Buckets:

rtrm's picture
download
raw
11.2 kB
<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;FLAN-UL2&quot;,&quot;local&quot;:&quot;flan-ul2&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Overview&quot;,&quot;local&quot;:&quot;overview&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Running on low resource devices&quot;,&quot;local&quot;:&quot;running-on-low-resource-devices&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}">
<link href="/docs/transformers/main/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
<link rel="modulepreload" href="/docs/transformers/main/en/_app/immutable/entry/start.2135b7e6.js">
<link rel="modulepreload" href="/docs/transformers/main/en/_app/immutable/chunks/scheduler.25b97de1.js">
<link rel="modulepreload" href="/docs/transformers/main/en/_app/immutable/chunks/singletons.0f2b7d5f.js">
<link rel="modulepreload" href="/docs/transformers/main/en/_app/immutable/chunks/index.e188933d.js">
<link rel="modulepreload" href="/docs/transformers/main/en/_app/immutable/chunks/paths.3d04d2c6.js">
<link rel="modulepreload" href="/docs/transformers/main/en/_app/immutable/entry/app.24372c84.js">
<link rel="modulepreload" href="/docs/transformers/main/en/_app/immutable/chunks/index.d9030fc9.js">
<link rel="modulepreload" href="/docs/transformers/main/en/_app/immutable/nodes/0.026d2fdd.js">
<link rel="modulepreload" href="/docs/transformers/main/en/_app/immutable/chunks/each.e59479a4.js">
<link rel="modulepreload" href="/docs/transformers/main/en/_app/immutable/nodes/142.cfcf9841.js">
<link rel="modulepreload" href="/docs/transformers/main/en/_app/immutable/chunks/Tip.baa67368.js">
<link rel="modulepreload" href="/docs/transformers/main/en/_app/immutable/chunks/CodeBlock.e6cd0d95.js">
<link rel="modulepreload" href="/docs/transformers/main/en/_app/immutable/chunks/EditOnGithub.91d95064.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;FLAN-UL2&quot;,&quot;local&quot;:&quot;flan-ul2&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Overview&quot;,&quot;local&quot;:&quot;overview&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Running on low resource devices&quot;,&quot;local&quot;:&quot;running-on-low-resource-devices&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <h1 class="relative group"><a id="flan-ul2" 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="#flan-ul2"><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>FLAN-UL2</span></h1> <h2 class="relative group"><a id="overview" 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="#overview"><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>Overview</span></h2> <p data-svelte-h="svelte-gpwdss">Flan-UL2 is an encoder decoder model based on the T5 architecture. It uses the same configuration as the <a href="ul2">UL2</a> model released earlier last year.
It was fine tuned using the “Flan” prompt tuning and dataset collection. Similar to <code>Flan-T5</code>, one can directly use FLAN-UL2 weights without finetuning the model:</p> <p data-svelte-h="svelte-10cnwdi">According to the original blog here are the notable improvements:</p> <ul data-svelte-h="svelte-145gzzg"><li>The original UL2 model was only trained with receptive field of 512, which made it non-ideal for N-shot prompting where N is large.</li> <li>The Flan-UL2 checkpoint uses a receptive field of 2048 which makes it more usable for few-shot in-context learning.</li> <li>The original UL2 model also had mode switch tokens that was rather mandatory to get good performance. However, they were a little cumbersome as this requires often some changes during inference or finetuning. In this update/change, we continue training UL2 20B for an additional 100k steps (with small batch) to forget “mode tokens” before applying Flan instruction tuning. This Flan-UL2 checkpoint does not require mode tokens anymore.
Google has released the following variants:</li></ul> <p data-svelte-h="svelte-tjdjai">The original checkpoints can be found <a href="https://github.com/google-research/t5x/blob/main/docs/models.md#flan-ul2-checkpoints" rel="nofollow">here</a>.</p> <h2 class="relative group"><a id="running-on-low-resource-devices" 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-on-low-resource-devices"><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 on low resource devices</span></h2> <p data-svelte-h="svelte-1qrqz37">The model is pretty heavy (~40GB in half precision) so if you just want to run the model, make sure you load your model in 8bit, and use <code>device_map=&quot;auto&quot;</code> to make sure you don’t have any OOM issue!</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-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoModelForSeq2SeqLM, AutoTokenizer
<span class="hljs-meta">&gt;&gt;&gt; </span>model = AutoModelForSeq2SeqLM.from_pretrained(<span class="hljs-string">&quot;google/flan-ul2&quot;</span>, load_in_8bit=<span class="hljs-literal">True</span>, device_map=<span class="hljs-string">&quot;auto&quot;</span>)
<span class="hljs-meta">&gt;&gt;&gt; </span>tokenizer = AutoTokenizer.from_pretrained(<span class="hljs-string">&quot;google/flan-ul2&quot;</span>)
<span class="hljs-meta">&gt;&gt;&gt; </span>inputs = tokenizer(<span class="hljs-string">&quot;A step by step recipe to make bolognese pasta:&quot;</span>, return_tensors=<span class="hljs-string">&quot;pt&quot;</span>)
<span class="hljs-meta">&gt;&gt;&gt; </span>outputs = model.generate(**inputs)
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-built_in">print</span>(tokenizer.batch_decode(outputs, skip_special_tokens=<span class="hljs-literal">True</span>))
[<span class="hljs-string">&#x27;In a large skillet, brown the ground beef and onion over medium heat. Add the garlic&#x27;</span>]<!-- HTML_TAG_END --></pre></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-qwctac">Refer to <a href="t5">T5’s documentation page</a> for API reference, tips, code examples and notebooks.</p></div> <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/model_doc/flan-ul2.md" 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_1xexzbk = {
assets: "/docs/transformers/main/en",
base: "/docs/transformers/main/en",
env: {}
};
const element = document.currentScript.parentElement;
const data = [null,null];
Promise.all([
import("/docs/transformers/main/en/_app/immutable/entry/start.2135b7e6.js"),
import("/docs/transformers/main/en/_app/immutable/entry/app.24372c84.js")
]).then(([kit, app]) => {
kit.start(app, element, {
node_ids: [0, 142],
data,
form: null,
error: null
});
});
}
</script>

Xet Storage Details

Size:
11.2 kB
·
Xet hash:
9807c05a55703b4fe75199501499fd2868cd175df84405224019d31ec4943918

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