Home / datawhalechina / self-llm
Repository Analysis

datawhalechina/self-llm

《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程

4.4 Likely human-written View on GitHub
4.4
Adjusted Score
4.4
Raw Score
100%
Time Factor
2026-04-24
Last Push
30,676
Stars
Jupyter Notebook
Language
97,628
Lines of Code
366
Files
245
Pattern Hits
2026-05-31
Scan Date

Score History

Severity Breakdown

CRITICAL 0HIGH 32MEDIUM 26LOW 187

Pattern Findings

245 matches across 11 categories. Click a row to expand file-level details.

Cross-File Repetition30 hits · 150 pts
SeverityFileLineSnippet
HIGHmodels/ChatGLM/05-ChatGLM3-6B接入LangChain搭建知识库助手.md0使用以下上下文来回答最后的问题。如果你不知道答案，就说你不知道，不要试图编造答案。尽量使答案简明扼要。总是在回答的最后说“谢谢你的提问！”。 {context} 问题: {question} 有用的回答:
HIGHmodels/InternLM/06-InternLM接入LangChain搭建知识库助手.md0使用以下上下文来回答最后的问题。如果你不知道答案，就说你不知道，不要试图编造答案。尽量使答案简明扼要。总是在回答的最后说“谢谢你的提问！”。 {context} 问题: {question} 有用的回答:
HIGHmodels/Atom/03-Atom-7B-Chat 接入langchain搭建知识库助手.md0使用以下上下文来回答最后的问题。如果你不知道答案，就说你不知道，不要试图编造答案。尽量使答案简明扼要。总是在回答的最后说“谢谢你的提问！”。 {context} 问题: {question} 有用的回答:
HIGHmodels/Qwen/07-Qwen-7B-Chat 接入langchain搭建知识库助手.md0使用以下上下文来回答最后的问题。如果你不知道答案，就说你不知道，不要试图编造答案。尽量使答案简明扼要。总是在回答的最后说“谢谢你的提问！”。 {context} 问题: {question} 有用的回答:
HIGHmodels/Yi/02-Yi-6B-Chat 接入langchain搭建知识库助手.md0使用以下上下文来回答最后的问题。如果你不知道答案，就说你不知道，不要试图编造答案。尽量使答案简明扼要。总是在回答的最后说“谢谢你的提问！”。 {context} 问题: {question} 有用的回答:
HIGHmodels/ChatGLM/05-ChatGLM3-6B接入LangChain搭建知识库助手.md0使用以下上下文来回答最后的问题。如果你不知道答案，就说你不知道，不要试图编造答 案。尽量使答案简明扼要。总是在回答的最后说“谢谢你的提问！”。 {context} 问题: {question} 有用的回答:
HIGH…ChatGLM/05-ChatGLM3-6B接入LangChain搭建知识库助手/run_gradio.py0使用以下上下文来回答最后的问题。如果你不知道答案，就说你不知道，不要试图编造答 案。尽量使答案简明扼要。总是在回答的最后说“谢谢你的提问！”。 {context} 问题: {question} 有用的回答:
HIGHmodels/InternLM/06-InternLM接入LangChain搭建知识库助手.md0使用以下上下文来回答最后的问题。如果你不知道答案，就说你不知道，不要试图编造答 案。尽量使答案简明扼要。总是在回答的最后说“谢谢你的提问！”。 {context} 问题: {question} 有用的回答:
HIGH…s/InternLM/06-InternLM接入LangChain搭建知识库助手/run_gradio.py0使用以下上下文来回答最后的问题。如果你不知道答案，就说你不知道，不要试图编造答 案。尽量使答案简明扼要。总是在回答的最后说“谢谢你的提问！”。 {context} 问题: {question} 有用的回答:
HIGHmodels/Atom/03-Atom-7B-Chat 接入langchain搭建知识库助手.md0使用以下上下文来回答最后的问题。如果你不知道答案，就说你不知道，不要试图编造答 案。尽量使答案简明扼要。总是在回答的最后说“谢谢你的提问！”。 {context} 问题: {question} 有用的回答:
HIGHmodels/Qwen/07-Qwen-7B-Chat 接入langchain搭建知识库助手.md0使用以下上下文来回答最后的问题。如果你不知道答案，就说你不知道，不要试图编造答 案。尽量使答案简明扼要。总是在回答的最后说“谢谢你的提问！”。 {context} 问题: {question} 有用的回答:
HIGH…/Qwen/07-Qwen-7B-Chat 接入langchain搭建知识库助手/run_gradio.py0使用以下上下文来回答最后的问题。如果你不知道答案，就说你不知道，不要试图编造答 案。尽量使答案简明扼要。总是在回答的最后说“谢谢你的提问！”。 {context} 问题: {question} 有用的回答:
HIGHmodels/ChatGLM/05-ChatGLM3-6B接入LangChain搭建知识库助手.md0提醒：<br> 1. 初始化数据库时间可能较长，请耐心等待。 2. 使用中如果出现异常，将会在文本输入框进行展示，请不要惊慌。 <br>
HIGH…ChatGLM/05-ChatGLM3-6B接入LangChain搭建知识库助手/run_gradio.py0提醒：<br> 1. 初始化数据库时间可能较长，请耐心等待。 2. 使用中如果出现异常，将会在文本输入框进行展示，请不要惊慌。 <br>
HIGHmodels/InternLM/06-InternLM接入LangChain搭建知识库助手.md0提醒：<br> 1. 初始化数据库时间可能较长，请耐心等待。 2. 使用中如果出现异常，将会在文本输入框进行展示，请不要惊慌。 <br>
HIGH…s/InternLM/06-InternLM接入LangChain搭建知识库助手/run_gradio.py0提醒：<br> 1. 初始化数据库时间可能较长，请耐心等待。 2. 使用中如果出现异常，将会在文本输入框进行展示，请不要惊慌。 <br>
HIGHmodels/Atom/03-Atom-7B-Chat 接入langchain搭建知识库助手.md0提醒：<br> 1. 初始化数据库时间可能较长，请耐心等待。 2. 使用中如果出现异常，将会在文本输入框进行展示，请不要惊慌。 <br>
HIGH…/Atom/03-Atom-7B-Chat 接入langchain搭建知识库助手/run_gradio.py0提醒：<br> 1. 初始化数据库时间可能较长，请耐心等待。 2. 使用中如果出现异常，将会在文本输入框进行展示，请不要惊慌。 <br>
HIGHmodels/Qwen/07-Qwen-7B-Chat 接入langchain搭建知识库助手.md0提醒：<br> 1. 初始化数据库时间可能较长，请耐心等待。 2. 使用中如果出现异常，将会在文本输入框进行展示，请不要惊慌。 <br>
HIGH…/Qwen/07-Qwen-7B-Chat 接入langchain搭建知识库助手/run_gradio.py0提醒：<br> 1. 初始化数据库时间可能较长，请耐心等待。 2. 使用中如果出现异常，将会在文本输入框进行展示，请不要惊慌。 <br>
HIGHmodels/Gemma3/04-Gemma3-4b evalscope智商情商评测.md0以下为多个ai服务的api端点地址，用于配置任务： - siliconflow: https://api.siliconflow.cn/v1/chat/completions - dashscope: https://dashscope.a
HIGHmodels/Gemma4/04-Gemma4-E4B-it evalscope智商情商评测.md0以下为多个ai服务的api端点地址，用于配置任务： - siliconflow: https://api.siliconflow.cn/v1/chat/completions - dashscope: https://dashscope.a
HIGHmodels/Qwen3/04-Qwen3-8B EvalScope智商情商评测.md0以下为多个ai服务的api端点地址，用于配置任务： - siliconflow: https://api.siliconflow.cn/v1/chat/completions - dashscope: https://dashscope.a
HIGH…3B-Instruct/04-Hunyuan-A13B-Instruct EvalScope 并发测试.md0以下为多个ai服务的api端点地址，用于配置任务： - siliconflow: https://api.siliconflow.cn/v1/chat/completions - dashscope: https://dashscope.a
HIGHmodels/Gemma3/6-gemma3-4B-itGRPO微调及通过swanlab可视化.md0you are given a problem. think about the problem and provide your working out. place it between {reasoning_start} and {r
HIGHmodels/Gemma4/6-gemma4-E4B-itGRPO微调及通过swanlab可视化.md0you are given a problem. think about the problem and provide your working out. place it between {reasoning_start} and {r
HIGHmodels/Qwen3/10-Qwen3-8B GRPO微调及通过swanlab可视化.md0you are given a problem. think about the problem and provide your working out. place it between {reasoning_start} and {r
HIGHmodels/phi4/05-Phi-4-Lora 微调 命名实体识别.md0你是一个文本实体识别领域的专家，你需要从给定的句子中提取 - mic - dru - pro - ite - dis - sym - equ - bod - dep 这些实体. 以 json 格式输出, 如 {"entity_text":
HIGHmodels/phi4/05-Phi-4-Lora 微调 命名实体识别.md0你是一个文本实体识别领域的专家，你需要从给定的句子中提取 - mic - dru - pro - ite - dis - sym - equ - bod - dep 这些实体. 以 json 格式输出, 如 {"entity_text":
HIGHmodels/phi4/05-Phi-4-Lora-Ner.py0你是一个文本实体识别领域的专家，你需要从给定的句子中提取 - mic - dru - pro - ite - dis - sym - equ - bod - dep 这些实体. 以 json 格式输出, 如 {"entity_text":
Excessive Try-Catch Wrapping112 hits · 122 pts
SeverityFileLineSnippet
MEDIUMutils.py124 print(f"Error: {data['message']}")
LOWmodels_amd/gemma3/2-gemma3-4b-it 模型服务部署.md86 except Exception as e:
LOWmodels_amd/qwen3/1-Qwen3-8B-AMD部署调用.md86 except Exception as e:
LOWmodels_amd/qwen3/1-Qwen3-8B-AMD部署调用.md196 except Exception as e:
LOWmodels_amd/qwen3/1-Qwen3-8B-AMD部署调用.md253 except Exception as e:
LOWmodels_amd/qwen3/1-Qwen3-8B-AMD部署调用.md266 except Exception as e:
LOWmodels_amd/qwen3/1-Qwen3-8B-AMD部署调用.md287 except Exception as e:
LOWmodels_amd/qwen3/1-Qwen3-8B-AMD部署调用.md362 except Exception as e:
LOWmodels/Llama4/01-Llama4-对话助手/01-Llama4-对话助手.md277 except Exception as e:
LOWmodels/Llama4/01-Llama4-对话助手/01-Llama4-对话助手.md291 except Exception as e:
MEDIUMmodels/Llama4/01-Llama4-对话助手/01-Llama4-对话助手.md217def generate():
MEDIUMmodels/Llama4/01-Llama4-对话助手/01-Llama4-对话助手.md281def clear_history():
LOWmodels/Llama4/01-Llama4-对话助手/app/app.py129 except Exception as e:
LOWmodels/Llama4/01-Llama4-对话助手/app/app.py143 except Exception as e:
MEDIUMmodels/Llama4/01-Llama4-对话助手/app/app.py69def generate():
MEDIUMmodels/Llama4/01-Llama4-对话助手/app/app.py133def clear_history():
LOWmodels/Qwen3-VL/02-Qwen3-VL-4B-Instruct FastApi 部署调用.md188 except Exception as e:
LOWmodels/Qwen3-VL/02-Qwen3-VL-4B-Instruct FastApi 部署调用.md255 except Exception as e:
LOWmodels/Qwen3-VL/02-Qwen3-VL-4B-Instruct FastApi 部署调用.md294 except Exception as e:
LOWmodels/Qwen3-VL/02-Qwen3-VL-4B-Instruct FastApi 部署调用.md345 except Exception as e:
LOWmodels/Qwen3-VL/02-Qwen3-VL-4B-Instruct FastApi 部署调用.md535 except Exception as e:
LOWmodels/Qwen3-VL/02-Qwen3-VL-4B-Instruct FastApi 部署调用.md599 except Exception as e:
LOWmodels/Qwen3-VL/02-Qwen3-VL-4B-Instruct FastApi 部署调用.md650 except Exception as e:
LOW…VL/05-Qwen3-VL-4B-Instruct Lora 可视化微调案例 - LaTexOCR.md725 except Exception:
LOW…VL/05-Qwen3-VL-4B-Instruct Lora 可视化微调案例 - LaTexOCR.md824 except Exception:
LOW…VL/05-Qwen3-VL-4B-Instruct Lora 可视化微调案例 - LaTexOCR.md836 except Exception:
LOW…VL/05-Qwen3-VL-4B-Instruct Lora 可视化微调案例 - LaTexOCR.md838 except Exception as e:
LOW…n3-VL/Qwen3-VL-4B-Instruct Lora 可视化微调案例 - LaTexOCR.md706 except Exception:
LOW…n3-VL/Qwen3-VL-4B-Instruct Lora 可视化微调案例 - LaTexOCR.md805 except Exception:
LOW…n3-VL/Qwen3-VL-4B-Instruct Lora 可视化微调案例 - LaTexOCR.md817 except Exception:
LOW…n3-VL/Qwen3-VL-4B-Instruct Lora 可视化微调案例 - LaTexOCR.md819 except Exception as e:
LOW…L-4B-Instruct FastApi 参考代码/api_server_qwen3vl_video.py126 except Exception as e:
LOW…1-Qwen3-VL-4B-Instruct FastApi 参考代码/test_simple_api.py25 except Exception as e:
LOW…1-Qwen3-VL-4B-Instruct FastApi 参考代码/test_simple_api.py64 except Exception as e:
LOW…1-Qwen3-VL-4B-Instruct FastApi 参考代码/test_simple_api.py115 except Exception as e:
LOW…01-Qwen3-VL-4B-Instruct FastApi 参考代码/test_video_api.py28 except Exception as e:
LOW…01-Qwen3-VL-4B-Instruct FastApi 参考代码/test_video_api.py79 except Exception as e:
LOW…-4B-Instruct FastApi 参考代码/api_server_qwen3vl_simple.py125 except Exception as e:
LOW…uct Lora 可视化微调案例 - LaTexOCR/compare_qwen3_vl_infer.py63 except Exception:
LOW…uct Lora 可视化微调案例 - LaTexOCR/compare_qwen3_vl_infer.py162 except Exception:
LOW…uct Lora 可视化微调案例 - LaTexOCR/compare_qwen3_vl_infer.py174 except Exception:
LOW…uct Lora 可视化微调案例 - LaTexOCR/compare_qwen3_vl_infer.py176 except Exception as e:
LOWmodels/gpt-oss/4-gpt-oss-20b Lora 微调及 SwanLab 可视化记录.md245except Exception as e:
LOWmodels/gpt-oss/3-gpt-oss-20b lmstudio 本地部署调用.md130 except Exception as exc:
LOWmodels/ChatGLM/05-ChatGLM3-6B接入LangChain搭建知识库助手.md398 except Exception as e:
LOWmodels/ChatGLM/Extra-ChatGLM3-6B-Pipeline.md341except Exception as e:
LOWmodels/ChatGLM/Extra-ChatGLM3-6B-Pipeline.md404 except Exception as e:
LOWmodels/ChatGLM/Extra-ChatGLM3-6B-Pipeline.md457 except Exception as e:
LOWmodels/ChatGLM/Extra-ChatGLM3-6B-Pipeline.md491 except Exception as e:
LOW…ChatGLM/05-ChatGLM3-6B接入LangChain搭建知识库助手/run_gradio.py71 except Exception as e:
LOWmodels/InternLM/06-InternLM接入LangChain搭建知识库助手.md401 except Exception as e:
LOW…s/InternLM/06-InternLM接入LangChain搭建知识库助手/run_gradio.py61 except Exception as e:
LOW…VL/02-Qwen2-VL-2B-Instruct Web Demo 参考代码/mm_qwen2vl.py167 except Exception:
LOWmodels/Qwen2.5/06-Qwen2.5-7B-Instruct o1-like 推理链实现.md118 except Exception as e:
LOWmodels/Gemma3/8-gemma3-4b-it 模型服务部署.md86 except Exception as e:
LOWmodels/Gemma3/01-gemma-3-4b-it FastApi 部署调用.md136 except Exception as e:
LOWmodels/Gemma3/01-gemma-3-4b-it FastApi 部署调用.md146 except Exception as e:
LOWmodels/Gemma3/01-gemma-3-4b-it FastApi 部署调用.md210 except Exception as e:
LOWmodels/Atom/02-Atom-7B-Chat Lora 微调.md298except Exception as e:
LOWmodels/Atom/03-Atom-7B-Chat 接入langchain搭建知识库助手.md443 except Exception as e:
52 more matches not shown…
Decorative Section Separators16 hits · 57 pts
SeverityFileLineSnippet
MEDIUMmodels/Qwen3/10-Qwen3-8B GRPO微调及通过swanlab可视化.md427# ========================
MEDIUMmodels/Qwen3/10-Qwen3-8B GRPO微调及通过swanlab可视化.md429# ========================
MEDIUMmodels_mlx/run_app_gradio.py20# ============================================================
MEDIUMmodels_mlx/run_app_gradio.py22# ============================================================
MEDIUMmodels_mlx/run_app_gradio.py131# ============================================================
MEDIUMmodels_mlx/run_app_gradio.py133# ============================================================
MEDIUMmodels_mlx/run_app_gradio.py307# ============================================================
MEDIUMmodels_mlx/run_app_gradio.py309# ============================================================
MEDIUMmodels_mlx/modules/framework.py104# ============================================================
MEDIUMmodels_mlx/modules/framework.py106# ============================================================
MEDIUMmodels_mlx/modules/download_model.py14# ============================================================
MEDIUMmodels_mlx/modules/download_model.py16# ============================================================
MEDIUMmodels_mlx/modules/download_model.py23# ============================================================
MEDIUMmodels_mlx/modules/download_model.py25# ============================================================
MEDIUMmodels_mlx/modules/download_model.py183# ============================================================
MEDIUMmodels_mlx/modules/download_model.py185# ============================================================
Unused Imports34 hits · 34 pts
SeverityFileLineSnippet
LOWutils.py2
LOWutils.py3
LOW…uct Lora 可视化微调案例 - LaTexOCR/compare_qwen3_vl_infer.py2
LOW…uct Lora 可视化微调案例 - LaTexOCR/compare_qwen3_vl_infer.py3
LOW…uct Lora 可视化微调案例 - LaTexOCR/compare_qwen3_vl_infer.py3
LOW…ChatGLM/05-ChatGLM3-6B接入LangChain搭建知识库助手/run_gradio.py15
LOW…s/InternLM/06-InternLM接入LangChain搭建知识库助手/run_gradio.py5
LOW…2B-Instruct FastApi 参考代码/api_server_image_and_video.py3
LOW…-Qwen2-VL-2B-Instruct FastApi 参考代码/api_server_image.py3
LOW…-Instruct FastApi 参考代码/qwen_vl_utils/vision_process.py1
LOW…/Atom/03-Atom-7B-Chat 接入langchain搭建知识库助手/run_gradio.py5
LOWmodels/Atom/02-Atom-7B-Chat-Lora/train.py15
LOWmodels/Atom/02-Atom-7B-Chat-Lora/train.py18
LOWmodels/Gemma4/api.py2
LOW…dels/MiniCPM-o/04-MiniCPM-0-2.6 Lora微调 参考代码/trainer.py5
LOW…CPM-o/04-MiniCPM-0-2.6 Lora微调 参考代码/minicpm_datasets.py2
LOW…CPM-o/04-MiniCPM-0-2.6 Lora微调 参考代码/minicpm_datasets.py5
LOW…CPM-o/04-MiniCPM-0-2.6 Lora微调 参考代码/minicpm_datasets.py8
LOW…CPM-o/04-MiniCPM-0-2.6 Lora微调 参考代码/minicpm_datasets.py8
LOW…CPM-o/04-MiniCPM-0-2.6 Lora微调 参考代码/minicpm_datasets.py9
LOW…CPM-o/04-MiniCPM-0-2.6 Lora微调 参考代码/minicpm_datasets.py9
LOW…CPM-o/04-MiniCPM-0-2.6 Lora微调 参考代码/minicpm_datasets.py16
LOW…CPM-o/04-MiniCPM-0-2.6 Lora微调 参考代码/minicpm_datasets.py16
LOWmodels/MiniCPM/train.py6
LOWmodels/Kimi-VL/01-Kimi-VL-对话助手/app/app.py9
LOW…/Qwen/07-Qwen-7B-Chat 接入langchain搭建知识库助手/run_gradio.py5
LOWmodels/XVERSE/code/LLM.py4
LOWmodels/XVERSE/code/LLM.py4
LOWmodels/XVERSE/code/model_download.py1
LOWmodels/XVERSE/code/model_download.py2
LOWmodels/XVERSE/code/model_download.py2
LOWmodels/XVERSE/code/model_download.py3
LOWmodels/BlueLM/04-BlueLM-7B-Chat Lora 微调.py3
LOWexamples/Chat-嬛嬛/train.py4
Deep Nesting19 hits · 19 pts
SeverityFileLineSnippet
LOWutils.py91
LOW…/ChatGLM/05-ChatGLM3-6B接入LangChain搭建知识库助手/create_db.py23
LOW…els/InternLM/06-InternLM接入LangChain搭建知识库助手/creat_db.py11
LOW…-Instruct FastApi 参考代码/qwen_vl_utils/vision_process.py82
LOW…-Instruct FastApi 参考代码/qwen_vl_utils/vision_process.py303
LOW…VL/02-Qwen2-VL-2B-Instruct Web Demo 参考代码/mm_qwen2vl.py54
LOW…VL/02-Qwen2-VL-2B-Instruct Web Demo 参考代码/mm_qwen2vl.py229
LOW…ls/Atom/03-Atom-7B-Chat 接入langchain搭建知识库助手/creat_db.py13
LOWmodels/Gemma4/verify_gemma4_tutorials.py66
LOWmodels/Gemma4/verify_gemma4_tutorials.py134
LOWmodels/Gemma4/api.py107
LOW…CPM-o/04-MiniCPM-0-2.6 Lora微调 参考代码/minicpm_datasets.py231
LOW…CPM-o/04-MiniCPM-0-2.6 Lora微调 参考代码/minicpm_datasets.py271
LOW…CPM-o/04-MiniCPM-0-2.6 Lora微调 参考代码/minicpm_datasets.py310
LOW…CPM-o/04-MiniCPM-0-2.6 Lora微调 参考代码/minicpm_datasets.py427
LOWmodels/Kimi-VL/01-Kimi-VL-对话助手/app/app.py167
LOW…ls/Qwen/07-Qwen-7B-Chat 接入langchain搭建知识库助手/creat_db.py11
LOWmodels_mlx/run_app_gradio.py329
LOWmodels_mlx/modules/download_model.py120
Hyper-Verbose Identifiers13 hits · 12 pts
SeverityFileLineSnippet
LOWmodels/Gemma3/6-gemma3-4B-itGRPO微调及通过swanlab可视化.md258def match_format_approximately(completions, **kwargs):
LOWmodels/Gemma4/verify_gemma4_tutorials.py66def test_fastapi_smoke_with_mock() -> bool:
LOWmodels/Gemma4/6-gemma4-E4B-itGRPO微调及通过swanlab可视化.md260def match_format_approximately(completions, **kwargs):
LOWmodels/phi4/06-Phi-4-GRPO及swanlab可视化.md229def strict_format_reward_func(completions, **kwargs) -> list[float]:
LOWmodels/MiniCPM-o/04-MiniCPM-0-2.6 Lora微调.md259def make_supervised_data_module(
LOWmodels/MiniCPM-o/04-MiniCPM-0-2.6 Lora微调 参考代码/train.py17def make_supervised_data_module(
LOW…CPM-o/04-MiniCPM-0-2.6 Lora微调 参考代码/minicpm_datasets.py199def conversation_to_ids_minicpm(conversation, tokenizer):
LOWmodels/Qwen3/10-Qwen3-8B GRPO微调及通过swanlab可视化.md474def match_format_approximately(completions, **kwargs):
LOW…n-A13B-Instruct/03-Hunyuan-A13B-Instruct-SGLang部署调用.md157def chatcompletionwiththinkbyargs(messages, enable_thinking=True):
LOW…l-Qwen/05-DeepSeek-R1-0528-Qwen3-8B-GRPO及swanlab可视化.md198def match_format_approximately(completions, **kwargs):
LOW…l-Qwen/05-DeepSeek-R1-0528-Qwen3-8B-GRPO及swanlab可视化.md287def format_and_language_reward_func(completions, **kwargs):
LOWexamples/数字生命/readme.md23def convert_to_sharegpt_format(original_data,new_system_value=None):
LOWexamples/Tianji-天机/readme.md225def extract_and_merge_conversations(folder_path, output_file):
Over-Commented Block11 hits · 11 pts
SeverityFileLineSnippet
LOWmodels/GLM-4/04-GLM-4-9B-Chat vLLM 部署调用.md101 # tokenizer = AutoTokenizer.from_pretrained(model, use_fast=False) # 加载分词器后传入vLLM 模型，但不是必要的。
LOWmodels/Qwen2.5/03-Qwen2.5-7B-Instruct vLLM 部署调用.md101
LOWmodels/MiniCPM-o/03-MiniCPM-o-2.6 多模态语音能力.md141
LOWmodels/Qwen2/04-Qwen2-7B-Instruct vLLM 部署调用.md121 # tokenizer = AutoTokenizer.from_pretrained(model, use_fast=False)
LOWmodels/Qwen/08-Qwen-7B-Chat Lora 低精度微调.py61 tokenized_id = ds.map(process_func, remove_columns=ds.column_names)
LOWmodels/Qwen1.5/07-Qwen1.5-7B-Chat vLLM 推理部署调用.md101if __name__ == "__main__":
LOWmodels/XVERSE/code/data_format.py21with open('ruozhiba.json', 'w', encoding='utf-8') as f:
LOWmodels/InternLM3/04-InternLM3-8B-Instruct LoRA.md201> 注意：此处要记得修改为自己的模型路径哦~
LOWmodels/InternLM3/04-InternLM3-8B-Instruct LoRA.md221# )
LOW…still-Qwen/04-DeepSeek-R1-Distill-Qwen-7B vLLM 部署调用.md101 # tokenizer = AutoTokenizer.from_pretrained(model, use_fast=False)
LOWexamples/Tianji-天机/readme.md41from zhipuai import ZhipuAI
Redundant / Tautological Comments7 hits · 10 pts
SeverityFileLineSnippet
LOWutils.py21 # Read files
LOWutils.py61 # Check if the task contains "Lora" or "微调" (case-insensitive)
LOWutils.py84 # Print results
LOWmodels/GLM-4/benchmark_throughput.py155 # Check if we can add more requests to the batch.
LOWmodels/Qwen2.5/benchmark_throughput.py257 # Check if we can add more requests to the batch.
LOWmodels/Qwen2/benchmark_throughput.py154 # Check if we can add more requests to the batch.
LOWmodels/Qwen1.5/benchmark_throughput.py154 # Check if we can add more requests to the batch.
Docstring Block Structure1 hit · 5 pts
SeverityFileLineSnippet
HIGH…-Instruct FastApi 参考代码/qwen_vl_utils/vision_process.py132calculate the number of frames for video used for model inputs. Args: ele (dict): a dict contains the confi
Magic Placeholder Names1 hit · 5 pts
SeverityFileLineSnippet
HIGH…dels/GLM-4.7-Flash/03-GLM-4.7-Flash-Lora微调及Docker镜像.md137swanlab.login(api_key='your-apikey', save=True) # 记得替换为自己账号的apikey
Example Usage Blocks1 hit · 2 pts
SeverityFileLineSnippet
LOWutils.py149# Usage example