Buckets:
| <meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Quickstart","local":"quickstart","sections":[{"title":"Set up","local":"set-up","sections":[],"depth":2},{"title":"Pretrained models","local":"pretrained-models","sections":[],"depth":2},{"title":"Pipeline","local":"pipeline","sections":[],"depth":2},{"title":"Trainer","local":"trainer","sections":[{"title":"TensorFlow","local":"tensorflow","sections":[],"depth":3}],"depth":2},{"title":"Next steps","local":"next-steps","sections":[],"depth":2}],"depth":1}"> | |
| <link href="/docs/transformers/pr_36839/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_36839/en/_app/immutable/entry/start.6be8d590.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_36839/en/_app/immutable/chunks/scheduler.01eeda35.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_36839/en/_app/immutable/chunks/singletons.177df05e.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_36839/en/_app/immutable/chunks/index.4862150a.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_36839/en/_app/immutable/chunks/paths.517376d1.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_36839/en/_app/immutable/entry/app.09748b4b.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_36839/en/_app/immutable/chunks/index.6dd51b66.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_36839/en/_app/immutable/nodes/0.8897c14d.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_36839/en/_app/immutable/chunks/each.e59479a4.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_36839/en/_app/immutable/nodes/449.4fd87ade.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_36839/en/_app/immutable/chunks/Tip.de9bae2b.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_36839/en/_app/immutable/chunks/CodeBlock.864da1b0.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_36839/en/_app/immutable/chunks/DocNotebookDropdown.54e76c6c.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_36839/en/_app/immutable/chunks/globals.7f7f1b26.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_36839/en/_app/immutable/chunks/EditOnGithub.7faefd25.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_36839/en/_app/immutable/chunks/HfOption.f7f04550.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_36839/en/_app/immutable/chunks/stores.318eade7.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"Quickstart","local":"quickstart","sections":[{"title":"Set up","local":"set-up","sections":[],"depth":2},{"title":"Pretrained models","local":"pretrained-models","sections":[],"depth":2},{"title":"Pipeline","local":"pipeline","sections":[],"depth":2},{"title":"Trainer","local":"trainer","sections":[{"title":"TensorFlow","local":"tensorflow","sections":[],"depth":3}],"depth":2},{"title":"Next steps","local":"next-steps","sections":[],"depth":2}],"depth":1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <h1 class="relative group"><a id="quickstart" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#quickstart"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Quickstart</span></h1> <div class="flex space-x-1 absolute z-10 right-0 top-0"> <div class="relative colab-dropdown "> <button class=" " type="button"> <img alt="Open In Colab" class="!m-0" src="https://colab.research.google.com/assets/colab-badge.svg"> </button> </div> <div class="relative colab-dropdown "> <button class=" " type="button"> <img alt="Open In Studio Lab" class="!m-0" src="https://studiolab.sagemaker.aws/studiolab.svg"> </button> </div></div> <p data-svelte-h="svelte-661vj6">Transformers is designed to be fast and easy to use so that everyone can start learning or building with transformer models.</p> <p data-svelte-h="svelte-5htbgh">The number of user-facing abstractions is limited to only three classes for instantiating a model, and two APIs for inference or training. This quickstart introduces you to Transformers’ key features and shows you how to:</p> <ul data-svelte-h="svelte-ju2ez8"><li>load a pretrained model</li> <li>run inference with <a href="/docs/transformers/pr_36839/en/main_classes/pipelines#transformers.Pipeline">Pipeline</a></li> <li>fine-tune a model with <a href="/docs/transformers/pr_36839/en/main_classes/trainer#transformers.Trainer">Trainer</a></li></ul> <h2 class="relative group"><a id="set-up" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#set-up"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Set up</span></h2> <p data-svelte-h="svelte-2xzset">To start, we recommend creating a Hugging Face <a href="https://hf.co/join" rel="nofollow">account</a>. An account lets you host and access version controlled models, datasets, and <a href="https://hf.co/spaces" rel="nofollow">Spaces</a> on the Hugging Face <a href="https://hf.co/docs/hub/index" rel="nofollow">Hub</a>, a collaborative platform for discovery and building.</p> <p data-svelte-h="svelte-1hzybaw">Create a <a href="https://hf.co/docs/hub/security-tokens#user-access-tokens" rel="nofollow">User Access Token</a> and log in to your account.</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> huggingface_hub <span class="hljs-keyword">import</span> notebook_login | |
| notebook_login()<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-jrg5k1">Install a machine learning framework.</p> <div class="flex space-x-2 items-center my-1.5 mr-8 h-7 !pl-0 -mx-3 md:mx-0"><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd border-gray-800 bg-black dark:bg-gray-700 text-white">PyTorch </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm">TensorFlow </div></div> <div class="language-select"><div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->!pip install torch<!-- HTML_TAG_END --></pre></div> </div> <p data-svelte-h="svelte-lgf98o">Then install an up-to-date version of Transformers and some additional libraries from the Hugging Face ecosystem for accessing datasets and vision models, evaluating training, and optimizing training for large models.</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->!pip install -U transformers datasets evaluate accelerate timm<!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="pretrained-models" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#pretrained-models"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Pretrained models</span></h2> <p data-svelte-h="svelte-1qfgkiz">Each pretrained model inherits from three base classes.</p> <table data-svelte-h="svelte-1par1bs"><thead><tr><th><strong>Class</strong></th> <th><strong>Description</strong></th></tr></thead> <tbody><tr><td><a href="/docs/transformers/pr_36839/en/main_classes/configuration#transformers.PretrainedConfig">PretrainedConfig</a></td> <td>A file that specifies a models attributes such as the number of attention heads or vocabulary size.</td></tr> <tr><td><a href="/docs/transformers/pr_36839/en/main_classes/model#transformers.PreTrainedModel">PreTrainedModel</a></td> <td>A model (or architecture) defined by the model attributes from the configuration file. A pretrained model only returns the raw hidden states. For a specific task, use the appropriate model head to convert the raw hidden states into a meaningful result (for example, <a href="/docs/transformers/pr_36839/en/model_doc/llama#transformers.LlamaModel">LlamaModel</a> versus <a href="/docs/transformers/pr_36839/en/model_doc/llama#transformers.LlamaForCausalLM">LlamaForCausalLM</a>).</td></tr> <tr><td>Preprocessor</td> <td>A class for converting raw inputs (text, images, audio, multimodal) into numerical inputs to the model. For example, <a href="/docs/transformers/pr_36839/en/main_classes/tokenizer#transformers.PreTrainedTokenizer">PreTrainedTokenizer</a> converts text into tensors and <a href="/docs/transformers/pr_36839/en/internal/image_processing_utils#transformers.ImageProcessingMixin">ImageProcessingMixin</a> converts pixels into tensors.</td></tr></tbody></table> <p data-svelte-h="svelte-1cw7zup">We recommend using the <a href="./model_doc/auto">AutoClass</a> API to load models and preprocessors because it automatically infers the appropriate architecture for each task and machine learning framework based on the name or path to the pretrained weights and configuration file.</p> <p data-svelte-h="svelte-19f7u7o">Use <a href="/docs/transformers/pr_36839/en/main_classes/model#transformers.PreTrainedModel.from_pretrained">from_pretrained()</a> to load the weights and configuration file from the Hub into the model and preprocessor class.</p> <div class="flex space-x-2 items-center my-1.5 mr-8 h-7 !pl-0 -mx-3 md:mx-0"><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd border-gray-800 bg-black dark:bg-gray-700 text-white">PyTorch </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm">TensorFlow </div></div> <div class="language-select"><p data-svelte-h="svelte-fw3y6g">When you load a model, configure the following parameters to ensure the model is optimally loaded.</p> <ul data-svelte-h="svelte-uuw8kb"><li><code>device_map="auto"</code> automatically allocates the model weights to your fastest device first, which is typically the GPU.</li> <li><code>torch_dtype="auto"</code> directly initializes the model weights in the data type they’re stored in, which can help avoid loading the weights twice (PyTorch loads weights in <code>torch.float32</code> by default).</li></ul> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoModelForCausalLM, AutoTokenizer | |
| model = AutoModelForCausalLM.from_pretrained(<span class="hljs-string">"meta-llama/Llama-2-7b-hf"</span>, torch_dtype=<span class="hljs-string">"auto"</span>, device_map=<span class="hljs-string">"auto"</span>) | |
| tokenizer = AutoTokenizer.from_pretrained(<span class="hljs-string">"meta-llama/Llama-2-7b-hf"</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1m2is5y">Tokenize the text and return PyTorch tensors with the tokenizer. Move the model to a GPU if it’s available to accelerate inference.</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->model_inputs = tokenizer([<span class="hljs-string">"The secret to baking a good cake is "</span>], return_tensors=<span class="hljs-string">"pt"</span>).to(<span class="hljs-string">"cuda"</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-std1x6">The model is now ready for inference or training.</p> <p data-svelte-h="svelte-155v921">For inference, pass the tokenized inputs to <a href="/docs/transformers/pr_36839/en/main_classes/text_generation#transformers.GenerationMixin.generate">generate()</a> to generate text. Decode the token ids back into text with <a href="/docs/transformers/pr_36839/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.batch_decode">batch_decode()</a>.</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->generated_ids = model.generate(**model_inputs, max_length=<span class="hljs-number">30</span>) | |
| tokenizer.batch_decode(generated_ids)[<span class="hljs-number">0</span>] | |
| <span class="hljs-string">'<s> The secret to baking a good cake is 100% in the preparation. There are so many recipes out there,'</span><!-- HTML_TAG_END --></pre></div> </div> <div class="course-tip bg-gradient-to-br dark:bg-gradient-to-r before:border-green-500 dark:before:border-green-800 from-green-50 dark:from-gray-900 to-white dark:to-gray-950 border border-green-50 text-green-700 dark:text-gray-400"><p data-svelte-h="svelte-1alb80h">Skip ahead to the <a href="#trainer-api">Trainer</a> section to learn how to fine-tune a model.</p></div> <h2 class="relative group"><a id="pipeline" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#pipeline"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Pipeline</span></h2> <p data-svelte-h="svelte-17auhrw">The <a href="/docs/transformers/pr_36839/en/main_classes/pipelines#transformers.Pipeline">Pipeline</a> class is the most convenient way to inference with a pretrained model. It supports many tasks such as text generation, image segmentation, automatic speech recognition, document question answering, and more.</p> <div class="course-tip bg-gradient-to-br dark:bg-gradient-to-r before:border-green-500 dark:before:border-green-800 from-green-50 dark:from-gray-900 to-white dark:to-gray-950 border border-green-50 text-green-700 dark:text-gray-400"><p data-svelte-h="svelte-1dafwgm">Refer to the <a href="./main_classes/pipelines">Pipeline</a> API reference for a complete list of available tasks.</p></div> <p data-svelte-h="svelte-1qhmg6a">Create a <a href="/docs/transformers/pr_36839/en/main_classes/pipelines#transformers.Pipeline">Pipeline</a> object and select a task. By default, <a href="/docs/transformers/pr_36839/en/main_classes/pipelines#transformers.Pipeline">Pipeline</a> downloads and caches a default pretrained model for a given task. Pass the model name to the <code>model</code> parameter to choose a specific model.</p> <div class="flex space-x-2 items-center my-1.5 mr-8 h-7 !pl-0 -mx-3 md:mx-0"><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd border-gray-800 bg-black dark:bg-gray-700 text-white">text generation </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm">image segmentation </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm">automatic speech recognition </div></div> <div class="language-select"><p data-svelte-h="svelte-i28usx">Set <code>device="cuda"</code> to accelerate inference with a GPU.</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> pipeline | |
| pipeline = pipeline(<span class="hljs-string">"text-generation"</span>, model=<span class="hljs-string">"meta-llama/Llama-2-7b-hf"</span>, device=<span class="hljs-string">"cuda"</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-tvw3s6">Prompt <a href="/docs/transformers/pr_36839/en/main_classes/pipelines#transformers.Pipeline">Pipeline</a> with some initial text to generate more text.</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->pipeline(<span class="hljs-string">"The secret to baking a good cake is "</span>, max_length=<span class="hljs-number">50</span>) | |
| [{<span class="hljs-string">'generated_text'</span>: <span class="hljs-string">'The secret to baking a good cake is 100% in the batter. The secret to a great cake is the icing.\nThis is why we’ve created the best buttercream frosting reci'</span>}]<!-- HTML_TAG_END --></pre></div> </div> <h2 class="relative group"><a id="trainer" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#trainer"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Trainer</span></h2> <p data-svelte-h="svelte-1v78xuk"><a href="/docs/transformers/pr_36839/en/main_classes/trainer#transformers.Trainer">Trainer</a> is a complete training and evaluation loop for PyTorch models. It abstracts away a lot of the boilerplate usually involved in manually writing a training loop, so you can start training faster and focus on training design choices. You only need a model, dataset, a preprocessor, and a data collator to build batches of data from the dataset.</p> <p data-svelte-h="svelte-1su7lc6">Use the <a href="/docs/transformers/pr_36839/en/main_classes/trainer#transformers.TrainingArguments">TrainingArguments</a> class to customize the training process. It provides many options for training, evaluation, and more. Experiment with training hyperparameters and features like batch size, learning rate, mixed precision, torch.compile, and more to meet your training needs. You could also use the default training parameters to quickly produce a baseline.</p> <p data-svelte-h="svelte-2aamqd">Load a model, tokenizer, and dataset for training.</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoModelForSequenceClassification, AutoTokenizer | |
| <span class="hljs-keyword">from</span> datasets <span class="hljs-keyword">import</span> load_dataset | |
| model = AutoModelForSequenceClassification.from_pretrained(<span class="hljs-string">"distilbert/distilbert-base-uncased"</span>) | |
| tokenizer = AutoTokenizer.from_pretrained(<span class="hljs-string">"distilbert/distilbert-base-uncased"</span>) | |
| dataset = load_dataset(<span class="hljs-string">"rotten_tomatoes"</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-6yueww">Create a function to tokenize the text and convert it into PyTorch tensors. Apply this function to the whole dataset with the <a href="https://huggingface.co/docs/datasets/main/en/package_reference/main_classes#datasets.Dataset.map" rel="nofollow">map</a> method.</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">def</span> <span class="hljs-title function_">tokenize_dataset</span>(<span class="hljs-params">dataset</span>): | |
| <span class="hljs-keyword">return</span> tokenizer(dataset[<span class="hljs-string">"text"</span>]) | |
| dataset = dataset.<span class="hljs-built_in">map</span>(tokenize_dataset, batched=<span class="hljs-literal">True</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-bbg97b">Load a data collator to create batches of data and pass the tokenizer to it.</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> DataCollatorWithPadding | |
| data_collator = DataCollatorWithPadding(tokenizer=tokenizer)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-34f5gk">Next, set up <a href="/docs/transformers/pr_36839/en/main_classes/trainer#transformers.TrainingArguments">TrainingArguments</a> with the training features and hyperparameters.</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> TrainingArguments | |
| training_args = TrainingArguments( | |
| output_dir=<span class="hljs-string">"distilbert-rotten-tomatoes"</span>, | |
| learning_rate=<span class="hljs-number">2e-5</span>, | |
| per_device_train_batch_size=<span class="hljs-number">8</span>, | |
| per_device_eval_batch_size=<span class="hljs-number">8</span>, | |
| num_train_epochs=<span class="hljs-number">2</span>, | |
| push_to_hub=<span class="hljs-literal">True</span>, | |
| )<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1jv9gcy">Finally, pass all these separate components to <a href="/docs/transformers/pr_36839/en/main_classes/trainer#transformers.Trainer">Trainer</a> and call <a href="/docs/transformers/pr_36839/en/main_classes/trainer#transformers.Trainer.train">train()</a> to start.</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> Trainer | |
| trainer = Trainer( | |
| model=model, | |
| args=training_args, | |
| train_dataset=dataset[<span class="hljs-string">"train"</span>], | |
| eval_dataset=dataset[<span class="hljs-string">"test"</span>], | |
| tokenizer=tokenizer, | |
| data_collator=data_collator, | |
| ) | |
| trainer.train()<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1mrrpyt">Share your model and tokenizer to the Hub with <a href="/docs/transformers/pr_36839/en/main_classes/trainer#transformers.Trainer.push_to_hub">push_to_hub()</a>.</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->trainer.push_to_hub()<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1205d2s">Congratulations, you just trained your first model with Transformers!</p> <h3 class="relative group"><a id="tensorflow" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#tensorflow"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>TensorFlow</span></h3> <div class="course-tip course-tip-orange bg-gradient-to-br dark:bg-gradient-to-r before:border-orange-500 dark:before:border-orange-800 from-orange-50 dark:from-gray-900 to-white dark:to-gray-950 border border-orange-50 text-orange-700 dark:text-gray-400"><p data-svelte-h="svelte-jebxnx">Not all pretrained models are available in TensorFlow. Refer to a models API doc to check whether a TensorFlow implementation is supported.</p></div> <p data-svelte-h="svelte-pwmeet"><a href="/docs/transformers/pr_36839/en/main_classes/trainer#transformers.Trainer">Trainer</a> doesn’t work with TensorFlow models, but you can still train a Transformers model implemented in TensorFlow with <a href="https://keras.io/" rel="nofollow">Keras</a>. Transformers TensorFlow models are a standard <a href="https://www.tensorflow.org/api_docs/python/tf/keras/Model" rel="nofollow">tf.keras.Model</a>, which is compatible with Keras’ <a href="https://keras.io/api/models/model_training_apis/#compile-method" rel="nofollow">compile</a> and <a href="https://keras.io/api/models/model_training_apis/#fit-method" rel="nofollow">fit</a> methods.</p> <p data-svelte-h="svelte-2aamqd">Load a model, tokenizer, and dataset for training.</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> TFAutoModelForSequenceClassification, AutoTokenizer | |
| model = TFAutoModelForSequenceClassification.from_pretrained(<span class="hljs-string">"distilbert/distilbert-base-uncased"</span>) | |
| tokenizer = AutoTokenizer.from_pretrained(<span class="hljs-string">"distilbert/distilbert-base-uncased"</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1uk73zq">Create a function to tokenize the text and convert it into TensorFlow tensors. Apply this function to the whole dataset with the <a href="https://huggingface.co/docs/datasets/main/en/package_reference/main_classes#datasets.Dataset.map" rel="nofollow">map</a> method.</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">def</span> <span class="hljs-title function_">tokenize_dataset</span>(<span class="hljs-params">dataset</span>): | |
| <span class="hljs-keyword">return</span> tokenizer(dataset[<span class="hljs-string">"text"</span>]) | |
| dataset = dataset.<span class="hljs-built_in">map</span>(tokenize_dataset)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-18rrokg">Transformers provides the <a href="/docs/transformers/pr_36839/en/main_classes/model#transformers.TFPreTrainedModel.prepare_tf_dataset">prepare_tf_dataset()</a> method to collate and batch a dataset.</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->tf_dataset = model.prepare_tf_dataset( | |
| dataset[<span class="hljs-string">"train"</span>], batch_size=<span class="hljs-number">16</span>, shuffle=<span class="hljs-literal">True</span>, tokenizer=tokenizer | |
| )<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1ebicwx">Finally, call <a href="https://keras.io/api/models/model_training_apis/#compile-method" rel="nofollow">compile</a> to configure the model for training and <a href="https://keras.io/api/models/model_training_apis/#fit-method" rel="nofollow">fit</a> to start.</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> tensorflow.keras.optimizers <span class="hljs-keyword">import</span> Adam | |
| model.<span class="hljs-built_in">compile</span>(optimizer=<span class="hljs-string">"adam"</span>) | |
| model.fit(tf_dataset)<!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="next-steps" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#next-steps"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Next steps</span></h2> <p data-svelte-h="svelte-ruteo0">Now that you have a better understanding of Transformers and what it offers, it’s time to keep exploring and learning what interests you the most.</p> <ul data-svelte-h="svelte-1jxru3m"><li><strong>Base classes</strong>: Learn more about the configuration, model and processor classes. This will help you understand how to create and customize models, preprocess different types of inputs (audio, images, multimodal), and how to share your model.</li> <li><strong>Inference</strong>: Explore the <a href="/docs/transformers/pr_36839/en/main_classes/pipelines#transformers.Pipeline">Pipeline</a> further, inference and chatting with LLMs, agents, and how to optimize inference with your machine learning framework and hardware.</li> <li><strong>Training</strong>: Study the <a href="/docs/transformers/pr_36839/en/main_classes/trainer#transformers.Trainer">Trainer</a> in more detail, as well as distributed training and optimizing training on specific hardware.</li> <li><strong>Quantization</strong>: Reduce memory and storage requirements with quantization and speed up inference by representing weights with fewer bits.</li> <li><strong>Resources</strong>: Looking for end-to-end recipes for how to train and inference with a model for a specific task? Check out the task recipes!</li></ul> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/transformers/blob/main/docs/source/en/quicktour.md" target="_blank"><span data-svelte-h="svelte-1kd6by1"><</span> <span data-svelte-h="svelte-x0xyl0">></span> <span data-svelte-h="svelte-1dajgef"><span class="underline ml-1.5">Update</span> on GitHub</span></a> <p></p> | |
| <script> | |
| { | |
| __sveltekit_1bm5psi = { | |
| assets: "/docs/transformers/pr_36839/en", | |
| base: "/docs/transformers/pr_36839/en", | |
| env: {} | |
| }; | |
| const element = document.currentScript.parentElement; | |
| const data = [null,null]; | |
| Promise.all([ | |
| import("/docs/transformers/pr_36839/en/_app/immutable/entry/start.6be8d590.js"), | |
| import("/docs/transformers/pr_36839/en/_app/immutable/entry/app.09748b4b.js") | |
| ]).then(([kit, app]) => { | |
| kit.start(app, element, { | |
| node_ids: [0, 449], | |
| data, | |
| form: null, | |
| error: null | |
| }); | |
| }); | |
| } | |
| </script> | |
Xet Storage Details
- Size:
- 54.6 kB
- Xet hash:
- e1cd33551c9b90c898cd9588b9603f7870f06360dec25464182d1273bb090f2c
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.