├── .gitignore ├── LICENSE ├── README.md ├── build_and_upload.sh ├── pyproject.toml ├── src └── light_hf_proxy │ └── __init__.py └── tests └── test.py /.gitignore: -------------------------------------------------------------------------------- 1 | cache 2 | *.swp 3 | 4 | # Byte-compiled / optimized / DLL files 5 | __pycache__/ 6 | *.py[cod] 7 | *$py.class 8 | 9 | # C extensions 10 | *.so 11 | 12 | # Distribution / packaging 13 | .Python 14 | build/ 15 | develop-eggs/ 16 | dist/ 17 | downloads/ 18 | eggs/ 19 | .eggs/ 20 | lib/ 21 | lib64/ 22 | parts/ 23 | sdist/ 24 | var/ 25 | wheels/ 26 | share/python-wheels/ 27 | *.egg-info/ 28 | .installed.cfg 29 | *.egg 30 | MANIFEST 31 | 32 | # PyInstaller 33 | # Usually these files are written by a python script from a template 34 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 35 | *.manifest 36 | *.spec 37 | 38 | # Installer logs 39 | pip-log.txt 40 | pip-delete-this-directory.txt 41 | 42 | # Unit test / coverage reports 43 | htmlcov/ 44 | .tox/ 45 | .nox/ 46 | .coverage 47 | .coverage.* 48 | .cache 49 | nosetests.xml 50 | coverage.xml 51 | *.cover 52 | *.py,cover 53 | .hypothesis/ 54 | .pytest_cache/ 55 | cover/ 56 | 57 | # Translations 58 | *.mo 59 | *.pot 60 | 61 | # Django stuff: 62 | *.log 63 | local_settings.py 64 | db.sqlite3 65 | db.sqlite3-journal 66 | 67 | # Flask stuff: 68 | instance/ 69 | .webassets-cache 70 | 71 | # Scrapy stuff: 72 | .scrapy 73 | 74 | # Sphinx documentation 75 | docs/_build/ 76 | 77 | # PyBuilder 78 | .pybuilder/ 79 | target/ 80 | 81 | # Jupyter Notebook 82 | .ipynb_checkpoints 83 | 84 | # IPython 85 | profile_default/ 86 | ipython_config.py 87 | 88 | # pyenv 89 | # For a library or package, you might want to ignore these files since the code is 90 | # intended to run in multiple environments; otherwise, check them in: 91 | # .python-version 92 | 93 | # pipenv 94 | # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. 95 | # However, in case of collaboration, if having platform-specific dependencies or dependencies 96 | # having no cross-platform support, pipenv may install dependencies that don't work, or not 97 | # install all needed dependencies. 98 | #Pipfile.lock 99 | 100 | # poetry 101 | # Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control. 102 | # This is especially recommended for binary packages to ensure reproducibility, and is more 103 | # commonly ignored for libraries. 104 | # https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control 105 | #poetry.lock 106 | 107 | # pdm 108 | # Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control. 109 | #pdm.lock 110 | # pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it 111 | # in version control. 112 | # https://pdm.fming.dev/#use-with-ide 113 | .pdm.toml 114 | 115 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm 116 | __pypackages__/ 117 | 118 | # Celery stuff 119 | celerybeat-schedule 120 | celerybeat.pid 121 | 122 | # SageMath parsed files 123 | *.sage.py 124 | 125 | # Environments 126 | .env 127 | .venv 128 | env/ 129 | venv/ 130 | ENV/ 131 | env.bak/ 132 | venv.bak/ 133 | 134 | # Spyder project settings 135 | .spyderproject 136 | .spyproject 137 | 138 | # Rope project settings 139 | .ropeproject 140 | 141 | # mkdocs documentation 142 | /site 143 | 144 | # mypy 145 | .mypy_cache/ 146 | .dmypy.json 147 | dmypy.json 148 | 149 | # Pyre type checker 150 | .pyre/ 151 | 152 | # pytype static type analyzer 153 | .pytype/ 154 | 155 | # Cython debug symbols 156 | cython_debug/ 157 | 158 | # PyCharm 159 | # JetBrains specific template is maintained in a separate JetBrains.gitignore that can 160 | # be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore 161 | # and can be added to the global gitignore or merged into this file. For a more nuclear 162 | # option (not recommended) you can uncomment the following to ignore the entire idea folder. 163 | #.idea/ 164 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # light-hf-proxy 2 | A light proxy solution for HuggingFace hub. It is supposed to work with diffusers, transformers and datasets from HuggingFace. 3 | 4 | # Install / 安装 5 | 6 | ```bash 7 | pip install light-hf-proxy --index-url https://pypi.org/simple/ 8 | ``` 9 | 10 | # Usage / 使用 11 | 12 | ```python 13 | # Just import light_hf_proxy before any huggingface libraries: transformers, diffusers, etc. 14 | import light_hf_proxy 15 | 16 | # Do whatever you normally do. 17 | from transformers import AutoTokenizer, AutoModelForCausalLM, TextStreamer 18 | 19 | model_path = "LinkSoul/Chinese-Llama-2-7b" 20 | cache_dir = "cache" 21 | 22 | tokenizer = AutoTokenizer.from_pretrained(model_path, use_fast=False, cache_dir=cache_dir) 23 | model = AutoModelForCausalLM.from_pretrained(model_path, cache_dir=cache_dir).half().cuda() 24 | streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True) 25 | 26 | instruction = """[INST] <>\nYou are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. 27 | 28 | If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.\n<>\n\n{} [/INST]""" 29 | 30 | prompt = instruction.format("用中文回答，When is the best time to visit Beijing, and do you have any suggestions for me?") 31 | generate_ids = model.generate(tokenizer(prompt, return_tensors='pt').input_ids.cuda(), max_new_tokens=4096, streamer=streamer) 32 | ``` 33 | 34 | Just import light_hf_proxy and no more steps needed. 35 | 36 | We only provide relay service for the following repos so as to support our own research: 37 | - [LinkSoul.AI](https://huggingface.co/LinkSoul) 38 | - [BAAI](https://huggingface.co/BAAI) 39 | - [OpenAI](https://huggingface.co/openai) 40 | 41 | Any other repos will fallback to [https://hf-mirror.com/](https://hf-mirror.com/), which is a mirror server maintained by [padeoe](https://gist.github.com/padeoe). 42 | 43 | ## Use private relay server or mirror 44 | 45 | You can setup your own relay server or mirror to speedup model downloading. Though, we are not going to provide any tutorial or information about how to setup relay server or mirror. 46 | 47 | To use private relay server, you can use this library as following: 48 | ```bash 49 | RELAY_SERVER=https://your.relay.server python script.py 50 | ``` 51 | 52 | To use private mirror, you can use this library as following: 53 | ```bash 54 | HF_MIRROR_URL=https://your.mirror.server python script.py 55 | ``` 56 | 57 | 58 | # 项目声明 59 | 60 | 本项目是一个开源项目，仅供学术研究使用。请注意以下声明： 61 | 62 | 本项目的目的是为了促进学术研究和技术探索。项目内容仅供研究人员和开发者参考和学习之用。 63 | 64 | 本项目不应用于商业场景或其他非学术研究的用途。禁止将本项目用于商业目的，包括但不限于商业产品、服务或任何形式的盈利活动。 65 | 66 | 本项目的代码和资源仅供个人学习和研究使用。未经许可，不得将本项目的代码、数据或任何相关内容用于其他项目或产品。 67 | 68 | 本项目的创建者和贡献者不对不正确使用本项目导致的后果负责。使用者应当承担使用本项目所产生的一切风险和责任。 69 | 70 | 请遵守适用的法律法规和伦理准则，确保在使用本项目时不会侵犯他人的权益，包括但不限于知识产权和隐私权。 71 | 72 | 如果您有任何关于本项目的疑问、建议或发现了任何违反上述声明的行为，请及时与我们联系。 73 | 74 | 过使用本项目，您表示您已阅读、理解并同意遵守上述声明。 75 | 76 | # Project Statement 77 | 78 | This project is an open-source project intended for academic research purposes only. Please note the following statement: 79 | 80 | The purpose of this project is to facilitate academic research and technical exploration. The project content is intended for reference and learning purposes for researchers and developers. 81 | 82 | This project should not be used for commercial purposes or any other non-academic research purposes. It is strictly prohibited to use this project for commercial purposes, including but not limited to commercial products, services, or any form of profit-making activities. 83 | 84 | The code and resources of this project are intended for personal learning and research use. Without permission, the code, data, or any related content of this project should not be used for other projects or products. 85 | 86 | The creators and contributors of this project are not responsible for any consequences resulting from the incorrect use of this project. Users should assume all risks and liabilities associated with the use of this project. 87 | 88 | Please comply with applicable laws, regulations, and ethical guidelines to ensure that the use of this project does not infringe upon the rights of others, including but not limited to intellectual property rights and privacy rights. 89 | 90 | If you have any questions, suggestions, or if you notice any behavior that violates the above statement regarding this project, please contact us promptly. 91 | 92 | By using this project, you acknowledge that you have read, understood, and agreed to comply with the above statement. 93 | -------------------------------------------------------------------------------- /build_and_upload.sh: -------------------------------------------------------------------------------- 1 | #!/bin/sh 2 | 3 | python -m build && twine upload dist/* 4 | -------------------------------------------------------------------------------- /pyproject.toml: -------------------------------------------------------------------------------- 1 | [project] 2 | name = "light-hf-proxy" 3 | version = "0.0.4" 4 | authors = [ 5 | { name="Yemin Shi", email="shiyemin2@gmail.com" }, 6 | ] 7 | description = "A light proxy solution for HuggingFace hub." 8 | readme = "README.md" 9 | requires-python = ">=3.7" 10 | license = {file = "LICENSE"} 11 | classifiers = [ 12 | "Programming Language :: Python :: 3", 13 | "License :: OSI Approved :: Apache Software License", 14 | "Operating System :: OS Independent", 15 | ] 16 | dependencies = [ 17 | "huggingface_hub" 18 | ] 19 | 20 | [project.urls] 21 | "Homepage" = "https://github.com/shiyemin/light-hf-proxy" 22 | "Bug Tracker" = "https://github.com/shiyemin/light-hf-proxy/issues" 23 | -------------------------------------------------------------------------------- /src/light_hf_proxy/__init__.py: -------------------------------------------------------------------------------- 1 | import os 2 | import requests 3 | import huggingface_hub.utils 4 | 5 | FORCE_USE_RELAY_SERVER = os.environ.get("FORCE_USE_RELAY_SERVER", False) 6 | 7 | # Relay servers and mirror urls 8 | RELAY_SERVER = os.environ.get("RELAY_SERVER", "https://relay.yimo.space") 9 | RELAY_SERVER_SUPPORT_PREFIX = os.environ.get("RELAY_SERVER_SUPPORT_PREFIX", "https://huggingface.co/LinkSoul,https://huggingface.co/datasets/LinkSoul,https://huggingface.co/BAAI,https://huggingface.co/datasets/BAAI,https://huggingface.co/openai,https://cdn-lfs.huggingface.co") 10 | 11 | HF_MIRROR_URL = os.environ.get("HF_MIRROR_URL", "https://hf-mirror.com") 12 | HF_LFS_MIRROR_URL = os.environ.get("HF_LFS_MIRROR_URL", "https://lfs5.hf-mirror.com") 13 | 14 | # Deinfe official urls 15 | HF_OFFICIAL_URL = os.environ.get("HF_OFFICIAL_URL", "https://huggingface.co") 16 | HF_LFS_OFFICIAL_URL = os.environ.get("HF_LFS_OFFICIAL_URL", "https://cdn-lfs.huggingface.co") 17 | 18 | 19 | # Preprocess 20 | RELAY_SERVER_SUPPORT_PREFIX = [p.lower() for p in RELAY_SERVER_SUPPORT_PREFIX.split(",")] 21 | 22 | class ProxySession(requests.Session): 23 | def request(self, method, url, *args, **kwargs): 24 | url = self.patch_url(url) 25 | 26 | ret = super().request(method, url, *args, **kwargs) 27 | return ret 28 | 29 | def patch_url(self, url): 30 | # Only patch hf and lfs urls 31 | if (not url.startswith(HF_OFFICIAL_URL)) and \ 32 | (not url.startswith(HF_LFS_OFFICIAL_URL)): 33 | return url 34 | # Force use relay server 35 | if FORCE_USE_RELAY_SERVER: 36 | return os.path.join(RELAY_SERVER, url) 37 | # If url match relay server prefix, use relay server 38 | for p in RELAY_SERVER_SUPPORT_PREFIX: 39 | if url.lower().startswith(p): 40 | return os.path.join(RELAY_SERVER, url) 41 | # If url match official prefix, replace it 42 | if url.startswith(HF_OFFICIAL_URL): 43 | return url.replace(HF_OFFICIAL_URL, HF_MIRROR_URL) 44 | # It's a bad choice to replace lfs prefix. We put it here just in case. 45 | if url.startswith(HF_LFS_OFFICIAL_URL): 46 | return url.replace(HF_LFS_OFFICIAL_URL, HF_LFS_MIRROR_URL) 47 | 48 | # You are not supposed to be here 49 | return url 50 | 51 | def _proxied_backend_factory() -> requests.Session: 52 | session = ProxySession() 53 | session.mount("http://", huggingface_hub.utils._http.UniqueRequestIdAdapter()) 54 | session.mount("https://", huggingface_hub.utils._http.UniqueRequestIdAdapter()) 55 | return session 56 | 57 | def proxied_request(method, url, **kwargs): 58 | with ProxySession() as session: 59 | return session.request(method=method, url=url, **kwargs) 60 | 61 | huggingface_hub.utils._http.configure_http_backend(_proxied_backend_factory) 62 | requests.request = proxied_request 63 | 64 | 65 | if __name__ == "__main__": 66 | from transformers import AutoTokenizer, AutoModelForCausalLM, TextStreamer 67 | 68 | model_path = "LinkSoul/Chinese-Llama-2-7b" 69 | cache_dir = "cache" 70 | 71 | tokenizer = AutoTokenizer.from_pretrained(model_path, use_fast=False, cache_dir=cache_dir) 72 | model = AutoModelForCausalLM.from_pretrained(model_path, cache_dir=cache_dir).half().cuda() 73 | streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True) 74 | 75 | instruction = """[INST] <>\nYou are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. 76 | 77 | If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.\n<>\n\n{} [/INST]""" 78 | 79 | prompt = instruction.format("用中文回答，When is the best time to visit Beijing, and do you have any suggestions for me?") 80 | generate_ids = model.generate(tokenizer(prompt, return_tensors='pt').input_ids.cuda(), max_new_tokens=4096, streamer=streamer) 81 | -------------------------------------------------------------------------------- /tests/test.py: -------------------------------------------------------------------------------- 1 | import light_hf_proxy 2 | 3 | from transformers import AutoTokenizer, AutoModelForCausalLM, TextStreamer 4 | 5 | model_path = "LinkSoul/Chinese-Llama-2-7b" 6 | cache_dir = "cache" 7 | 8 | tokenizer = AutoTokenizer.from_pretrained(model_path, use_fast=False, cache_dir=cache_dir) 9 | model = AutoModelForCausalLM.from_pretrained(model_path, cache_dir=cache_dir).half().cuda() 10 | streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True) 11 | 12 | instruction = """[INST] <>\nYou are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. 13 | 14 | If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.\n<>\n\n{} [/INST]""" 15 | 16 | prompt = instruction.format("用中文回答，When is the best time to visit Beijing, and do you have any suggestions for me?") 17 | generate_ids = model.generate(tokenizer(prompt, return_tensors='pt').input_ids.cuda(), max_new_tokens=4096, streamer=streamer) 18 | --------------------------------------------------------------------------------