Created by Davide Di Blasi <[email protected]>.
+# Ported to Python 3.3 venv by Andrew Svetlov <[email protected]>
+
+alias deactivate 'test $?_OLD_VIRTUAL_PATH != 0 && setenv PATH "$_OLD_VIRTUAL_PATH" && unset _OLD_VIRTUAL_PATH; rehash; test $?_OLD_VIRTUAL_PROMPT != 0 && set prompt="$_OLD_VIRTUAL_PROMPT" && unset _OLD_VIRTUAL_PROMPT; unsetenv VIRTUAL_ENV; unsetenv VIRTUAL_ENV_PROMPT; test "\!:*" != "nondestructive" && unalias deactivate'
+
+# Unset irrelevant variables.
+deactivate nondestructive
+
+setenv VIRTUAL_ENV /home/ubuntuai/models/DeepSeek-V3/inference/.venv
+
+set _OLD_VIRTUAL_PATH="$PATH"
+setenv PATH "$VIRTUAL_ENV/"bin":$PATH"
+
+
+set _OLD_VIRTUAL_PROMPT="$prompt"
+
+if (! "$?VIRTUAL_ENV_DISABLE_PROMPT") then
+    set prompt = '(.venv) '"$prompt"
+    setenv VIRTUAL_ENV_PROMPT '(.venv) '
+endif
+
+alias pydoc python -m pydoc
+
+rehash

inference/.venv/bin/activate.fish

@@ -0,0 +1,69 @@
+# This file must be used with "source <venv>/bin/activate.fish" *from fish*
+# (https://fishshell.com/); you cannot run it directly.
+
+function deactivate  -d "Exit virtual environment and return to normal shell environment"
+    # reset old environment variables
+    if test -n "$_OLD_VIRTUAL_PATH"
+        set -gx PATH $_OLD_VIRTUAL_PATH
+        set -e _OLD_VIRTUAL_PATH
+    end
+    if test -n "$_OLD_VIRTUAL_PYTHONHOME"
+        set -gx PYTHONHOME $_OLD_VIRTUAL_PYTHONHOME
+        set -e _OLD_VIRTUAL_PYTHONHOME
+    end
+
+    if test -n "$_OLD_FISH_PROMPT_OVERRIDE"
+        set -e _OLD_FISH_PROMPT_OVERRIDE
+        # prevents error when using nested fish instances (Issue #93858)
+        if functions -q _old_fish_prompt
+            functions -e fish_prompt
+            functions -c _old_fish_prompt fish_prompt
+            functions -e _old_fish_prompt
+        end
+    end
+
+    set -e VIRTUAL_ENV
+    set -e VIRTUAL_ENV_PROMPT
+    if test "$argv[1]" != "nondestructive"
+        # Self-destruct!
+        functions -e deactivate
+    end
+end
+
+# Unset irrelevant variables.
+deactivate nondestructive
+
+set -gx VIRTUAL_ENV /home/ubuntuai/models/DeepSeek-V3/inference/.venv
+
+set -gx _OLD_VIRTUAL_PATH $PATH
+set -gx PATH "$VIRTUAL_ENV/"bin $PATH
+
+# Unset PYTHONHOME if set.
+if set -q PYTHONHOME
+    set -gx _OLD_VIRTUAL_PYTHONHOME $PYTHONHOME
+    set -e PYTHONHOME
+end
+
+if test -z "$VIRTUAL_ENV_DISABLE_PROMPT"
+    # fish uses a function instead of an env var to generate the prompt.
+
+    # Save the current fish_prompt function as the function _old_fish_prompt.
+    functions -c fish_prompt _old_fish_prompt
+
+    # With the original prompt function renamed, we can override with our own.
+    function fish_prompt
+        # Save the return status of the last command.
+        set -l old_status $status
+
+        # Output the venv prompt; color taken from the blue of the Python logo.
+        printf "%s%s%s" (set_color 4B8BBE) '(.venv) ' (set_color normal)
+
+        # Restore the return status of the previous command.
+        echo "exit $old_status" | .
+        # Output the original/"old" prompt.
+        _old_fish_prompt
+    end
+
+    set -gx _OLD_FISH_PROMPT_OVERRIDE "$VIRTUAL_ENV"
+    set -gx VIRTUAL_ENV_PROMPT '(.venv) '
+end

inference/.venv/bin/convert-caffe2-to-onnx

@@ -0,0 +1,8 @@
+#!/home/ubuntuai/models/DeepSeek-V3/inference/.venv/bin/python
+# -*- coding: utf-8 -*-
+import re
+import sys
+from caffe2.python.onnx.bin.conversion import caffe2_to_onnx
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(caffe2_to_onnx())

inference/.venv/bin/convert-onnx-to-caffe2

@@ -0,0 +1,8 @@
+#!/home/ubuntuai/models/DeepSeek-V3/inference/.venv/bin/python
+# -*- coding: utf-8 -*-
+import re
+import sys
+from caffe2.python.onnx.bin.conversion import onnx_to_caffe2
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(onnx_to_caffe2())

inference/.venv/bin/f2py

@@ -0,0 +1,8 @@
+#!/home/ubuntuai/models/DeepSeek-V3/inference/.venv/bin/python
+# -*- coding: utf-8 -*-
+import re
+import sys
+from numpy.f2py.f2py2e import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

inference/.venv/bin/huggingface-cli

@@ -0,0 +1,8 @@
+#!/home/ubuntuai/models/DeepSeek-V3/inference/.venv/bin/python
+# -*- coding: utf-8 -*-
+import re
+import sys
+from huggingface_hub.commands.huggingface_cli import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

inference/.venv/bin/isympy

@@ -0,0 +1,8 @@
+#!/home/ubuntuai/models/DeepSeek-V3/inference/.venv/bin/python
+# -*- coding: utf-8 -*-
+import re
+import sys
+from isympy import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

inference/.venv/bin/normalizer

@@ -0,0 +1,8 @@
+#!/home/ubuntuai/models/DeepSeek-V3/inference/.venv/bin/python
+# -*- coding: utf-8 -*-
+import re
+import sys
+from charset_normalizer import cli
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(cli.cli_detect())

inference/.venv/bin/numpy-config

@@ -0,0 +1,8 @@
+#!/home/ubuntuai/models/DeepSeek-V3/inference/.venv/bin/python
+# -*- coding: utf-8 -*-
+import re
+import sys
+from numpy._configtool import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

inference/.venv/bin/pip

@@ -0,0 +1,8 @@
+#!/home/ubuntuai/models/DeepSeek-V3/inference/.venv/bin/python3
+# -*- coding: utf-8 -*-
+import re
+import sys
+from pip._internal.cli.main import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

inference/.venv/bin/pip3

@@ -0,0 +1,8 @@
+#!/home/ubuntuai/models/DeepSeek-V3/inference/.venv/bin/python3
+# -*- coding: utf-8 -*-
+import re
+import sys
+from pip._internal.cli.main import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

inference/.venv/bin/pip3.10

@@ -0,0 +1,8 @@
+#!/home/ubuntuai/models/DeepSeek-V3/inference/.venv/bin/python3
+# -*- coding: utf-8 -*-
+import re
+import sys
+from pip._internal.cli.main import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

inference/.venv/bin/proton

@@ -0,0 +1,8 @@
+#!/home/ubuntuai/models/DeepSeek-V3/inference/.venv/bin/python
+# -*- coding: utf-8 -*-
+import re
+import sys
+from triton.profiler.proton import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

inference/.venv/bin/proton-viewer

@@ -0,0 +1,8 @@
+#!/home/ubuntuai/models/DeepSeek-V3/inference/.venv/bin/python
+# -*- coding: utf-8 -*-
+import re
+import sys
+from triton.profiler.viewer import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

inference/.venv/bin/python

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caec073da847da0ba8e22059a61a877b38b25e0454c2d83520dea2b25c88bbec
+size 5941832

inference/.venv/bin/python3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caec073da847da0ba8e22059a61a877b38b25e0454c2d83520dea2b25c88bbec
+size 5941832

inference/.venv/bin/python3.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caec073da847da0ba8e22059a61a877b38b25e0454c2d83520dea2b25c88bbec
+size 5941832

inference/.venv/bin/torchrun

@@ -0,0 +1,8 @@
+#!/home/ubuntuai/models/DeepSeek-V3/inference/.venv/bin/python
+# -*- coding: utf-8 -*-
+import re
+import sys
+from torch.distributed.run import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

inference/.venv/bin/tqdm

@@ -0,0 +1,8 @@
+#!/home/ubuntuai/models/DeepSeek-V3/inference/.venv/bin/python
+# -*- coding: utf-8 -*-
+import re
+import sys
+from tqdm.cli import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

inference/.venv/bin/transformers-cli

@@ -0,0 +1,8 @@
+#!/home/ubuntuai/models/DeepSeek-V3/inference/.venv/bin/python
+# -*- coding: utf-8 -*-
+import re
+import sys
+from transformers.commands.transformers_cli import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

inference/.venv/lib/python3.10/site-packages/MarkupSafe-3.0.2.dist-info/INSTALLER

@@ -0,0 +1 @@
+pip

inference/.venv/lib/python3.10/site-packages/MarkupSafe-3.0.2.dist-info/LICENSE.txt

@@ -0,0 +1,28 @@
+Copyright 2010 Pallets
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are
+met:
+
+1.  Redistributions of source code must retain the above copyright
+    notice, this list of conditions and the following disclaimer.
+
+2.  Redistributions in binary form must reproduce the above copyright
+    notice, this list of conditions and the following disclaimer in the
+    documentation and/or other materials provided with the distribution.
+
+3.  Neither the name of the copyright holder nor the names of its
+    contributors may be used to endorse or promote products derived from
+    this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
+PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED
+TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
+PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

inference/.venv/lib/python3.10/site-packages/MarkupSafe-3.0.2.dist-info/METADATA

@@ -0,0 +1,92 @@
+Metadata-Version: 2.1
+Name: MarkupSafe
+Version: 3.0.2
+Summary: Safely add untrusted strings to HTML/XML markup.
+Maintainer-email: Pallets <[email protected]>
+License: Copyright 2010 Pallets
+        
+        Redistribution and use in source and binary forms, with or without
+        modification, are permitted provided that the following conditions are
+        met:
+        
+        1.  Redistributions of source code must retain the above copyright
+            notice, this list of conditions and the following disclaimer.
+        
+        2.  Redistributions in binary form must reproduce the above copyright
+            notice, this list of conditions and the following disclaimer in the
+            documentation and/or other materials provided with the distribution.
+        
+        3.  Neither the name of the copyright holder nor the names of its
+            contributors may be used to endorse or promote products derived from
+            this software without specific prior written permission.
+        
+        THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+        "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+        LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
+        PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+        HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+        SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED
+        TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
+        PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+        LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+        NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+        SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+        
+Project-URL: Donate, https://palletsprojects.com/donate
+Project-URL: Documentation, https://markupsafe.palletsprojects.com/
+Project-URL: Changes, https://markupsafe.palletsprojects.com/changes/
+Project-URL: Source, https://github.com/pallets/markupsafe/
+Project-URL: Chat, https://discord.gg/pallets
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Environment :: Web Environment
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: BSD License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python
+Classifier: Topic :: Internet :: WWW/HTTP :: Dynamic Content
+Classifier: Topic :: Text Processing :: Markup :: HTML
+Classifier: Typing :: Typed
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE.txt
+
+# MarkupSafe
+
+MarkupSafe implements a text object that escapes characters so it is
+safe to use in HTML and XML. Characters that have special meanings are
+replaced so that they display as the actual characters. This mitigates
+injection attacks, meaning untrusted user input can safely be displayed
+on a page.
+
+
+## Examples
+
+```pycon
+>>> from markupsafe import Markup, escape
+
+>>> # escape replaces special characters and wraps in Markup
+>>> escape("<script>alert(document.cookie);</script>")
+Markup('&lt;script&gt;alert(document.cookie);&lt;/script&gt;')
+
+>>> # wrap in Markup to mark text "safe" and prevent escaping
+>>> Markup("<strong>Hello</strong>")
+Markup('<strong>hello</strong>')
+
+>>> escape(Markup("<strong>Hello</strong>"))
+Markup('<strong>hello</strong>')
+
+>>> # Markup is a str subclass
+>>> # methods and operators escape their arguments
+>>> template = Markup("Hello <em>{name}</em>")
+>>> template.format(name='"World"')
+Markup('Hello <em>&#34;World&#34;</em>')
+```
+
+## Donate
+
+The Pallets organization develops and supports MarkupSafe and other
+popular packages. In order to grow the community of contributors and
+users, and allow the maintainers to devote more time to the projects,
+[please donate today][].
+
+[please donate today]: https://palletsprojects.com/donate

inference/.venv/lib/python3.10/site-packages/MarkupSafe-3.0.2.dist-info/RECORD

@@ -0,0 +1,14 @@
+MarkupSafe-3.0.2.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
+MarkupSafe-3.0.2.dist-info/LICENSE.txt,sha256=SJqOEQhQntmKN7uYPhHg9-HTHwvY-Zp5yESOf_N9B-o,1475
+MarkupSafe-3.0.2.dist-info/METADATA,sha256=aAwbZhSmXdfFuMM-rEHpeiHRkBOGESyVLJIuwzHP-nw,3975
+MarkupSafe-3.0.2.dist-info/RECORD,,
+MarkupSafe-3.0.2.dist-info/WHEEL,sha256=_kVlewavvOSnwZE_whBk3jlE_Ob-nL5GvlVcLkpXSD8,151
+MarkupSafe-3.0.2.dist-info/top_level.txt,sha256=qy0Plje5IJuvsCBjejJyhDCjEAdcDLK_2agVcex8Z6U,11
+markupsafe/__init__.py,sha256=sr-U6_27DfaSrj5jnHYxWN-pvhM27sjlDplMDPZKm7k,13214
+markupsafe/__pycache__/__init__.cpython-310.pyc,,
+markupsafe/__pycache__/_native.cpython-310.pyc,,
+markupsafe/_native.py,sha256=hSLs8Jmz5aqayuengJJ3kdT5PwNpBWpKrmQSdipndC8,210
+markupsafe/_speedups.c,sha256=O7XulmTo-epI6n2FtMVOrJXl8EAaIwD2iNYmBI5SEoQ,4149
+markupsafe/_speedups.cpython-310-x86_64-linux-gnu.so,sha256=x4RoxWgyqAEokk-AZrWvrLDxLE-dm-zZSZYV_gOiLJA,34976
+markupsafe/_speedups.pyi,sha256=ENd1bYe7gbBUf2ywyYWOGUpnXOHNJ-cgTNqetlW8h5k,41
+markupsafe/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0

inference/.venv/lib/python3.10/site-packages/MarkupSafe-3.0.2.dist-info/WHEEL

@@ -0,0 +1,6 @@
+Wheel-Version: 1.0
+Generator: setuptools (75.2.0)
+Root-Is-Purelib: false
+Tag: cp310-cp310-manylinux_2_17_x86_64
+Tag: cp310-cp310-manylinux2014_x86_64
+

inference/.venv/lib/python3.10/site-packages/MarkupSafe-3.0.2.dist-info/top_level.txt

@@ -0,0 +1 @@
+markupsafe

inference/.venv/lib/python3.10/site-packages/PyYAML-6.0.2.dist-info/INSTALLER

@@ -0,0 +1 @@
+pip

inference/.venv/lib/python3.10/site-packages/PyYAML-6.0.2.dist-info/LICENSE

@@ -0,0 +1,20 @@
+Copyright (c) 2017-2021 Ingy döt Net
+Copyright (c) 2006-2016 Kirill Simonov
+
+Permission is hereby granted, free of charge, to any person obtaining a copy of
+this software and associated documentation files (the "Software"), to deal in
+the Software without restriction, including without limitation the rights to
+use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies
+of the Software, and to permit persons to whom the Software is furnished to do
+so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

inference/.venv/lib/python3.10/site-packages/PyYAML-6.0.2.dist-info/METADATA

@@ -0,0 +1,46 @@
+Metadata-Version: 2.1
+Name: PyYAML
+Version: 6.0.2
+Summary: YAML parser and emitter for Python
+Home-page: https://pyyaml.org/
+Download-URL: https://pypi.org/project/PyYAML/
+Author: Kirill Simonov
+Author-email: [email protected]
+License: MIT
+Project-URL: Bug Tracker, https://github.com/yaml/pyyaml/issues
+Project-URL: CI, https://github.com/yaml/pyyaml/actions
+Project-URL: Documentation, https://pyyaml.org/wiki/PyYAMLDocumentation
+Project-URL: Mailing lists, http://lists.sourceforge.net/lists/listinfo/yaml-core
+Project-URL: Source Code, https://github.com/yaml/pyyaml
+Platform: Any
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Cython
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: Implementation :: CPython
+Classifier: Programming Language :: Python :: Implementation :: PyPy
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Text Processing :: Markup
+Requires-Python: >=3.8
+License-File: LICENSE
+
+YAML is a data serialization format designed for human readability
+and interaction with scripting languages.  PyYAML is a YAML parser
+and emitter for Python.
+
+PyYAML features a complete YAML 1.1 parser, Unicode support, pickle
+support, capable extension API, and sensible error messages.  PyYAML
+supports standard YAML tags and provides Python-specific tags that
+allow to represent an arbitrary Python object.
+
+PyYAML is applicable for a broad range of tasks from complex
+configuration files to object serialization and persistence.

inference/.venv/lib/python3.10/site-packages/PyYAML-6.0.2.dist-info/RECORD

@@ -0,0 +1,43 @@
+PyYAML-6.0.2.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
+PyYAML-6.0.2.dist-info/LICENSE,sha256=jTko-dxEkP1jVwfLiOsmvXZBAqcoKVQwfT5RZ6V36KQ,1101
+PyYAML-6.0.2.dist-info/METADATA,sha256=9-odFB5seu4pGPcEv7E8iyxNF51_uKnaNGjLAhz2lto,2060
+PyYAML-6.0.2.dist-info/RECORD,,
+PyYAML-6.0.2.dist-info/WHEEL,sha256=baMMpUvyD0gnRdCe6fvqCg8rft4FNTdLqZQ01WfKJmc,152
+PyYAML-6.0.2.dist-info/top_level.txt,sha256=rpj0IVMTisAjh_1vG3Ccf9v5jpCQwAz6cD1IVU5ZdhQ,11
+_yaml/__init__.py,sha256=04Ae_5osxahpJHa3XBZUAf4wi6XX32gR8D6X6p64GEA,1402
+_yaml/__pycache__/__init__.cpython-310.pyc,,
+yaml/__init__.py,sha256=N35S01HMesFTe0aRRMWkPj0Pa8IEbHpE9FK7cr5Bdtw,12311
+yaml/__pycache__/__init__.cpython-310.pyc,,
+yaml/__pycache__/composer.cpython-310.pyc,,
+yaml/__pycache__/constructor.cpython-310.pyc,,
+yaml/__pycache__/cyaml.cpython-310.pyc,,
+yaml/__pycache__/dumper.cpython-310.pyc,,
+yaml/__pycache__/emitter.cpython-310.pyc,,
+yaml/__pycache__/error.cpython-310.pyc,,
+yaml/__pycache__/events.cpython-310.pyc,,
+yaml/__pycache__/loader.cpython-310.pyc,,
+yaml/__pycache__/nodes.cpython-310.pyc,,
+yaml/__pycache__/parser.cpython-310.pyc,,
+yaml/__pycache__/reader.cpython-310.pyc,,
+yaml/__pycache__/representer.cpython-310.pyc,,
+yaml/__pycache__/resolver.cpython-310.pyc,,
+yaml/__pycache__/scanner.cpython-310.pyc,,
+yaml/__pycache__/serializer.cpython-310.pyc,,
+yaml/__pycache__/tokens.cpython-310.pyc,,
+yaml/_yaml.cpython-310-x86_64-linux-gnu.so,sha256=20HV-cVpIFuOuVUTmQ1-PQIbyt0n8ctfXq7JCMIfbrU,2383664
+yaml/composer.py,sha256=_Ko30Wr6eDWUeUpauUGT3Lcg9QPBnOPVlTnIMRGJ9FM,4883
+yaml/constructor.py,sha256=kNgkfaeLUkwQYY_Q6Ff1Tz2XVw_pG1xVE9Ak7z-viLA,28639
+yaml/cyaml.py,sha256=6ZrAG9fAYvdVe2FK_w0hmXoG7ZYsoYUwapG8CiC72H0,3851
+yaml/dumper.py,sha256=PLctZlYwZLp7XmeUdwRuv4nYOZ2UBnDIUy8-lKfLF-o,2837
+yaml/emitter.py,sha256=jghtaU7eFwg31bG0B7RZea_29Adi9CKmXq_QjgQpCkQ,43006
+yaml/error.py,sha256=Ah9z-toHJUbE9j-M8YpxgSRM5CgLCcwVzJgLLRF2Fxo,2533
+yaml/events.py,sha256=50_TksgQiE4up-lKo_V-nBy-tAIxkIPQxY5qDhKCeHw,2445
+yaml/loader.py,sha256=UVa-zIqmkFSCIYq_PgSGm4NSJttHY2Rf_zQ4_b1fHN0,2061
+yaml/nodes.py,sha256=gPKNj8pKCdh2d4gr3gIYINnPOaOxGhJAUiYhGRnPE84,1440
+yaml/parser.py,sha256=ilWp5vvgoHFGzvOZDItFoGjD6D42nhlZrZyjAwa0oJo,25495
+yaml/reader.py,sha256=0dmzirOiDG4Xo41RnuQS7K9rkY3xjHiVasfDMNTqCNw,6794
+yaml/representer.py,sha256=IuWP-cAW9sHKEnS0gCqSa894k1Bg4cgTxaDwIcbRQ-Y,14190
+yaml/resolver.py,sha256=9L-VYfm4mWHxUD1Vg4X7rjDRK_7VZd6b92wzq7Y2IKY,9004
+yaml/scanner.py,sha256=YEM3iLZSaQwXcQRg2l2R4MdT0zGP2F9eHkKGKnHyWQY,51279
+yaml/serializer.py,sha256=ChuFgmhU01hj4xgI8GaKv6vfM2Bujwa9i7d2FAHj7cA,4165
+yaml/tokens.py,sha256=lTQIzSVw8Mg9wv459-TjiOQe6wVziqaRlqX2_89rp54,2573

inference/.venv/lib/python3.10/site-packages/PyYAML-6.0.2.dist-info/WHEEL

@@ -0,0 +1,6 @@
+Wheel-Version: 1.0
+Generator: bdist_wheel (0.44.0)
+Root-Is-Purelib: false
+Tag: cp310-cp310-manylinux_2_17_x86_64
+Tag: cp310-cp310-manylinux2014_x86_64
+

inference/.venv/lib/python3.10/site-packages/PyYAML-6.0.2.dist-info/top_level.txt

@@ -0,0 +1,2 @@
+_yaml
+yaml

inference/.venv/lib/python3.10/site-packages/_distutils_hack/__init__.py

@@ -0,0 +1,132 @@
+import sys
+import os
+import re
+import importlib
+import warnings
+
+
+is_pypy = '__pypy__' in sys.builtin_module_names
+
+
+warnings.filterwarnings('ignore',
+                        r'.+ distutils\b.+ deprecated',
+                        DeprecationWarning)
+
+
+def warn_distutils_present():
+    if 'distutils' not in sys.modules:
+        return
+    if is_pypy and sys.version_info < (3, 7):
+        # PyPy for 3.6 unconditionally imports distutils, so bypass the warning
+        # https://foss.heptapod.net/pypy/pypy/-/blob/be829135bc0d758997b3566062999ee8b23872b4/lib-python/3/site.py#L250
+        return
+    warnings.warn(
+        "Distutils was imported before Setuptools, but importing Setuptools "
+        "also replaces the `distutils` module in `sys.modules`. This may lead "
+        "to undesirable behaviors or errors. To avoid these issues, avoid "
+        "using distutils directly, ensure that setuptools is installed in the "
+        "traditional way (e.g. not an editable install), and/or make sure "
+        "that setuptools is always imported before distutils.")
+
+
+def clear_distutils():
+    if 'distutils' not in sys.modules:
+        return
+    warnings.warn("Setuptools is replacing distutils.")
+    mods = [name for name in sys.modules if re.match(r'distutils\b', name)]
+    for name in mods:
+        del sys.modules[name]
+
+
+def enabled():
+    """
+    Allow selection of distutils by environment variable.
+    """
+    which = os.environ.get('SETUPTOOLS_USE_DISTUTILS', 'stdlib')
+    return which == 'local'
+
+
+def ensure_local_distutils():
+    clear_distutils()
+
+    # With the DistutilsMetaFinder in place,
+    # perform an import to cause distutils to be
+    # loaded from setuptools._distutils. Ref #2906.
+    add_shim()
+    importlib.import_module('distutils')
+    remove_shim()
+
+    # check that submodules load as expected
+    core = importlib.import_module('distutils.core')
+    assert '_distutils' in core.__file__, core.__file__
+
+
+def do_override():
+    """
+    Ensure that the local copy of distutils is preferred over stdlib.
+
+    See https://github.com/pypa/setuptools/issues/417#issuecomment-392298401
+    for more motivation.
+    """
+    if enabled():
+        warn_distutils_present()
+        ensure_local_distutils()
+
+
+class DistutilsMetaFinder:
+    def find_spec(self, fullname, path, target=None):
+        if path is not None:
+            return
+
+        method_name = 'spec_for_{fullname}'.format(**locals())
+        method = getattr(self, method_name, lambda: None)
+        return method()
+
+    def spec_for_distutils(self):
+        import importlib.abc
+        import importlib.util
+
+        class DistutilsLoader(importlib.abc.Loader):
+
+            def create_module(self, spec):
+                return importlib.import_module('setuptools._distutils')
+
+            def exec_module(self, module):
+                pass
+
+        return importlib.util.spec_from_loader('distutils', DistutilsLoader())
+
+    def spec_for_pip(self):
+        """
+        Ensure stdlib distutils when running under pip.
+        See pypa/pip#8761 for rationale.
+        """
+        if self.pip_imported_during_build():
+            return
+        clear_distutils()
+        self.spec_for_distutils = lambda: None
+
+    @staticmethod
+    def pip_imported_during_build():
+        """
+        Detect if pip is being imported in a build script. Ref #2355.
+        """
+        import traceback
+        return any(
+            frame.f_globals['__file__'].endswith('setup.py')
+            for frame, line in traceback.walk_stack(None)
+        )
+
+
+DISTUTILS_FINDER = DistutilsMetaFinder()
+
+
+def add_shim():
+    sys.meta_path.insert(0, DISTUTILS_FINDER)
+
+
+def remove_shim():
+    try:
+        sys.meta_path.remove(DISTUTILS_FINDER)
+    except ValueError:
+        pass