Buckets:
| <meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Multi Adapter RL (MARL) - a single base model for everything","local":"multi-adapter-rl-marl---a-single-base-model-for-everything","sections":[{"title":"Requirements","local":"requirements","sections":[],"depth":2},{"title":"Summary","local":"summary","sections":[],"depth":2},{"title":"Quickstart","local":"quickstart","sections":[],"depth":2},{"title":"Advanced usage","local":"advanced-usage","sections":[{"title":"Control on the adapter name","local":"control-on-the-adapter-name","sections":[],"depth":3},{"title":"Using 4-bit and 8-bit base models","local":"using-4-bit-and-8-bit-base-models","sections":[],"depth":3}],"depth":2}],"depth":1}"> | |
| <link href="/docs/trl/main/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload"> | |
| <link rel="modulepreload" href="/docs/trl/main/en/_app/immutable/entry/start.183b226a.js"> | |
| <link rel="modulepreload" href="/docs/trl/main/en/_app/immutable/chunks/scheduler.85c25b89.js"> | |
| <link rel="modulepreload" href="/docs/trl/main/en/_app/immutable/chunks/singletons.98fe034d.js"> | |
| <link rel="modulepreload" href="/docs/trl/main/en/_app/immutable/chunks/paths.eb9df337.js"> | |
| <link rel="modulepreload" href="/docs/trl/main/en/_app/immutable/entry/app.9853b7f5.js"> | |
| <link rel="modulepreload" href="/docs/trl/main/en/_app/immutable/chunks/index.c142fe32.js"> | |
| <link rel="modulepreload" href="/docs/trl/main/en/_app/immutable/nodes/0.5efac18d.js"> | |
| <link rel="modulepreload" href="/docs/trl/main/en/_app/immutable/chunks/each.e59479a4.js"> | |
| <link rel="modulepreload" href="/docs/trl/main/en/_app/immutable/nodes/23.b656364e.js"> | |
| <link rel="modulepreload" href="/docs/trl/main/en/_app/immutable/chunks/CodeBlock.a5e95a57.js"> | |
| <link rel="modulepreload" href="/docs/trl/main/en/_app/immutable/chunks/EditOnGithub.a592e7aa.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"Multi Adapter RL (MARL) - a single base model for everything","local":"multi-adapter-rl-marl---a-single-base-model-for-everything","sections":[{"title":"Requirements","local":"requirements","sections":[],"depth":2},{"title":"Summary","local":"summary","sections":[],"depth":2},{"title":"Quickstart","local":"quickstart","sections":[],"depth":2},{"title":"Advanced usage","local":"advanced-usage","sections":[{"title":"Control on the adapter name","local":"control-on-the-adapter-name","sections":[],"depth":3},{"title":"Using 4-bit and 8-bit base models","local":"using-4-bit-and-8-bit-base-models","sections":[],"depth":3}],"depth":2}],"depth":1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <h1 class="relative group"><a id="multi-adapter-rl-marl---a-single-base-model-for-everything" 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="#multi-adapter-rl-marl---a-single-base-model-for-everything"><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>Multi Adapter RL (MARL) - a single base model for everything</span></h1> <p data-svelte-h="svelte-1ni6bkb">Here we present an approach that uses a single base model for the entire PPO algorithm - which includes retrieving the reference logits, computing the active logits and the rewards. This feature is experimental as we did not test the convergence of the approach. We encourage the community to let us know if they potentially face issues.</p> <h2 class="relative group"><a id="requirements" 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="#requirements"><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>Requirements</span></h2> <p data-svelte-h="svelte-1crdfuc">You just need to install <code>peft</code> and optionally install <code>bitsandbytes</code> as well if you want to go for 8bit base models, for more memory efficient finetuning.</p> <h2 class="relative group"><a id="summary" 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="#summary"><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>Summary</span></h2> <p data-svelte-h="svelte-1nxlg56">You need to address this approach in three stages that we summarize as follows:</p> <p data-svelte-h="svelte-1v59j6k">1- Train a base model on the target domain (e.g. <a href="https://huggingface.co/datasets/stanfordnlp/imdb" rel="nofollow">IMDB dataset</a>) - this is the Supervised Fine Tuning stage - it can leverage the <code>SFTTrainer</code> from TRL. | |
| 2- Train a reward model using <code>peft</code>. This is required in order to re-use the adapter during the RL optimisation process (step 3 below). We show an example of leveraging the <code>RewardTrainer</code> from TRL in <a href="https://github.com/huggingface/trl/tree/main/examples/scripts/reward_modeling.py" rel="nofollow">this example</a> | |
| 3- Fine tune new adapters on the base model using PPO and the reward adapter. (“0 abstraction RL”)</p> <p data-svelte-h="svelte-x4geit">Make sure to use the same model (i.e. same architecture and same weights) for the stages 2 & 3.</p> <h2 class="relative group"><a id="quickstart" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#quickstart"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Quickstart</span></h2> <p data-svelte-h="svelte-yusdbc">Let us assume you have trained your reward adapter on <code>llama-7b</code> model using <code>RewardTrainer</code> and pushed the weights on the hub under <code>trl-lib/llama-7b-hh-rm-adapter</code>. | |
| When doing PPO, before passing the model to <code>PPOTrainer</code> create your model 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 -->model_name = <span class="hljs-string">"huggyllama/llama-7b"</span> | |
| rm_adapter_id = <span class="hljs-string">"trl-lib/llama-7b-hh-rm-adapter"</span> | |
| <span class="hljs-comment"># PPO adapter</span> | |
| lora_config = LoraConfig( | |
| r=<span class="hljs-number">16</span>, | |
| lora_alpha=<span class="hljs-number">32</span>, | |
| lora_dropout=<span class="hljs-number">0.05</span>, | |
| bias=<span class="hljs-string">"none"</span>, | |
| task_type=<span class="hljs-string">"CAUSAL_LM"</span>, | |
| ) | |
| model = AutoModelForCausalLMWithValueHead.from_pretrained( | |
| model_name, | |
| peft_config=lora_config, | |
| reward_adapter=rm_adapter_id, | |
| ) | |
| ... | |
| trainer = PPOTrainer( | |
| model=model, | |
| ... | |
| ) | |
| ...<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-uwecsv">Then inside your PPO training loop, call the <code>compute_reward_score</code> method by accessing the <code>model</code> attribute from <code>PPOTrainer</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 -->rewards = trainer.model.compute_reward_score(**inputs)<!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="advanced-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="#advanced-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>Advanced usage</span></h2> <h3 class="relative group"><a id="control-on-the-adapter-name" 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="#control-on-the-adapter-name"><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>Control on the adapter name</span></h3> <p data-svelte-h="svelte-3l2jwi">If you are familiar with the <code>peft</code> library, you know that you can use multiple adapters inside the same model. What you can do is train multiple adapters on the same base model to fine-tune on different policies. | |
| In this case, you want to be able to control the adapter name you want to activate back, after retrieving the reward. For that, simply pass the appropriate <code>adapter_name</code> to <code>ppo_adapter_name</code> argument when calling <code>compute_reward_score</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 -->adapter_name_policy_1 = <span class="hljs-string">"policy_1"</span> | |
| rewards = trainer.model.compute_reward_score(**inputs, ppo_adapter_name=adapter_name_policy_1) | |
| ...<!-- HTML_TAG_END --></pre></div> <h3 class="relative group"><a id="using-4-bit-and-8-bit-base-models" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#using-4-bit-and-8-bit-base-models"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Using 4-bit and 8-bit base models</span></h3> <p data-svelte-h="svelte-17i0flk">For more memory efficient fine-tuning, you can load your base model in 8-bit or 4-bit while keeping the adapters in the default precision (float32). | |
| Just pass the appropriate arguments (i.e. <code>load_in_8bit=True</code> or <code>load_in_4bit=True</code>) to <code>AutoModelForCausalLMWithValueHead.from_pretrained</code> as follows (assuming you have installed <code>bitsandbytes</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 -->model_name = <span class="hljs-string">"llama-7b"</span> | |
| rm_adapter_id = <span class="hljs-string">"trl-lib/llama-7b-hh-rm-adapter"</span> | |
| <span class="hljs-comment"># PPO adapter</span> | |
| lora_config = LoraConfig( | |
| r=<span class="hljs-number">16</span>, | |
| lora_alpha=<span class="hljs-number">32</span>, | |
| lora_dropout=<span class="hljs-number">0.05</span>, | |
| bias=<span class="hljs-string">"none"</span>, | |
| task_type=<span class="hljs-string">"CAUSAL_LM"</span>, | |
| ) | |
| model = AutoModelForCausalLMWithValueHead.from_pretrained( | |
| model_name, | |
| peft_config=lora_config, | |
| reward_adapter=rm_adapter_id, | |
| load_in_8bit=<span class="hljs-literal">True</span>, | |
| ) | |
| ... | |
| trainer = PPOTrainer( | |
| model=model, | |
| ... | |
| ) | |
| ...<!-- 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/trl/blob/main/docs/source/multi_adapter_rl.mdx" target="_blank"><span data-svelte-h="svelte-1kd6by1"><</span> <span data-svelte-h="svelte-x0xyl0">></span> <span data-svelte-h="svelte-1dajgef"><span class="underline ml-1.5">Update</span> on GitHub</span></a> <p></p> | |
| <script> | |
| { | |
| __sveltekit_5yobsv = { | |
| assets: "/docs/trl/main/en", | |
| base: "/docs/trl/main/en", | |
| env: {} | |
| }; | |
| const element = document.currentScript.parentElement; | |
| const data = [null,null]; | |
| Promise.all([ | |
| import("/docs/trl/main/en/_app/immutable/entry/start.183b226a.js"), | |
| import("/docs/trl/main/en/_app/immutable/entry/app.9853b7f5.js") | |
| ]).then(([kit, app]) => { | |
| kit.start(app, element, { | |
| node_ids: [0, 23], | |
| data, | |
| form: null, | |
| error: null | |
| }); | |
| }); | |
| } | |
| </script> | |
Xet Storage Details
- Size:
- 21.7 kB
- Xet hash:
- 7b433630b3a99931954f91121910b675a44613c40533346d41d0afb57a759f84
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.