Hugging Face's logo

Buckets:
hf-doc-build
/
doc-dev

Files
xet
hf-doc-build/doc-dev / lighteval /pr_985 /en /quicktour.html
rtrm's picture
rtrm
download
raw
31.8 kB
<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Quick Tour&quot;,&quot;local&quot;:&quot;quick-tour&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Available Commands&quot;,&quot;local&quot;:&quot;available-commands&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Evaluation Backends&quot;,&quot;local&quot;:&quot;evaluation-backends&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;Evaluation Utils&quot;,&quot;local&quot;:&quot;evaluation-utils&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;Utils&quot;,&quot;local&quot;:&quot;utils&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3}],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Basic Usage&quot;,&quot;local&quot;:&quot;basic-usage&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Task Specification&quot;,&quot;local&quot;:&quot;task-specification&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;Running Multiple Tasks&quot;,&quot;local&quot;:&quot;running-multiple-tasks&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3}],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Backend Configuration&quot;,&quot;local&quot;:&quot;backend-configuration&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;General Information&quot;,&quot;local&quot;:&quot;general-information&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;Nanotron&quot;,&quot;local&quot;:&quot;nanotron&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3}],&quot;depth&quot;:2}],&quot;depth&quot;:1}">
 <link href="/docs/lighteval/pr_985/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
 <link rel="modulepreload" href="/docs/lighteval/pr_985/en/_app/immutable/entry/start.a1a6a691.js">
 <link rel="modulepreload" href="/docs/lighteval/pr_985/en/_app/immutable/chunks/scheduler.7da89386.js">
 <link rel="modulepreload" href="/docs/lighteval/pr_985/en/_app/immutable/chunks/singletons.f9d110be.js">
 <link rel="modulepreload" href="/docs/lighteval/pr_985/en/_app/immutable/chunks/paths.bc1dfb10.js">
 <link rel="modulepreload" href="/docs/lighteval/pr_985/en/_app/immutable/entry/app.89a7558b.js">
 <link rel="modulepreload" href="/docs/lighteval/pr_985/en/_app/immutable/chunks/index.20910acc.js">
 <link rel="modulepreload" href="/docs/lighteval/pr_985/en/_app/immutable/nodes/0.ff240387.js">
 <link rel="modulepreload" href="/docs/lighteval/pr_985/en/_app/immutable/chunks/each.e59479a4.js">
 <link rel="modulepreload" href="/docs/lighteval/pr_985/en/_app/immutable/nodes/19.ea772760.js">
 <link rel="modulepreload" href="/docs/lighteval/pr_985/en/_app/immutable/chunks/CodeBlock.143bd81e.js">
 <link rel="modulepreload" href="/docs/lighteval/pr_985/en/_app/immutable/chunks/getInferenceSnippets.375cdad5.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Quick Tour&quot;,&quot;local&quot;:&quot;quick-tour&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Available Commands&quot;,&quot;local&quot;:&quot;available-commands&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Evaluation Backends&quot;,&quot;local&quot;:&quot;evaluation-backends&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;Evaluation Utils&quot;,&quot;local&quot;:&quot;evaluation-utils&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;Utils&quot;,&quot;local&quot;:&quot;utils&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3}],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Basic Usage&quot;,&quot;local&quot;:&quot;basic-usage&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Task Specification&quot;,&quot;local&quot;:&quot;task-specification&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;Running Multiple Tasks&quot;,&quot;local&quot;:&quot;running-multiple-tasks&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3}],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Backend Configuration&quot;,&quot;local&quot;:&quot;backend-configuration&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;General Information&quot;,&quot;local&quot;:&quot;general-information&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;Nanotron&quot;,&quot;local&quot;:&quot;nanotron&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3}],&quot;depth&quot;:2}],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <h1 class="relative group"><a id="quick-tour" 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="#quick-tour"><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>Quick Tour</span></h1> <blockquote class="tip" data-svelte-h="svelte-1a4xnl6"><p>We recommend using the <code>--help</code> flag to get more information about the
available options for each command.
<code>lighteval --help</code></p></blockquote> <p data-svelte-h="svelte-1g3zc6w">Lighteval can be used with several different commands, each optimized for different evaluation scenarios.</p> <h2 class="relative group"><a id="available-commands" 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="#available-commands"><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>Available Commands</span></h2> <h3 class="relative group"><a id="evaluation-backends" 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="#evaluation-backends"><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>Evaluation Backends</span></h3> <ul data-svelte-h="svelte-1h8gca"><li><code>lighteval accelerate</code>: Evaluate models on CPU or one or more GPUs using <a href="https://github.com/huggingface/accelerate" rel="nofollow">🤗
Accelerate</a></li> <li><code>lighteval nanotron</code>: Evaluate models in distributed settings using <a href="https://github.com/huggingface/nanotron" rel="nofollow">⚡️
Nanotron</a></li> <li><code>lighteval vllm</code>: Evaluate models on one or more GPUs using <a href="https://github.com/vllm-project/vllm" rel="nofollow">🚀
VLLM</a></li> <li><code>lighteval custom</code>: Evaluate custom models (can be anything)</li> <li><code>lighteval sglang</code>: Evaluate models using <a href="https://github.com/sgl-project/sglang" rel="nofollow">SGLang</a> as backend</li> <li><code>lighteval endpoint</code>: Evaluate models using various endpoints as backend<ul><li><code>lighteval endpoint inference-endpoint</code>: Evaluate models using Hugging Face’s <a href="https://huggingface.co/inference-endpoints/dedicated" rel="nofollow">Inference Endpoints API</a></li> <li><code>lighteval endpoint tgi</code>: Evaluate models using <a href="https://huggingface.co/docs/text-generation-inference/en/index" rel="nofollow">🔗 Text Generation Inference</a> running locally</li> <li><code>lighteval endpoint litellm</code>: Evaluate models on any compatible API using <a href="https://www.litellm.ai/" rel="nofollow">LiteLLM</a></li> <li><code>lighteval endpoint inference-providers</code>: Evaluate models using <a href="https://huggingface.co/docs/inference-providers/en/index" rel="nofollow">HuggingFace’s inference providers</a> as backend</li></ul></li></ul> <h3 class="relative group"><a id="evaluation-utils" 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="#evaluation-utils"><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>Evaluation Utils</span></h3> <ul data-svelte-h="svelte-1hjb9o8"><li><code>lighteval baseline</code>: Compute baselines for given tasks</li></ul> <h3 class="relative group"><a id="utils" 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="#utils"><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>Utils</span></h3> <ul data-svelte-h="svelte-tf0rfb"><li><code>lighteval tasks</code>: List or inspect tasks<ul><li><code>lighteval tasks list</code>: List all available tasks</li> <li><code>lighteval tasks inspect</code>: Inspect a specific task to see its configuration and samples</li> <li><code>lighteval tasks create</code>: Create a new task from a template</li></ul></li></ul> <h2 class="relative group"><a id="basic-usage" 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="#basic-usage"><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>Basic Usage</span></h2> <p data-svelte-h="svelte-1jqacui">To evaluate <code>GPT-2</code> on the Truthful QA benchmark with <a href="https://github.com/huggingface/accelerate" rel="nofollow">🤗
Accelerate</a>, run:</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 -->lighteval accelerate \
 <span class="hljs-string">&quot;model_name=openai-community/gpt2&quot;</span> \
 <span class="hljs-string">&quot;leaderboard|truthfulqa:mc|0&quot;</span><!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1lfhd94">Here, we first choose a backend (either <code>accelerate</code>, <code>nanotron</code>, <code>endpoint</code>, or <code>vllm</code>), and then specify the model and task(s) to run.</p> <h3 class="relative group"><a id="task-specification" 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="#task-specification"><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>Task Specification</span></h3> <p data-svelte-h="svelte-1u8n90i">The syntax for the task specification might be a bit hard to grasp at first. The format is as follows:</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 -->{suite}|{task}|{num_few_shot}<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1vkd3du">Tasks have a function applied at the sample level and one at the corpus level. For example,</p> <ul data-svelte-h="svelte-1c8qycp"><li>an exact match can be applied per sample, then averaged over the corpus to give the final score</li> <li>samples can be left untouched before applying Corpus BLEU at the corpus level
etc.</li></ul> <p data-svelte-h="svelte-15xqaj2">If the task you are looking at has a sample level function (<code>sample_level_fn</code>) which can be parametrized, you can pass parameters in the CLI.
For example</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 -->{suite}|{task}@{parameter_name1}={value1}@{parameter_name2}={value2},...|0<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-e70eqq">All officially supported tasks can be found at the <a href="available-tasks">tasks_list</a> and in the
<a href="https://github.com/huggingface/lighteval/tree/main/src/lighteval/tasks/extended" rel="nofollow">extended folder</a>.
Moreover, community-provided tasks can be found in the
<a href="https://github.com/huggingface/lighteval/tree/main/community_tasks" rel="nofollow">community</a> folder.</p> <p data-svelte-h="svelte-kxdhy6">For more details on the implementation of the tasks, such as how prompts are constructed or which metrics are used, you can examine the
<a href="https://github.com/huggingface/lighteval/blob/main/src/lighteval/tasks/default_tasks.py" rel="nofollow">implementation file</a>.</p> <h3 class="relative group"><a id="running-multiple-tasks" 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="#running-multiple-tasks"><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>Running Multiple Tasks</span></h3> <p data-svelte-h="svelte-102effw">Running multiple tasks is supported, either with a comma-separated list or by specifying a file path.
The file should be structured like <a href="https://github.com/huggingface/lighteval/blob/main/examples/tasks/recommended_set.txt" rel="nofollow">examples/tasks/recommended_set.txt</a>.
When specifying a path to a file, it should start with <code>./</code>.</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 -->lighteval accelerate \
 <span class="hljs-string">&quot;model_name=openai-community/gpt2&quot;</span> \
 ./path/to/lighteval/examples/tasks/recommended_set.txt
<span class="hljs-comment"># or, e.g., &quot;leaderboard|truthfulqa:mc|0,leaderboard|gsm8k|3&quot;</span><!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="backend-configuration" 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="#backend-configuration"><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>Backend Configuration</span></h2> <h3 class="relative group"><a id="general-information" 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="#general-information"><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>General Information</span></h3> <p data-svelte-h="svelte-17uu0an">The <code>model-args</code> argument takes a string representing a list of model
arguments. The arguments allowed vary depending on the backend you use and
correspond to the fields of the model configurations.</p> <p data-svelte-h="svelte-quwklj">The model configurations can be found <a href="./package_reference/models">here</a>.</p> <p data-svelte-h="svelte-1eknffc">All models allow you to post-process your reasoning model predictions
to remove the thinking tokens from the trace used to compute the metrics,
using <code>--remove-reasoning-tags</code> and <code>--reasoning-tags</code> to specify which
reasoning tags to remove (defaults to <code>&lt;think&gt;</code> and <code>&lt;/think&gt;</code>).</p> <p data-svelte-h="svelte-16brxvi">Here’s an example with <code>mistralai/Magistral-Small-2507</code> which outputs custom
thinking tokens:</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 -->lighteval vllm \
 <span class="hljs-string">&quot;model_name=mistralai/Magistral-Small-2507,dtype=float16,data_parallel_size=4&quot;</span> \
 <span class="hljs-string">&quot;lighteval|aime24|0&quot;</span> \
 --remove-reasoning-tags \
 --reasoning-tags=<span class="hljs-string">&quot;[(&#x27;[THINK]&#x27;,&#x27;[/THINK]&#x27;)]&quot;</span><!-- HTML_TAG_END --></pre></div> <h3 class="relative group"><a id="nanotron" 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="#nanotron"><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>Nanotron</span></h3> <p data-svelte-h="svelte-l3or2u">To evaluate a model trained with Nanotron on a single GPU:</p> <blockquote class="warning" data-svelte-h="svelte-1w9heqt"><p>Nanotron models cannot be evaluated without torchrun.</p></blockquote> <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 -->torchrun --standalone --nnodes=1 --nproc-per-node=1 \
 src/lighteval/__main__.py nanotron \
 --checkpoint-config-path ../nanotron/checkpoints/10/config.yaml \
 --lighteval-config-path examples/nanotron/lighteval_config_override_template.yaml<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-s5fucd">The <code>nproc-per-node</code> argument should match the data, tensor, and pipeline
parallelism configured in the <code>lighteval_config_template.yaml</code> file.
That is: <code>nproc-per-node = data_parallelism * tensor_parallelism * pipeline_parallelism</code>.</p> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/lighteval/blob/main/docs/source/quicktour.mdx" target="_blank"><span data-svelte-h="svelte-1kd6by1">&lt;</span> <span data-svelte-h="svelte-x0xyl0">&gt;</span> <span data-svelte-h="svelte-1dajgef"><span class="underline ml-1.5">Update</span> on GitHub</span></a> <p></p>
<script>
 {
 __sveltekit_n0glyp = {
 assets: "/docs/lighteval/pr_985/en",
 base: "/docs/lighteval/pr_985/en",
 env: {}
 };
 const element = document.currentScript.parentElement;
 const data = [null,null];
 Promise.all([
 import("/docs/lighteval/pr_985/en/_app/immutable/entry/start.a1a6a691.js"),
 import("/docs/lighteval/pr_985/en/_app/immutable/entry/app.89a7558b.js")
 ]).then(([kit, app]) => {
 kit.start(app, element, {
 node_ids: [0, 19],
 data,
 form: null,
 error: null
 });
 });
 }
 </script>

Xet Storage Details

Size:
31.8 kB
·
Xet hash:
d5acdde3b9124fe42ba9c5561072389a86f046b56333a948fb268c56a275d8d6

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.