Buckets:
| <meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"P-tuning for sequence classification","local":"p-tuning-for-sequence-classification","sections":[{"title":"Setup","local":"setup","sections":[],"depth":2},{"title":"Load dataset and metric","local":"load-dataset-and-metric","sections":[],"depth":2},{"title":"Preprocess dataset","local":"preprocess-dataset","sections":[],"depth":2},{"title":"Train","local":"train","sections":[],"depth":2},{"title":"Share model","local":"share-model","sections":[],"depth":2},{"title":"Inference","local":"inference","sections":[],"depth":2}],"depth":1}"> | |
| <link href="/docs/peft/main/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload"> | |
| <link rel="modulepreload" href="/docs/peft/main/en/_app/immutable/entry/start.d6c2bc1c.js"> | |
| <link rel="modulepreload" href="/docs/peft/main/en/_app/immutable/chunks/scheduler.924d507e.js"> | |
| <link rel="modulepreload" href="/docs/peft/main/en/_app/immutable/chunks/singletons.1db9e4df.js"> | |
| <link rel="modulepreload" href="/docs/peft/main/en/_app/immutable/chunks/index.382c9da2.js"> | |
| <link rel="modulepreload" href="/docs/peft/main/en/_app/immutable/chunks/paths.5da4bdec.js"> | |
| <link rel="modulepreload" href="/docs/peft/main/en/_app/immutable/entry/app.973a0e51.js"> | |
| <link rel="modulepreload" href="/docs/peft/main/en/_app/immutable/chunks/index.0ece89e8.js"> | |
| <link rel="modulepreload" href="/docs/peft/main/en/_app/immutable/nodes/0.dacc2355.js"> | |
| <link rel="modulepreload" href="/docs/peft/main/en/_app/immutable/chunks/each.e59479a4.js"> | |
| <link rel="modulepreload" href="/docs/peft/main/en/_app/immutable/nodes/38.4109043f.js"> | |
| <link rel="modulepreload" href="/docs/peft/main/en/_app/immutable/chunks/Tip.a5ce8f1d.js"> | |
| <link rel="modulepreload" href="/docs/peft/main/en/_app/immutable/chunks/CodeBlock.d01ac312.js"> | |
| <link rel="modulepreload" href="/docs/peft/main/en/_app/immutable/chunks/Heading.c9bff43c.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"P-tuning for sequence classification","local":"p-tuning-for-sequence-classification","sections":[{"title":"Setup","local":"setup","sections":[],"depth":2},{"title":"Load dataset and metric","local":"load-dataset-and-metric","sections":[],"depth":2},{"title":"Preprocess dataset","local":"preprocess-dataset","sections":[],"depth":2},{"title":"Train","local":"train","sections":[],"depth":2},{"title":"Share model","local":"share-model","sections":[],"depth":2},{"title":"Inference","local":"inference","sections":[],"depth":2}],"depth":1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <h1 class="relative group"><a id="p-tuning-for-sequence-classification" 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="#p-tuning-for-sequence-classification"><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>P-tuning for sequence classification</span></h1> <p data-svelte-h="svelte-s3dbsf">It is challenging to finetune large language models for downstream tasks because they have so many parameters. To work around this, you can use <em>prompts</em> to steer the model toward a particular downstream task without fully finetuning a model. Typically, these prompts are handcrafted, which may be impractical because you need very large validation sets to find the best prompts. <em>P-tuning</em> is a method for automatically searching and optimizing for better prompts in a continuous space.</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-125xb5e">💡 Read <a href="https://arxiv.org/abs/2103.10385" rel="nofollow">GPT Understands, Too</a> to learn more about p-tuning.</p></div> <p data-svelte-h="svelte-1hr4cih">This guide will show you how to train a <a href="https://huggingface.co/roberta-large" rel="nofollow"><code>roberta-large</code></a> model (but you can also use any of the GPT, OPT, or BLOOM models) with p-tuning on the <code>mrpc</code> configuration of the <a href="https://huggingface.co/datasets/glue" rel="nofollow">GLUE</a> benchmark.</p> <p data-svelte-h="svelte-1c9nexd">Before you begin, make sure you have all the necessary libraries installed:</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 -q peft transformers datasets evaluate<!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="setup" 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="#setup"><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>Setup</span></h2> <p data-svelte-h="svelte-19nyg0p">To get started, import 🤗 Transformers to create the base model, 🤗 Datasets to load a dataset, 🤗 Evaluate to load an evaluation metric, and 🤗 PEFT to create a <a href="/docs/peft/main/en/package_reference/peft_model#peft.PeftModel">PeftModel</a> and setup the configuration for p-tuning.</p> <p data-svelte-h="svelte-30fuvg">Define the model, dataset, and some basic training 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> ( | |
| AutoModelForSequenceClassification, | |
| AutoTokenizer, | |
| DataCollatorWithPadding, | |
| TrainingArguments, | |
| Trainer, | |
| ) | |
| <span class="hljs-keyword">from</span> peft <span class="hljs-keyword">import</span> ( | |
| get_peft_config, | |
| get_peft_model, | |
| get_peft_model_state_dict, | |
| set_peft_model_state_dict, | |
| PeftType, | |
| PromptEncoderConfig, | |
| ) | |
| <span class="hljs-keyword">from</span> datasets <span class="hljs-keyword">import</span> load_dataset | |
| <span class="hljs-keyword">import</span> evaluate | |
| <span class="hljs-keyword">import</span> torch | |
| model_name_or_path = <span class="hljs-string">"roberta-large"</span> | |
| task = <span class="hljs-string">"mrpc"</span> | |
| num_epochs = <span class="hljs-number">20</span> | |
| lr = <span class="hljs-number">1e-3</span> | |
| batch_size = <span class="hljs-number">32</span><!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="load-dataset-and-metric" 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="#load-dataset-and-metric"><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>Load dataset and metric</span></h2> <p data-svelte-h="svelte-zx4u5n">Next, load the <code>mrpc</code> configuration - a corpus of sentence pairs labeled according to whether they’re semantically equivalent or not - from the <a href="https://huggingface.co/datasets/glue" rel="nofollow">GLUE</a> benchmark:</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 -->dataset = load_dataset(<span class="hljs-string">"glue"</span>, task) | |
| dataset[<span class="hljs-string">"train"</span>][<span class="hljs-number">0</span>] | |
| { | |
| <span class="hljs-string">"sentence1"</span>: <span class="hljs-string">'Amrozi accused his brother , whom he called " the witness " , of deliberately distorting his evidence .'</span>, | |
| <span class="hljs-string">"sentence2"</span>: <span class="hljs-string">'Referring to him as only " the witness " , Amrozi accused his brother of deliberately distorting his evidence .'</span>, | |
| <span class="hljs-string">"label"</span>: <span class="hljs-number">1</span>, | |
| <span class="hljs-string">"idx"</span>: <span class="hljs-number">0</span>, | |
| }<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1k36sge">From 🤗 Evaluate, load a metric for evaluating the model’s performance. The evaluation module returns the accuracy and F1 scores associated with this specific task.</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 -->metric = evaluate.load(<span class="hljs-string">"glue"</span>, task)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-17x055y">Now you can use the <code>metric</code> to write a function that computes the accuracy and F1 scores. The <code>compute_metric</code> function calculates the scores from the model predictions and labels:</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">import</span> numpy <span class="hljs-keyword">as</span> np | |
| <span class="hljs-keyword">def</span> <span class="hljs-title function_">compute_metrics</span>(<span class="hljs-params">eval_pred</span>): | |
| predictions, labels = eval_pred | |
| predictions = np.argmax(predictions, axis=<span class="hljs-number">1</span>) | |
| <span class="hljs-keyword">return</span> metric.compute(predictions=predictions, references=labels)<!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="preprocess-dataset" 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="#preprocess-dataset"><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>Preprocess dataset</span></h2> <p data-svelte-h="svelte-12y1arr">Initialize the tokenizer and configure the padding token to use. If you’re using a GPT, OPT, or BLOOM model, you should set the <code>padding_side</code> to the left; otherwise it’ll be set to the right. Tokenize the sentence pairs and truncate them to the maximum length.</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">if</span> <span class="hljs-built_in">any</span>(k <span class="hljs-keyword">in</span> model_name_or_path <span class="hljs-keyword">for</span> k <span class="hljs-keyword">in</span> (<span class="hljs-string">"gpt"</span>, <span class="hljs-string">"opt"</span>, <span class="hljs-string">"bloom"</span>)): | |
| padding_side = <span class="hljs-string">"left"</span> | |
| <span class="hljs-keyword">else</span>: | |
| padding_side = <span class="hljs-string">"right"</span> | |
| tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, padding_side=padding_side) | |
| <span class="hljs-keyword">if</span> <span class="hljs-built_in">getattr</span>(tokenizer, <span class="hljs-string">"pad_token_id"</span>) <span class="hljs-keyword">is</span> <span class="hljs-literal">None</span>: | |
| tokenizer.pad_token_id = tokenizer.eos_token_id | |
| <span class="hljs-keyword">def</span> <span class="hljs-title function_">tokenize_function</span>(<span class="hljs-params">examples</span>): | |
| <span class="hljs-comment"># max_length=None => use the model max length (it's actually the default)</span> | |
| outputs = tokenizer(examples[<span class="hljs-string">"sentence1"</span>], examples[<span class="hljs-string">"sentence2"</span>], truncation=<span class="hljs-literal">True</span>, max_length=<span class="hljs-literal">None</span>) | |
| <span class="hljs-keyword">return</span> outputs<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-a3ewpb">Use <a href="https://huggingface.co/docs/datasets/main/en/package_reference/main_classes#datasets.Dataset.map" rel="nofollow">map</a> to apply the <code>tokenize_function</code> to the dataset, and remove the unprocessed columns because the model won’t need those. You should also rename the <code>label</code> column to <code>labels</code> because that is the expected name for the labels by models in the 🤗 Transformers library.</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 -->tokenized_datasets = dataset.<span class="hljs-built_in">map</span>( | |
| tokenize_function, | |
| batched=<span class="hljs-literal">True</span>, | |
| remove_columns=[<span class="hljs-string">"idx"</span>, <span class="hljs-string">"sentence1"</span>, <span class="hljs-string">"sentence2"</span>], | |
| ) | |
| tokenized_datasets = tokenized_datasets.rename_column(<span class="hljs-string">"label"</span>, <span class="hljs-string">"labels"</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1ret57o">Create a collator function with <a href="https://huggingface.co/docs/transformers/main/en/main_classes/data_collator#transformers.DataCollatorWithPadding" rel="nofollow">DataCollatorWithPadding</a> to pad the examples in the batches to the <code>longest</code> sequence in the batch:</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 -->data_collator = DataCollatorWithPadding(tokenizer=tokenizer, padding=<span class="hljs-string">"longest"</span>)<!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="train" 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="#train"><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>Train</span></h2> <p data-svelte-h="svelte-1r18dhr">P-tuning uses a prompt encoder to optimize the prompt parameters, so you’ll need to initialize the <a href="/docs/peft/main/en/package_reference/p_tuning#peft.PromptEncoderConfig">PromptEncoderConfig</a> with several arguments:</p> <ul data-svelte-h="svelte-ivboi0"><li><code>task_type</code>: the type of task you’re training on, in this case it is sequence classification or <code>SEQ_CLS</code></li> <li><code>num_virtual_tokens</code>: the number of virtual tokens to use, or in other words, the prompt</li> <li><code>encoder_hidden_size</code>: the hidden size of the encoder used to optimize the prompt parameters</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 -->peft_config = PromptEncoderConfig(task_type=<span class="hljs-string">"SEQ_CLS"</span>, num_virtual_tokens=<span class="hljs-number">20</span>, encoder_hidden_size=<span class="hljs-number">128</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1fn1t9t">Create the base <code>roberta-large</code> model from <a href="https://huggingface.co/docs/transformers/main/en/model_doc/auto#transformers.AutoModelForSequenceClassification" rel="nofollow">AutoModelForSequenceClassification</a>, and then wrap the base model and <code>peft_config</code> with <a href="/docs/peft/main/en/package_reference/peft_model#peft.get_peft_model">get_peft_model()</a> to create a <a href="/docs/peft/main/en/package_reference/peft_model#peft.PeftModel">PeftModel</a>. If you’re curious to see how many parameters you’re actually training compared to training on all the model parameters, you can print it out with <a href="/docs/peft/main/en/package_reference/peft_model#peft.PeftModel.print_trainable_parameters">print_trainable_parameters()</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 -->model = AutoModelForSequenceClassification.from_pretrained(model_name_or_path, return_dict=<span class="hljs-literal">True</span>) | |
| model = get_peft_model(model, peft_config) | |
| model.print_trainable_parameters() | |
| <span class="hljs-string">"trainable params: 1351938 || all params: 355662082 || trainable%: 0.38011867680626127"</span><!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1a0gd35">From the 🤗 Transformers library, set up the <a href="https://huggingface.co/docs/transformers/main/en/main_classes/trainer#transformers.TrainingArguments" rel="nofollow">TrainingArguments</a> class with where you want to save the model to, the training hyperparameters, how to evaluate the model, and when to save the checkpoints:</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 -->training_args = TrainingArguments( | |
| output_dir=<span class="hljs-string">"your-name/roberta-large-peft-p-tuning"</span>, | |
| learning_rate=<span class="hljs-number">1e-3</span>, | |
| per_device_train_batch_size=<span class="hljs-number">32</span>, | |
| per_device_eval_batch_size=<span class="hljs-number">32</span>, | |
| num_train_epochs=<span class="hljs-number">2</span>, | |
| weight_decay=<span class="hljs-number">0.01</span>, | |
| evaluation_strategy=<span class="hljs-string">"epoch"</span>, | |
| save_strategy=<span class="hljs-string">"epoch"</span>, | |
| load_best_model_at_end=<span class="hljs-literal">True</span>, | |
| )<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-2l8qwy">Then pass the model, <code>TrainingArguments</code>, datasets, tokenizer, data collator, and evaluation function to the <a href="https://huggingface.co/docs/transformers/main/en/main_classes/trainer#transformers.Trainer" rel="nofollow">Trainer</a> class, which’ll handle the entire training loop for you. Once you’re ready, call <a href="https://huggingface.co/docs/transformers/main/en/main_classes/trainer#transformers.Trainer.train" rel="nofollow">train</a> to start 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 -->trainer = Trainer( | |
| model=model, | |
| args=training_args, | |
| train_dataset=tokenized_datasets[<span class="hljs-string">"train"</span>], | |
| eval_dataset=tokenized_datasets[<span class="hljs-string">"test"</span>], | |
| tokenizer=tokenizer, | |
| data_collator=data_collator, | |
| compute_metrics=compute_metrics, | |
| ) | |
| trainer.train()<!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="share-model" 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="#share-model"><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>Share model</span></h2> <p data-svelte-h="svelte-vati0h">You can store and share your model on the Hub if you’d like. Log in to your Hugging Face account and enter your token when prompted:</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-1yzi7ip">Upload the model to a specifc model repository on the Hub with the <a href="https://huggingface.co/docs/transformers/main/en/main_classes/model#transformers.PreTrainedModel.push_to_hub" rel="nofollow">push_to_hub</a> function:</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.push_to_hub(<span class="hljs-string">"your-name/roberta-large-peft-p-tuning"</span>, use_auth_token=<span class="hljs-literal">True</span>)<!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="inference" 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="#inference"><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>Inference</span></h2> <p data-svelte-h="svelte-19d9n1k">Once the model has been uploaded to the Hub, anyone can easily use it for inference. Load the configuration and model:</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">import</span> torch | |
| <span class="hljs-keyword">from</span> peft <span class="hljs-keyword">import</span> PeftModel, PeftConfig | |
| <span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoModelForSequenceClassification, AutoTokenizer | |
| peft_model_id = <span class="hljs-string">"smangrul/roberta-large-peft-p-tuning"</span> | |
| config = PeftConfig.from_pretrained(peft_model_id) | |
| inference_model = AutoModelForSequenceClassification.from_pretrained(config.base_model_name_or_path) | |
| tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path) | |
| model = PeftModel.from_pretrained(inference_model, peft_model_id)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-yrd6oi">Get some text and tokenize 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 -->classes = [<span class="hljs-string">"not equivalent"</span>, <span class="hljs-string">"equivalent"</span>] | |
| sentence1 = <span class="hljs-string">"Coast redwood trees are the tallest trees on the planet and can grow over 300 feet tall."</span> | |
| sentence2 = <span class="hljs-string">"The coast redwood trees, which can attain a height of over 300 feet, are the tallest trees on earth."</span> | |
| inputs = tokenizer(sentence1, sentence2, truncation=<span class="hljs-literal">True</span>, padding=<span class="hljs-string">"longest"</span>, return_tensors=<span class="hljs-string">"pt"</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1pxzrl4">Pass the inputs to the model to classify the sentences:</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">with</span> torch.no_grad(): | |
| outputs = model(**inputs).logits | |
| <span class="hljs-built_in">print</span>(outputs) | |
| paraphrased_text = torch.softmax(outputs, dim=<span class="hljs-number">1</span>).tolist()[<span class="hljs-number">0</span>] | |
| <span class="hljs-keyword">for</span> i <span class="hljs-keyword">in</span> <span class="hljs-built_in">range</span>(<span class="hljs-built_in">len</span>(classes)): | |
| <span class="hljs-built_in">print</span>(<span class="hljs-string">f"<span class="hljs-subst">{classes[i]}</span>: <span class="hljs-subst">{<span class="hljs-built_in">int</span>(<span class="hljs-built_in">round</span>(paraphrased_text[i] * <span class="hljs-number">100</span>))}</span>%"</span>) | |
| <span class="hljs-string">"not equivalent: 4%"</span> | |
| <span class="hljs-string">"equivalent: 96%"</span><!-- HTML_TAG_END --></pre></div> <p></p> | |
| <script> | |
| { | |
| __sveltekit_b01swq = { | |
| assets: "/docs/peft/main/en", | |
| base: "/docs/peft/main/en", | |
| env: {} | |
| }; | |
| const element = document.currentScript.parentElement; | |
| const data = [null,null]; | |
| Promise.all([ | |
| import("/docs/peft/main/en/_app/immutable/entry/start.d6c2bc1c.js"), | |
| import("/docs/peft/main/en/_app/immutable/entry/app.973a0e51.js") | |
| ]).then(([kit, app]) => { | |
| kit.start(app, element, { | |
| node_ids: [0, 38], | |
| data, | |
| form: null, | |
| error: null | |
| }); | |
| }); | |
| } | |
| </script> | |
Xet Storage Details
- Size:
- 47.8 kB
- Xet hash:
- 03bf1e500f2bbeeb74717d2b99cc89bc34ea8f24ded4b0cde3be83034d181de0
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.