Buckets:

hf-doc-build
/

doc-dev

Files

xet

hf-doc-build/doc-dev / transformers /pr_33913 /it /converting_tensorflow_models.html

rtrm

15 days ago

download

raw

29.6 kB

	<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Convertire checkpoint di Tensorflow","local":"convertire-checkpoint-di-tensorflow","sections":[{"title":"BERT","local":"bert","sections":[],"depth":2},{"title":"ALBERT","local":"albert","sections":[],"depth":2},{"title":"OpenAI GPT","local":"openai-gpt","sections":[],"depth":2},{"title":"OpenAI GPT-2","local":"openai-gpt-2","sections":[],"depth":2},{"title":"XLNet","local":"xlnet","sections":[],"depth":2},{"title":"XLM","local":"xlm","sections":[],"depth":2},{"title":"T5","local":"t5","sections":[],"depth":2}],"depth":1}">
	<link href="/docs/transformers/pr_33913/it/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
	<link rel="modulepreload" href="/docs/transformers/pr_33913/it/_app/immutable/entry/start.cef8f86b.js">
	<link rel="modulepreload" href="/docs/transformers/pr_33913/it/_app/immutable/chunks/scheduler.36a0863c.js">
	<link rel="modulepreload" href="/docs/transformers/pr_33913/it/_app/immutable/chunks/singletons.39cd3b38.js">
	<link rel="modulepreload" href="/docs/transformers/pr_33913/it/_app/immutable/chunks/index.733708bb.js">
	<link rel="modulepreload" href="/docs/transformers/pr_33913/it/_app/immutable/chunks/paths.64312358.js">
	<link rel="modulepreload" href="/docs/transformers/pr_33913/it/_app/immutable/entry/app.d399d34f.js">
	<link rel="modulepreload" href="/docs/transformers/pr_33913/it/_app/immutable/chunks/index.9c13489a.js">
	<link rel="modulepreload" href="/docs/transformers/pr_33913/it/_app/immutable/nodes/0.7859fb6f.js">
	<link rel="modulepreload" href="/docs/transformers/pr_33913/it/_app/immutable/chunks/each.e59479a4.js">
	<link rel="modulepreload" href="/docs/transformers/pr_33913/it/_app/immutable/nodes/8.f8ec4af8.js">
	<link rel="modulepreload" href="/docs/transformers/pr_33913/it/_app/immutable/chunks/Tip.3b06990e.js">
	<link rel="modulepreload" href="/docs/transformers/pr_33913/it/_app/immutable/chunks/CodeBlock.05d8ec32.js">
	<link rel="modulepreload" href="/docs/transformers/pr_33913/it/_app/immutable/chunks/EditOnGithub.e88f2b7b.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"Convertire checkpoint di Tensorflow","local":"convertire-checkpoint-di-tensorflow","sections":[{"title":"BERT","local":"bert","sections":[],"depth":2},{"title":"ALBERT","local":"albert","sections":[],"depth":2},{"title":"OpenAI GPT","local":"openai-gpt","sections":[],"depth":2},{"title":"OpenAI GPT-2","local":"openai-gpt-2","sections":[],"depth":2},{"title":"XLNet","local":"xlnet","sections":[],"depth":2},{"title":"XLM","local":"xlm","sections":[],"depth":2},{"title":"T5","local":"t5","sections":[],"depth":2}],"depth":1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <h1 class="relative group"><a id="convertire-checkpoint-di-tensorflow" 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="#convertire-checkpoint-di-tensorflow"><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>Convertire checkpoint di Tensorflow</span></h1> <p data-svelte-h="svelte-1h7vx38">È disponibile un’interfaccia a linea di comando per convertire gli originali checkpoint di Bert/GPT/GPT-2/Transformer-XL/XLNet/XLM
	in modelli che possono essere caricati utilizzando i metodi <code>from_pretrained</code> della libreria.</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-pno2uk">A partire dalla versione 2.3.0 lo script di conversione è parte di transformers CLI (<strong>transformers-cli</strong>), disponibile in ogni installazione
	di transformers >=2.3.0.</p> <p data-svelte-h="svelte-10735wn">La seguente documentazione riflette il formato dei comandi di <strong>transformers-cli convert</strong>.</p></div> <h2 class="relative group"><a id="bert" 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="#bert"><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>BERT</span></h2> <p data-svelte-h="svelte-12ewxsd">Puoi convertire qualunque checkpoint Tensorflow di BERT (in particolare
	<a href="https://github.com/google-research/bert#pre-trained-models" rel="nofollow">i modeli pre-allenati rilasciati da Google</a>)
	in un file di salvataggio Pytorch utilizzando lo script
	<a href="https://github.com/huggingface/transformers/tree/main/src/transformers/models/bert/convert_bert_original_tf_checkpoint_to_pytorch.py" rel="nofollow">convert_bert_original_tf_checkpoint_to_pytorch.py</a>.</p> <p data-svelte-h="svelte-1tk7qod">Questo CLI prende come input un checkpoint di Tensorflow (tre files che iniziano con <code>bert_model.ckpt</code>) ed il relativo
	file di configurazione (<code>bert_config.json</code>), crea un modello Pytorch per questa configurazione, carica i pesi dal
	checkpoint di Tensorflow nel modello di Pytorch e salva il modello che ne risulta in un file di salvataggio standard di Pytorch che
	può essere importato utilizzando <code>from_pretrained()</code> (vedi l’esempio nel
	<a href="quicktour">quicktour</a> , <a href="https://github.com/huggingface/transformers/tree/main/examples/pytorch/text-classification/run_glue.py" rel="nofollow">run_glue.py</a> ).</p> <p data-svelte-h="svelte-ltah7v">Devi soltanto lanciare questo script di conversione <strong>una volta</strong> per ottenere un modello Pytorch. Dopodichè, potrai tralasciare
	il checkpoint di Tensorflow (i tre files che iniziano con <code>bert_model.ckpt</code>), ma assicurati di tenere il file di configurazione
	(<code>bert_config.json</code>) ed il file di vocabolario (<code>vocab.txt</code>) in quanto queste componenti sono necessarie anche per il modello di Pytorch.</p> <p data-svelte-h="svelte-1gwoxz3">Per lanciare questo specifico script di conversione avrai bisogno di un’installazione di Tensorflow e di Pytorch
	(<code>pip install tensorflow</code>). Il resto della repository richiede soltanto Pytorch.</p> <p data-svelte-h="svelte-13c4iak">Questo è un esempio del processo di conversione per un modello <code>BERT-Base Uncased</code> pre-allenato:</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-built_in">export</span> BERT_BASE_DIR=/path/to/bert/uncased_L-12_H-768_A-12
	transformers-cli convert --model_type bert \
	--tf_checkpoint <span class="hljs-variable">$BERT_BASE_DIR</span>/bert_model.ckpt \
	--config <span class="hljs-variable">$BERT_BASE_DIR</span>/bert_config.json \
	--pytorch_dump_output <span class="hljs-variable">$BERT_BASE_DIR</span>/pytorch_model.bin<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-17ev3v6">Puoi scaricare i modelli pre-allenati di Google per la conversione <a href="https://github.com/google-research/bert#pre-trained-models" rel="nofollow">qua</a>.</p> <h2 class="relative group"><a id="albert" 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="#albert"><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>ALBERT</span></h2> <p data-svelte-h="svelte-bo3lt9">Per il modello ALBERT, converti checkpoint di Tensoflow in Pytorch utilizzando lo script
	<a href="https://github.com/huggingface/transformers/tree/main/src/transformers/models/albert/convert_albert_original_tf_checkpoint_to_pytorch.py" rel="nofollow">convert_albert_original_tf_checkpoint_to_pytorch.py</a>.</p> <p data-svelte-h="svelte-xfj20k">Il CLI prende come input un checkpoint di Tensorflow (tre files che iniziano con <code>model.ckpt-best</code>) e i relativi file di
	configurazione (<code>albert_config.json</code>), dopodichè crea e salva un modello Pytorch. Per lanciare questa conversione
	avrai bisogno di un’installazione di Tensorflow e di Pytorch.</p> <p data-svelte-h="svelte-hzzhlx">Ecco un esempio del procedimento di conversione di un modello <code>ALBERT Base</code> pre-allenato:</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-built_in">export</span> ALBERT_BASE_DIR=/path/to/albert/albert_base
	transformers-cli convert --model_type albert \
	--tf_checkpoint <span class="hljs-variable">$ALBERT_BASE_DIR</span>/model.ckpt-best \
	--config <span class="hljs-variable">$ALBERT_BASE_DIR</span>/albert_config.json \
	--pytorch_dump_output <span class="hljs-variable">$ALBERT_BASE_DIR</span>/pytorch_model.bin<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-p8zabj">Puoi scaricare i modelli pre-allenati di Google per la conversione <a href="https://github.com/google-research/albert#pre-trained-models" rel="nofollow">qui</a>.</p> <h2 class="relative group"><a id="openai-gpt" 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="#openai-gpt"><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>OpenAI GPT</span></h2> <p data-svelte-h="svelte-xb9em5">Ecco un esempio del processo di conversione di un modello OpenAI GPT pre-allenato, assumendo che il tuo checkpoint di NumPy
	sia salvato nello stesso formato dei modelli pre-allenati OpenAI (vedi <a href="https://github.com/openai/finetune-transformer-lm" rel="nofollow">qui</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 --><span class="hljs-built_in">export</span> OPENAI_GPT_CHECKPOINT_FOLDER_PATH=/path/to/openai/pretrained/numpy/weights
	transformers-cli convert --model_type gpt \
	--tf_checkpoint <span class="hljs-variable">$OPENAI_GPT_CHECKPOINT_FOLDER_PATH</span> \
	--pytorch_dump_output <span class="hljs-variable">$PYTORCH_DUMP_OUTPUT</span> \
	[--config OPENAI_GPT_CONFIG] \
	[--finetuning_task_name OPENAI_GPT_FINETUNED_TASK] \<!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="openai-gpt-2" 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="#openai-gpt-2"><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>OpenAI GPT-2</span></h2> <p data-svelte-h="svelte-ql4a6">Ecco un esempio del processo di conversione di un modello OpenAI GPT-2 pre-allenato (vedi <a href="https://github.com/openai/gpt-2" rel="nofollow">qui</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 --><span class="hljs-built_in">export</span> OPENAI_GPT2_CHECKPOINT_PATH=/path/to/openai-community/gpt2/pretrained/weights
	transformers-cli convert --model_type gpt2 \
	--tf_checkpoint <span class="hljs-variable">$OPENAI_GPT2_CHECKPOINT_PATH</span> \
	--pytorch_dump_output <span class="hljs-variable">$PYTORCH_DUMP_OUTPUT</span> \
	[--config OPENAI_GPT2_CONFIG] \
	[--finetuning_task_name OPENAI_GPT2_FINETUNED_TASK]<!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="xlnet" 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="#xlnet"><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>XLNet</span></h2> <p data-svelte-h="svelte-1pi6g15">Ecco un esempio del processo di conversione di un modello XLNet pre-allenato:</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-built_in">export</span> TRANSFO_XL_CHECKPOINT_PATH=/path/to/xlnet/checkpoint
	<span class="hljs-built_in">export</span> TRANSFO_XL_CONFIG_PATH=/path/to/xlnet/config
	transformers-cli convert --model_type xlnet \
	--tf_checkpoint <span class="hljs-variable">$TRANSFO_XL_CHECKPOINT_PATH</span> \
	--config <span class="hljs-variable">$TRANSFO_XL_CONFIG_PATH</span> \
	--pytorch_dump_output <span class="hljs-variable">$PYTORCH_DUMP_OUTPUT</span> \
	[--finetuning_task_name XLNET_FINETUNED_TASK] \<!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="xlm" 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="#xlm"><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>XLM</span></h2> <p data-svelte-h="svelte-nv1q1">Ecco un esempio del processo di conversione di un modello XLM pre-allenato:</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-built_in">export</span> XLM_CHECKPOINT_PATH=/path/to/xlm/checkpoint
	transformers-cli convert --model_type xlm \
	--tf_checkpoint <span class="hljs-variable">$XLM_CHECKPOINT_PATH</span> \
	--pytorch_dump_output <span class="hljs-variable">$PYTORCH_DUMP_OUTPUT</span>
	[--config XML_CONFIG] \
	[--finetuning_task_name XML_FINETUNED_TASK]<!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="t5" 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="#t5"><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>T5</span></h2> <p data-svelte-h="svelte-1xcr0cf">Ecco un esempio del processo di conversione di un modello T5 pre-allenato:</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-built_in">export</span> T5=/path/to/t5/uncased_L-12_H-768_A-12
	transformers-cli convert --model_type t5 \
	--tf_checkpoint <span class="hljs-variable">$T5</span>/t5_model.ckpt \
	--config <span class="hljs-variable">$T5</span>/t5_config.json \
	--pytorch_dump_output <span class="hljs-variable">$T5</span>/pytorch_model.bin<!-- 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/it/converting_tensorflow_models.md" 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_728xau = {
	assets: "/docs/transformers/pr_33913/it",
	base: "/docs/transformers/pr_33913/it",
	env: {}
	};

	const element = document.currentScript.parentElement;

	const data = [null,null];

	Promise.all([
	import("/docs/transformers/pr_33913/it/_app/immutable/entry/start.cef8f86b.js"),
	import("/docs/transformers/pr_33913/it/_app/immutable/entry/app.d399d34f.js")
	]).then(([kit, app]) => {
	kit.start(app, element, {
	node_ids: [0, 8],
	data,
	form: null,
	error: null
	});
	});
	}
	</script>

Xet Storage Details

Size:: 29.6 kB
Xet hash:: 346ff1c942e8e1c1107725af09059c923246b7f498369f049d5a5be0d501e64f

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