Library on 中文AI术语词典https://terms-en.ai-term-hub.com/zh/tags/library/Recent content in Library on 中文AI术语词典Hugozh-cnSat, 18 Jul 2026 11:44:45 +0000Unslothhttps://terms-en.ai-term-hub.com/zh/terms/unsloth/Sat, 18 Jul 2026 11:37:39 +0000https://terms-en.ai-term-hub.com/zh/terms/unsloth/<h2 id="definition">Definition</h2> <p>Unsloth 是一款专为优化大语言模型（LLM）的微调和部署而设计的工具。它通过替换标准的 PyTorch 操作，实现了显著的速度提升和内存占用减少。</p> <h3 id="summary">Summary</h3> <p>Unsloth 是一个开源库，通过优化的内存管理和内核实现，将大语言模型（LLM）的训练和推理速度提升高达 2 倍。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>内存优化</li> <li>自定义内核</li> <li>LLM 微调</li> <li>加速推理</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>在有限的 GPU 资源下微调 LLM</li> <li>加速推理流水线</li> <li>降低训练时的云计算成本</li> </ul> <h2 id="code-example">Code Example</h2> <div class="highlight"><pre tabindex="0" style="color:#f8f8f2;background-color:#272822;-moz-tab-size:4;-o-tab-size:4;tab-size:4;"><code class="language-python" data-lang="python"><span style="display:flex;"><span><span style="color:#f92672">from</span> unsloth <span style="color:#f92672">import</span> FastLanguageModel </span></span><span style="display:flex;"><span>model, tokenizer <span style="color:#f92672">=</span> FastLanguageModel<span style="color:#f92672">.</span>from_pretrained( </span></span><span style="display:flex;"><span> model_name<span style="color:#f92672">=</span><span style="color:#e6db74">&#34;unsloth/Llama-2-7b-bnb-4bit&#34;</span>, </span></span><span style="display:flex;"><span> max_seq_length<span style="color:#f92672">=</span><span style="color:#ae81ff">2048</span>, </span></span><span style="display:flex;"><span> dtype<span style="color:#f92672">=</span><span style="color:#66d9ef">None</span>, </span></span><span style="display:flex;"><span> load_in_4bit<span style="color:#f92672">=</span><span style="color:#66d9ef">True</span> </span></span><span style="display:flex;"><span>) </span></span></code></pre></div><h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/lora-%E4%BD%8E%E7%A7%A9%E9%80%82%E5%BA%94/">LoRA (低秩适应)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/pytorch-%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E6%A1%86%E6%9E%B6/">PyTorch (深度学习框架)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/hugging-face-%E6%A8%A1%E5%9E%8B%E7%A4%BE%E5%8C%BA%E5%B9%B3%E5%8F%B0/">Hugging Face (模型社区平台)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/flash-attention-%E9%AB%98%E6%95%88%E6%B3%A8%E6%84%8F%E5%8A%9B%E6%9C%BA%E5%88%B6/">Flash Attention (高效注意力机制)</a></li> </ul>Vllmhttps://terms-en.ai-term-hub.com/zh/terms/vllm/Sat, 18 Jul 2026 11:37:39 +0000https://terms-en.ai-term-hub.com/zh/terms/vllm/<h2 id="definition">Definition</h2> <p>vLLM（Virtual Large Language Model）是一个旨在加速 LLM 服务的开源库。它引入了 PagedAttention，这是一种受操作系统虚拟内存</p> <h3 id="summary">Summary</h3> <p>vLLM 是一个高吞吐量且内存高效的 LLM 推理引擎，利用 PagedAttention 优化 GPU 内存使用。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>PagedAttention</li> <li>KV Cache 管理</li> <li>推理服务</li> <li>吞吐量优化</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>高并发 API 服务</li> <li>批处理推理处理</li> <li>具有成本效益的 LLM 部署</li> </ul> <h2 id="code-example">Code Example</h2> <div class="highlight"><pre tabindex="0" style="color:#f8f8f2;background-color:#272822;-moz-tab-size:4;-o-tab-size:4;tab-size:4;"><code class="language-python" data-lang="python"><span style="display:flex;"><span><span style="color:#f92672">from</span> vllm <span style="color:#f92672">import</span> LLM, SamplingParams </span></span><span style="display:flex;"><span>llm <span style="color:#f92672">=</span> LLM(model<span style="color:#f92672">=</span><span style="color:#e6db74">&#34;facebook/opt-125m&#34;</span>) </span></span><span style="display:flex;"><span>prompts <span style="color:#f92672">=</span> [<span style="color:#e6db74">&#34;Hello, my name is&#34;</span>, <span style="color:#e6db74">&#34;The capital of France is&#34;</span>] </span></span><span style="display:flex;"><span>sampling_params <span style="color:#f92672">=</span> SamplingParams(temperature<span style="color:#f92672">=</span><span style="color:#ae81ff">0.8</span>, top_p<span style="color:#f92672">=</span><span style="color:#ae81ff">0.95</span>) </span></span><span style="display:flex;"><span>outputs <span style="color:#f92672">=</span> llm<span style="color:#f92672">.</span>generate(prompts, sampling_params) </span></span></code></pre></div><h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/tensorrt-nvidia-%E6%8E%A8%E7%90%86%E4%BC%98%E5%8C%96%E5%BA%93/">TensorRT (NVIDIA 推理优化库)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/tgi-%E6%96%87%E6%9C%AC%E7%94%9F%E6%88%90%E6%8E%A8%E7%90%86%E6%9C%8D%E5%8A%A1%E5%99%A8/">TGI (文本生成推理服务器)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/pagedattention-%E5%88%86%E9%A1%B5%E6%B3%A8%E6%84%8F%E5%8A%9B%E6%9C%BA%E5%88%B6/">PagedAttention (分页注意力机制)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/llm-serving-llm-%E6%9C%8D%E5%8A%A1%E5%8C%96/">LLM Serving (LLM 服务化)</a></li> </ul>Stable Diffusion Diffusershttps://terms-en.ai-term-hub.com/zh/terms/stable_diffusion_diffusers/Sat, 18 Jul 2026 11:35:05 +0000https://terms-en.ai-term-hub.com/zh/terms/stable_diffusion_diffusers/<h2 id="definition">Definition</h2> <p>Diffusers库是Hugging Face推出的一个开源工具包，旨在简化预训练扩散模型（特别是Stable Diffusion）的使用。它提供了模块化的管道（pipelines），处理从加载模型、预处理输入到后处理输出的整个流程。该库支持多种框架（如PyTorch和JAX），并允许用户轻松地进行模型微调（fine-tuning）和自定义推理配置，极大地降低了使用先进扩散模型的技术门槛。</p> <h3 id="summary">Summary</h3> <p>一个Hugging Face库，提供用于运行和微调Stable Diffusion模型的标准化管理流程。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>Hugging Face</li> <li>管道抽象</li> <li>微调</li> <li>模型互操作性</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>图像生成器的快速原型开发</li> <li>自定义模型微调</li> <li>扩散过程的教育演示</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/hugging-face-hub-hugging-face%E6%A8%A1%E5%9E%8B%E4%BB%93%E5%BA%93/">Hugging Face Hub (Hugging Face模型仓库)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/pytorch-%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E6%A1%86%E6%9E%B6/">PyTorch (深度学习框架)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/transformers-library-hugging-face%E8%87%AA%E7%84%B6%E8%AF%AD%E8%A8%80%E5%A4%84%E7%90%86%E5%BA%93/">Transformers Library (Hugging Face自然语言处理库)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/model-cards-%E6%A8%A1%E5%9E%8B%E5%8D%A1%E7%89%87-%E6%96%87%E6%A1%A3/">Model Cards (模型卡片/文档)</a></li> </ul>模型中心 Mixinhttps://terms-en.ai-term-hub.com/zh/terms/model_hub_mixin/Sat, 18 Jul 2026 11:26:24 +0000https://terms-en.ai-term-hub.com/zh/terms/model_hub_mixin/<h2 id="definition">Definition</h2> <p>Mixin 提供了保存、加载和推送模型到 Hugging Face Hub 等通用方法，无需每种模型架构单独实现这些工具。它们确保了代码的一致性和可维护性。</p> <h3 id="summary">Summary</h3> <p>模型中心 Mixin 是一个可重用的类组件，用于为 Hugging Face Transformers 模型添加标准化功能。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>代码可重用性</li> <li>Hugging Face 生态系统</li> <li>标准化 API</li> <li>继承</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>创建自定义模型架构</li> <li>将新模型集成到 Hub</li> <li>跨项目共享模型工具</li> </ul> <h2 id="code-example">Code Example</h2> <div class="highlight"><pre tabindex="0" style="color:#f8f8f2;background-color:#272822;-moz-tab-size:4;-o-tab-size:4;tab-size:4;"><code class="language-python" data-lang="python"><span style="display:flex;"><span><span style="color:#f92672">from</span> transformers.modeling_utils <span style="color:#f92672">import</span> PreTrainedModel </span></span><span style="display:flex;"><span><span style="color:#66d9ef">class</span> <span style="color:#a6e22e">MyModel</span>(PreTrainedModel): <span style="color:#66d9ef">pass</span> </span></span></code></pre></div><h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/hugging-face-hub-hugging-face-%E6%A8%A1%E5%9E%8B%E4%B8%AD%E5%BF%83/">Hugging Face Hub (Hugging Face 模型中心)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/transformers-library-transformers-%E5%BA%93/">Transformers Library (Transformers 库)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/pytorch-modules-pytorch-%E6%A8%A1%E5%9D%97/">PyTorch Modules (PyTorch 模块)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/model-saving-%E6%A8%A1%E5%9E%8B%E4%BF%9D%E5%AD%98/">Model Saving (模型保存)</a></li> </ul>Diffusershttps://terms-en.ai-term-hub.com/zh/terms/diffusers/Sat, 18 Jul 2026 11:14:55 +0000https://terms-en.ai-term-hub.com/zh/terms/diffusers/<h2 id="definition">Definition</h2> <p>Hugging Face Diffusers 是一个模块化工具包，旨在简化扩散模型的使用。它为文本生成图像、图像修复和超分辨率等任务提供了预训练管道。</p> <h3 id="summary">Summary</h3> <p>Hugging Face 生态系统中的一个库，提供了用于图像、音频和文本生成的最先进的扩散模型实现。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>管道抽象</li> <li>预训练模型</li> <li>去噪过程</li> <li>社区中心</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>构建创意 AI 艺术应用</li> <li>实现图像编辑工具</li> <li>快速原型开发生成式功能</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/stable-diffusion/">Stable Diffusion</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/hugging-face/">Hugging Face</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/%E6%BD%9C%E5%9C%A8%E6%89%A9%E6%95%A3-latent-diffusion/">潜在扩散 (Latent Diffusion)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/%E7%94%9F%E6%88%90%E5%BC%8F-ai-generative-ai/">生成式 AI (Generative AI)</a></li> </ul>Transformers库https://terms-en.ai-term-hub.com/zh/terms/transformers/Sat, 18 Jul 2026 10:55:40 +0000https://terms-en.ai-term-hub.com/zh/terms/transformers/<h2 id="definition">Definition</h2> <p>术语“Transformers”通常指由Hugging Face维护的广泛使用的Python库。它为下载、训练和部署基于Transformer架构的预训练模型提供了易于使用的接口。</p> <h3 id="summary">Summary</h3> <p>在此语境下，指Hugging Face Transformers库，这是一个流行的开源工具包，用于最先进的NLP和多模态模型。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>Hugging Face Hub</li> <li>Pipeline API</li> <li>Model Cards</li> <li>分词器集成</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>NLP应用的快速原型开发</li> <li>访问社区预训练模型</li> <li>标准化模型部署工作流</li> </ul> <h2 id="code-example">Code Example</h2> <div class="highlight"><pre tabindex="0" style="color:#f8f8f2;background-color:#272822;-moz-tab-size:4;-o-tab-size:4;tab-size:4;"><code class="language-python" data-lang="python"><span style="display:flex;"><span><span style="color:#f92672">from</span> transformers <span style="color:#f92672">import</span> pipeline </span></span><span style="display:flex;"><span>classifier <span style="color:#f92672">=</span> pipeline(<span style="color:#e6db74">&#39;sentiment-analysis&#39;</span>) </span></span></code></pre></div><h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/hugging_face-hugging-face%E5%B9%B3%E5%8F%B0/">hugging_face (Hugging Face平台)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/pipeline-%E6%B5%81%E6%B0%B4%E7%BA%BFapi/">pipeline (流水线API)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/tokenizer-%E5%88%86%E8%AF%8D%E5%99%A8/">tokenizer (分词器)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/pytorch-pytorch%E6%A1%86%E6%9E%B6/">pytorch (PyTorch框架)</a></li> </ul>