Buckets:

rtrm's picture
download
raw
10 kB
<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;ExecuTorch&quot;,&quot;local&quot;:&quot;executorch&quot;,&quot;sections&quot;:[],&quot;depth&quot;: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/19.fd4da2ba.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/EditOnGithub.7faefd25.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;ExecuTorch&quot;,&quot;local&quot;:&quot;executorch&quot;,&quot;sections&quot;:[],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <h1 class="relative group"><a id="executorch" 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="#executorch"><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>ExecuTorch</span></h1> <p data-svelte-h="svelte-uwjuic"><a href="https://pytorch.org/executorch/stable/index.html" rel="nofollow">ExecuTorch</a> is a platform that enables PyTorch training and inference programs to be run on mobile and edge devices. It is powered by <a href="https://pytorch.org/docs/stable/torch.compiler.html" rel="nofollow">torch.compile</a> and <a href="https://pytorch.org/docs/main/export.html" rel="nofollow">torch.export</a> for performance and deployment.</p> <p data-svelte-h="svelte-mn86fo">You can use ExecuTorch with Transformers with <a href="https://pytorch.org/docs/main/export.html" rel="nofollow">torch.export</a>. The <a href="/docs/transformers/pr_36839/en/main_classes/executorch#transformers.convert_and_export_with_cache">convert_and_export_with_cache()</a> method converts a <a href="/docs/transformers/pr_36839/en/main_classes/model#transformers.PreTrainedModel">PreTrainedModel</a> into an exportable module. Under the hood, it uses <a href="https://pytorch.org/docs/main/export.html" rel="nofollow">torch.export</a> to export the model, ensuring compatibility with ExecuTorch.</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> transformers <span class="hljs-keyword">import</span> LlamaForCausalLM, AutoTokenizer, GenerationConfig
<span class="hljs-keyword">from</span> transformers.integrations.executorch <span class="hljs-keyword">import</span>(
TorchExportableModuleWithStaticCache,
convert_and_export_with_cache
)
generation_config = GenerationConfig(
use_cache=<span class="hljs-literal">True</span>,
cache_implementation=<span class="hljs-string">&quot;static&quot;</span>,
cache_config={
<span class="hljs-string">&quot;batch_size&quot;</span>: <span class="hljs-number">1</span>,
<span class="hljs-string">&quot;max_cache_len&quot;</span>: <span class="hljs-number">20</span>,
}
)
tokenizer = AutoTokenizer.from_pretrained(<span class="hljs-string">&quot;meta-llama/Llama-3.2-1B&quot;</span>, pad_token=<span class="hljs-string">&quot;&lt;/s&gt;&quot;</span>, padding_side=<span class="hljs-string">&quot;right&quot;</span>)
model = LlamaForCausalLM.from_pretrained(<span class="hljs-string">&quot;meta-llama/Llama-3.2-1B&quot;</span>, device_map=<span class="hljs-string">&quot;auto&quot;</span>, torch_dtype=torch.bfloat16, attn_implementation=<span class="hljs-string">&quot;sdpa&quot;</span>, generation_config=generation_config)
exported_program = convert_and_export_with_cache(model)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-4zcxej">The exported PyTorch model is now ready to be used with ExecuTorch. Wrap the model with <a href="/docs/transformers/pr_36839/en/main_classes/executorch#transformers.TorchExportableModuleWithStaticCache">TorchExportableModuleWithStaticCache</a> to generate 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 -->prompts = [<span class="hljs-string">&quot;Simply put, the theory of relativity states that &quot;</span>]
prompt_tokens = tokenizer(prompts, return_tensors=<span class="hljs-string">&quot;pt&quot;</span>, padding=<span class="hljs-literal">True</span>).to(model.device)
prompt_token_ids = prompt_tokens[<span class="hljs-string">&quot;input_ids&quot;</span>]
generated_ids = TorchExportableModuleWithStaticCache.generate(
exported_program=exported_program, prompt_token_ids=prompt_token_ids, max_new_tokens=<span class="hljs-number">20</span>,
)
generated_text = tokenizer.batch_decode(generated_ids, skip_special_tokens=<span class="hljs-literal">True</span>)
<span class="hljs-built_in">print</span>(generated_text)
[<span class="hljs-string">&#x27;Simply put, the theory of relativity states that 1) the speed of light is the&#x27;</span>]<!-- HTML_TAG_END --></pre></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/executorch.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_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, 19],
data,
form: null,
error: null
});
});
}
</script>

Xet Storage Details

Size:
10 kB
·
Xet hash:
d56493dba98ee6f1c01e4785e479914305dbd57f477bbe673bf88a3d3878d499

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