{"id":4722,"date":"2024-04-18T22:49:14","date_gmt":"2024-04-18T22:49:14","guid":{"rendered":"https:\/\/game.intel.com\/?p=4722"},"modified":"2024-05-29T21:16:37","modified_gmt":"2024-05-29T21:16:37","slug":"wield-the-power-of-llms-on-intel-arc-gpus","status":"publish","type":"post","link":"https:\/\/game.intel.com\/br\/stories\/wield-the-power-of-llms-on-intel-arc-gpus\/","title":{"rendered":"Utilize o poder dos LLMs nas GPUs Intel\u00ae Arc"},"content":{"rendered":"<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<h3 class=\"wp-block-heading\">Execute facilmente uma variedade de LLMs localmente com as GPUs Intel\u00ae Arc<\/h3>\n<\/blockquote>\n\n\n\n<p>A IA generativa mudou o cen\u00e1rio do que \u00e9 poss\u00edvel na cria\u00e7\u00e3o de conte\u00fado. Essa tecnologia tem o potencial de fornecer imagens, v\u00eddeos e textos nunca antes imaginados. Os modelos de linguagem ampla (LLMs) t\u00eam sido manchetes na era da IA, permitindo que qualquer pessoa possa gerar letras de m\u00fasicas, obter respostas para perguntas complexas sobre f\u00edsica ou elaborar um esbo\u00e7o para uma apresenta\u00e7\u00e3o de slides. E esses recursos de IA n\u00e3o precisam mais estar conectados \u00e0 nuvem ou a servi\u00e7os de assinatura. Eles podem ser executados localmente no seu pr\u00f3prio PC, onde voc\u00ea tem controle total sobre o modelo para personalizar o resultado.<\/p>\n\n\n\n<p>Neste artigo, mostraremos como configurar e experimentar modelos de linguagem grandes (LLMs) populares em um PC com a placa de v\u00eddeo Intel\u00ae Arc\u2122 A770 de 16 GB. Embora este tutorial fa\u00e7a uso do LLM Mistral-7B-Instruct, essas mesmas etapas podem ser usadas com um LLM PyTorch de sua escolha, como Phi2, Llama2 etc. E sim, com o modelo mais recente do Llama3 tamb\u00e9m!<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">IPEX-LLM<\/h2>\n\n\n\n<p>A raz\u00e3o pela qual podemos executar uma variedade de modelos usando a mesma instala\u00e7\u00e3o b\u00e1sica \u00e9 gra\u00e7as a <a href=\"https:\/\/github.com\/intel-analytics\/ipex-llm\">IPEX-LLM<\/a>uma biblioteca LLM para PyTorch. Ela \u00e9 constru\u00edda sobre o <a href=\"https:\/\/github.com\/intel\/intel-extension-for-pytorch\">Extens\u00e3o Intel\u00ae para PyTorch<\/a> e cont\u00e9m otimiza\u00e7\u00f5es LLM de \u00faltima gera\u00e7\u00e3o e compacta\u00e7\u00e3o de pesos de bits baixos (INT4\/FP4\/INT8\/FP8) - com todas as otimiza\u00e7\u00f5es de desempenho mais recentes para o hardware Intel. O IPEX-LLM aproveita as vantagens do X<sup>e<\/sup>-Armazena a acelera\u00e7\u00e3o XMX AI em GPUs discretas da Intel, como as placas de v\u00eddeo Arc s\u00e9rie A, para melhorar o desempenho. Ele oferece suporte aos gr\u00e1ficos Intel Arc s\u00e9rie A no Subsistema Windows para Linux vers\u00e3o 2, ambientes Windows nativos e Linux nativo.<\/p>\n\n\n\n<p>E como tudo isso \u00e9 nativo do PyTorch, voc\u00ea pode trocar facilmente os modelos e os dados de entrada do PyTorch para execut\u00e1-los em uma GPU Intel Arc com acelera\u00e7\u00e3o de alto desempenho. Este experimento n\u00e3o teria sido completo sem uma compara\u00e7\u00e3o de desempenho. Usando as instru\u00e7\u00f5es abaixo para a Intel Arc e as instru\u00e7\u00f5es comumente dispon\u00edveis para a concorr\u00eancia, analisamos duas GPUs discretas posicionadas em um segmento de pre\u00e7o semelhante.<\/p>\n\n\n\n<figure data-wp-context=\"{&quot;imageId&quot;:&quot;69e146b3bb8ec&quot;}\" data-wp-interactive=\"core\/image\" data-wp-key=\"69e146b3bb8ec\" class=\"wp-block-image size-full wp-lightbox-container\"><img fetchpriority=\"high\" width=\"1280\" height=\"720\" data-wp-class--hide=\"state.isContentHidden\" data-wp-class--show=\"state.isContentVisible\" data-wp-init=\"callbacks.setButtonStyles\" data-wp-on--click=\"actions.showLightbox\" data-wp-on--load=\"callbacks.setButtonStyles\" data-wp-on-window--resize=\"callbacks.setButtonStyles\" src=\"https:\/\/game.intel.com\/wp-content\/uploads\/2024\/04\/LLM-Blog-041824-LLM-Execution-on-Arc-A770-2.png\" alt=\"\" class=\"wp-image-4782\"><button\n\t\t\tclass=\"lightbox-trigger\"\n\t\t\ttype=\"button\"\n\t\t\taria-haspopup=\"dialog\"\n\t\t\taria-label=\"Ampliar\"\n\t\t\tdata-wp-init=\"callbacks.initTriggerButton\"\n\t\t\tdata-wp-on--click=\"actions.showLightbox\"\n\t\t\tdata-wp-style--right=\"state.imageButtonRight\"\n\t\t\tdata-wp-style--top=\"state.imageButtonTop\"\n\t\t>\n\t\t\t<svg xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"12\" height=\"12\" fill=\"none\" viewbox=\"0 0 12 12\">\n\t\t\t\t<path fill=\"#fff\" d=\"M2 0a2 2 0 0 0-2 2v2h1.5V2a.5.5 0 0 1 .5-.5h2V0H2Zm2 10.5H2a.5.5 0 0 1-.5-.5V8H0v2a2 2 0 0 0 2 2h2v-1.5ZM8 12v-1.5h2a.5.5 0 0 0 .5-.5V8H12v2a2 2 0 0 1-2 2H8Zm2-12a2 2 0 0 1 2 2v2h-1.5V2a.5.5 0 0 0-.5-.5H8V0h2Z\" \/>\n\t\t\t<\/svg>\n\t\t<\/button><\/figure>\n\n\n\n<p>Por exemplo, ao executar o modelo Mistral 7B com a biblioteca IPEX-LLM, a placa de v\u00eddeo Arc A770 16GB pode processar 70 tokens por segundo (TPS), ou 70% mais TPS do que a GeForce RTX 4060 8GB usando CUDA. O que isso significa? Uma regra geral \u00e9 que 1 token \u00e9 equivalente a 0,75 de uma palavra e uma boa compara\u00e7\u00e3o \u00e9 o <a href=\"https:\/\/wordsrated.com\/speed-reading-statistics\/\">velocidade m\u00e9dia de leitura humana de 4 palavras por segundo<\/a> ou 5,3 TPS. A placa de v\u00eddeo Arc A770 16GB pode gerar palavras muito mais rapidamente do que uma pessoa comum pode l\u00ea-las!<\/p>\n\n\n\n<p>Nossos testes internos mostram que a placa de v\u00eddeo Arc A770 de 16 GB pode oferecer esse recurso e um desempenho competitivo ou l\u00edder em uma ampla gama de modelos em compara\u00e7\u00e3o com a RTX 4060, o que torna a placa de v\u00eddeo Intel Arc uma \u00f3tima op\u00e7\u00e3o para a execu\u00e7\u00e3o LLM local.<\/p>\n\n\n\n<p>Agora vamos \u00e0s instru\u00e7\u00f5es de configura\u00e7\u00e3o para que voc\u00ea comece a usar LLMs na GPU Arc s\u00e9rie A.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">Instru\u00e7\u00f5es de instala\u00e7\u00e3o<\/h2>\n\n\n\n<p>Tamb\u00e9m podemos consultar esta p\u00e1gina para configurar o ambiente: <a href=\"https:\/\/ipex-llm.readthedocs.io\/en\/latest\/doc\/LLM\/Quickstart\/install_windows_gpu.html\">Instala\u00e7\u00e3o do IPEX-LLM no Windows com GPU Intel - Documenta\u00e7\u00e3o mais recente do IPEX-LLM<\/a><\/p>\n\n\n\n<p>1. Desative a GPU integrada no gerenciador de dispositivos.<\/p>\n\n\n\n<p>2. Fa\u00e7a o download e instale <a href=\"https:\/\/www.anaconda.com\/download\">Anaconda<\/a>.<\/p>\n\n\n\n<p>3. Ap\u00f3s a conclus\u00e3o da instala\u00e7\u00e3o, abra o menu Iniciar, procure o Anaconda Prompt, execute-o como administrador e crie um ambiente virtual usando os seguintes comandos. Digite cada comando separadamente:<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>conda create -n llm python=3.10.6\n\nconda activate llm\n\nconda install libuv\n\npip install dpcpp-cpp-rt==2024.0.2 mkl-dpcpp==2024.0.0 onednn==2024.0.0 gradio\n\npip install --pre --upgrade ipex-llm[xpu] --extra-index-url https:\/\/pytorch-extension.intel.com\/release-whl\/stable\/xpu\/us\/\n\npip install transformers==4.38.0<\/code><\/pre>\n\n\n\n<p>4. Crie um documento de texto chamado demo.py e salve-o em C:\\Users\\Your_Username\\Documents ou no diret\u00f3rio de sua escolha.<\/p>\n\n\n\n<p>5. Abra o arquivo demo.py com seu editor favorito e copie o seguinte exemplo de c\u00f3digo para ele:<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>from transformers import AutoTokenizer\nfrom ipex_llm.transformers import AutoModelForCausalLM\nimportar torch\nimportar intel_extension_for_pytorch\n\ndevice = \"xpu\" # o dispositivo para carregar o modelo\n\nmodel_id = \"mistralai\/Mistral-7B-Instruct-v0.2\" # id do modelo huggingface\n\ntokenizer = AutoTokenizer.from_pretrained(model_id)\nmodel = AutoModelForCausalLM.from_pretrained(model_id, load_in_4bit=True, torch_dtype=torch.float16)\nmodel = model.to(device)\n\nmensagens = [\n    {\"role\": \"user\", \"content\": \"Qual \u00e9 o seu condimento favorito?\"},\n    {\"role\": \"assistant\" (assistente), \"content\" (conte\u00fado): \"Bem, eu gosto bastante de um bom suco de lim\u00e3o fresco. Ele acrescenta a quantidade certa de sabor picante ao que quer que eu esteja preparando na cozinha!\"},\n    {\"role\": \"user\" (usu\u00e1rio), \"content\" (conte\u00fado): \"Do you have mayonnaise recipes?\"}\n]\n\nencodeds = tokenizer.apply_chat_template(messages, return_tensors=\"pt\")\n\nmodel_inputs = encodeds.to(device)\nmodel.to(dispositivo)\n\ngenerated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)\ndecodificado = tokenizer.batch_decode(generated_ids)\nprint(decoded[0])<\/code><\/pre>\n\n\n\n<p class=\"has-small-font-size\"><em>C\u00f3digo criado a partir do c\u00f3digo de amostra <a href=\"https:\/\/huggingface.co\/mistralai\/Mistral-7B-Instruct-v0.2\">neste reposit\u00f3rio<\/a>.<\/em><\/p>\n\n\n\n<p>6. Salve o arquivo demo.py. No Anaconda, navegue at\u00e9 o diret\u00f3rio em que o demo.py est\u00e1 localizado usando o comando cd e execute o seguinte comando no prompt do Anaconda:<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>python demo.py<\/code><\/pre>\n\n\n\n<p>Agora voc\u00ea pode obter uma boa receita para fazer maionese!<\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><img fetchpriority=\"high\" width=\"1024\" height=\"213\" src=\"https:\/\/game.intel.com\/wp-content\/uploads\/2024\/04\/LLM-Blog-041824-mayo-recipe-1024x213.png\" alt=\"\" class=\"wp-image-4746\"><\/figure>\n\n\n\n<h2 class=\"wp-block-heading\">Mudan\u00e7a de modelos<\/h2>\n\n\n\n<p>Usando o mesmo ambiente que configuramos acima, voc\u00ea pode experimentar outros modelos populares no Hugging Face, como llama2-7B-chat-hf, llama3-8B-it, phi-2, gemma-7B-i e stablelm2, substituindo o ID do modelo Hugging Face acima no demo.py.<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>model_id = \"mistralai\/Mistral-7B-Instruct-v0.2\" ID do modelo huggingface #\n\npara\n\nmodel_id = \"stabilityai\/stablelm-2-zephyr-1_6b\" # id do modelo huggingface<\/code><\/pre>\n\n\n\n<p>Modelos diferentes podem exigir uma vers\u00e3o diferente do pacote de transformadores. Se voc\u00ea encontrar erros ao iniciar o demo.py, siga as etapas abaixo para fazer upgrade\/downgrade dos transformadores:<\/p>\n\n\n\n<ol class=\"wp-block-list\">\n<li>Abrir o prompt do Anaconda<\/li>\n\n\n\n<li>conda activate llm<\/li>\n\n\n\n<li>pip install transformers==4.37.0<\/li>\n<\/ol>\n\n\n\n<p><strong>Vers\u00f5es verificadas dos transformadores:<\/strong><\/p>\n\n\n\n<figure class=\"wp-block-table is-style-regular\"><table class=\"has-fixed-layout\"><thead><tr><th class=\"has-text-align-center\" data-align=\"center\">ID do modelo<\/th><th class=\"has-text-align-center\" data-align=\"center\">Vers\u00f5es do pacote de transformadores<\/th><\/tr><\/thead><tbody><tr><td class=\"has-text-align-center\" data-align=\"center\">meta-llama\/Llama-2-7b-chat-hf<\/td><td class=\"has-text-align-center\" data-align=\"center\">4.37.0<\/td><\/tr><tr><td class=\"has-text-align-center\" data-align=\"center\">meta-llama\/Meta-Llama-3-8B-Instruct<\/td><td class=\"has-text-align-center\" data-align=\"center\">4.37.0<\/td><\/tr><tr><td class=\"has-text-align-center\" data-align=\"center\">stabilityai\/stablelm-2-zephyr-1_6b<\/td><td class=\"has-text-align-center\" data-align=\"center\">4.38.0<\/td><\/tr><tr><td class=\"has-text-align-center\" data-align=\"center\">mistralai\/Mistral-7B-Instruct-v0.2<\/td><td class=\"has-text-align-center\" data-align=\"center\">4.38.0<\/td><\/tr><tr><td class=\"has-text-align-center\" data-align=\"center\">microsoft\/phi-2<\/td><td class=\"has-text-align-center\" data-align=\"center\">4.38.0<\/td><\/tr><tr><td class=\"has-text-align-center\" data-align=\"center\">google\/gemma-7b-it<\/td><td class=\"has-text-align-center\" data-align=\"center\">4.38.1<\/td><\/tr><tr><td class=\"has-text-align-center\" data-align=\"center\">THUDM\/chatglm3-6b<\/td><td class=\"has-text-align-center\" data-align=\"center\">4.38.0<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n<p>Os requisitos de mem\u00f3ria podem variar de acordo com o modelo e a estrutura. Para o Intel Arc A750 8GB em execu\u00e7\u00e3o com o IPEX-LLM, recomendamos o uso do Llama-2-7B-chat-hf, Mistral-7B-Instruct-v0.2, phi-2 ou chatglm3-6B.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">Implementa\u00e7\u00e3o de uma WebUI do ChatBot<\/h2>\n\n\n\n<p>Agora, vamos implementar um webui do chatbot do Gradio para obter uma experi\u00eancia melhor usando seu navegador da Web. Para obter mais informa\u00e7\u00f5es sobre a implementa\u00e7\u00e3o de um chatbot interativo com LLMs, visite <a href=\"https:\/\/www.gradio.app\/guides\/creating-a-chatbot-fast\">https:\/\/www.gradio.app\/guides\/creating-a-chatbot-fast<\/a><\/p>\n\n\n\n<p>1. Crie um documento chamado chatbot_gradio.py no editor de texto de sua prefer\u00eancia.<\/p>\n\n\n\n<p>2. Copie e cole o seguinte trecho de c\u00f3digo no chatbot_gradio.py:<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>importar gradio como gr\nimportar torch\nimport intel_extension_for_pytorch\nfrom ipex_llm.transformers import AutoModelForCausalLM\nfrom transformers import AutoTokenizer, StoppingCriteria, StoppingCriteriaList, TextIteratorStreamer\nfrom threading import Thread\n\nmodel_id = \"mistralai\/Mistral-7B-Instruct-v0.2\"\n\ntokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)\nmodel = AutoModelForCausalLM.from_pretrained(model_id, trust_remote_code=True, optimize_model=True, load_in_4bit=True, torch_dtype=torch.float16)\nmodel = model.half()\nmodel = model.to(\"xpu\")\nclass StopOnTokens(StoppingCriteria):\n    def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor, **kwargs) -&gt; bool:\n        stop_ids = [29, 0]\n        para stop_id em stop_ids:\n            if input_ids[0][-1] == stop_id:\n                return True\n        return False\n\ndef predict(message, history):\n    stop = StopOnTokens()\n    history_format = []\n    for human, assistant in history:\n        history_format.append({\"role\": \"user\", \"content\": human })\n        history_format.append({\"role\": \"assistant\", \"content\":assistant})\n    history_format.append({\"role\": \"user\", \"content\": message})\n\n    prompt = tokenizer.apply_chat_template(history_format, tokenize=False, add_generation_prompt=True)\n    model_inputs = tokenizer(prompt, return_tensors=\"pt\").to(\"xpu\")\n    streamer = TextIteratorStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)\n    generate_kwargs = dict(\n        model_inputs,\n        streamer=streamer,\n        max_new_tokens=300,\n        do_sample=True,\n        top_p=0,95,\n        top_k=20,\n        temperature=0.8,\n        num_beams=1,\n        pad_token_id=tokenizer.eos_token_id,\n        stopping_criteria=StoppingCriteriaList([stop])\n        )\n    t = Thread(target=model.generate, kwargs=generate_kwargs)\n    t.start()\n\n    partial_message = \"\"\n    for new_token in streamer:\n        if new_token != '&lt;&#039;:\n            partial_message += new_token\n            yield partial_message\n\ngr.ChatInterface(predict).launch()<\/code><\/pre>\n\n\n\n<p>3. Abra um novo prompt do anaconda e digite os seguintes comandos:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>pip install gradio<\/li>\n\n\n\n<li>conda activate llm<\/li>\n\n\n\n<li>cd para o diret\u00f3rio em que o chat_gradio.py est\u00e1 localizado<\/li>\n\n\n\n<li>python chatbot_gradio.py<\/li>\n<\/ul>\n\n\n\n<p>4. Abra seu navegador da Web e navegue at\u00e9 127.0.0.1:7860. Voc\u00ea ver\u00e1 um chatbot configurado com o modelo de linguagem mistral-7b-instruct-v0.2! Agora voc\u00ea tem um webui de apar\u00eancia sofisticada para o seu chatbot.<\/p>\n\n\n\n<p>5. Fa\u00e7a uma pergunta para iniciar uma conversa com seu chatbot.<\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" width=\"1469\" height=\"874\" src=\"https:\/\/game.intel.com\/wp-content\/uploads\/2024\/04\/LLM-Blog-041824-chatbot-Q-and-A.png\" alt=\"\" class=\"wp-image-4745\"><\/figure>\n\n\n\n<p><\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity is-style-wide\"\/>\n\n\n\n<p><\/p>\n\n\n\n<h3 class=\"wp-block-heading\">Avisos e isen\u00e7\u00f5es de responsabilidade<\/h3>\n\n\n\n<div class=\"wp-block-group is-layout-constrained wp-block-group-is-layout-constrained\">\n<p>O desempenho varia de acordo com o uso, a configura\u00e7\u00e3o e outros fatores. Saiba mais sobre o <a href=\"https:\/\/edc.intel.com\/content\/www\/us\/en\/products\/performance\/benchmarks\/overview\/\">Site do \u00cdndice de Desempenho<\/a>.<\/p>\n\n\n\n<p>Os resultados de desempenho s\u00e3o baseados em testes realizados nas datas mostradas nas configura\u00e7\u00f5es e podem n\u00e3o refletir todas as atualiza\u00e7\u00f5es dispon\u00edveis publicamente. Consulte o backup para obter detalhes da configura\u00e7\u00e3o. Nenhum produto ou componente pode ser absolutamente seguro.<\/p>\n\n\n\n<p>Os resultados que se baseiam em sistemas e componentes de pr\u00e9-produ\u00e7\u00e3o, bem como os resultados que foram estimados ou simulados usando uma Plataforma de Refer\u00eancia Intel (um exemplo interno de novo sistema), an\u00e1lise interna da Intel ou simula\u00e7\u00e3o ou modelagem de arquitetura s\u00e3o fornecidos apenas para fins informativos. Os resultados podem variar com base em altera\u00e7\u00f5es futuras em quaisquer sistemas, componentes, especifica\u00e7\u00f5es ou configura\u00e7\u00f5es.<\/p>\n\n\n\n<p>Seus custos e resultados podem variar.<\/p>\n\n\n\n<p>As tecnologias Intel podem exigir a ativa\u00e7\u00e3o de hardware, software ou servi\u00e7o.<\/p>\n\n\n\n<p>\u00a9 Intel Corporation. Intel, o logotipo da Intel, Arc e outras marcas da Intel s\u00e3o marcas registradas da Intel Corporation ou de suas subsidi\u00e1rias.<\/p>\n\n\n\n<p>*Outros nomes e marcas podem ser reivindicados como propriedade de terceiros.<\/p>\n<\/div>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" width=\"1280\" height=\"720\" src=\"https:\/\/game.intel.com\/wp-content\/uploads\/2024\/04\/LLM-Blog-041824-System-Configuration-and-Workloads.png\" alt=\"\" class=\"wp-image-4739\" style=\"object-fit:cover\"><\/figure>","protected":false},"excerpt":{"rendered":"<p>Generative AI has changed the landscape of what\u2019s possible in content creation. This technology has the potential to deliver previously unimagined images, videos and writing. Learn how to set up and experiment with popular large language models (LLMs) from the AI community Huggingface on a PC with the Intel\u00ae Arc\u2122 A770 16GB graphics card. <\/p>","protected":false},"author":27,"featured_media":4738,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"inline_featured_image":false,"footnotes":""},"categories":[6],"tags":[45,48,49,14,47],"class_list":["post-4722","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-intel-arc","tag-ai","tag-generative-ai","tag-huggingface","tag-intel-arc-graphics","tag-llms"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v26.8 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Wield The Power of LLMs On Intel\u00ae Arc\u2122 GPUs | Intel Gaming Access<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/game.intel.com\/br\/stories\/wield-the-power-of-llms-on-intel-arc-gpus\/\" \/>\n<meta property=\"og:locale\" content=\"pt_BR\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Wield The Power of LLMs On Intel\u00ae Arc\u2122 GPUs | Intel Gaming Access\" \/>\n<meta property=\"og:description\" content=\"Generative AI has changed the landscape of what\u2019s possible in content creation. This technology has the potential to deliver previously unimagined images, videos and writing. Learn how to set up and experiment with popular large language models (LLMs) from the AI community Huggingface on a PC with the Intel\u00ae Arc\u2122 A770 16GB graphics card.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/game.intel.com\/br\/stories\/wield-the-power-of-llms-on-intel-arc-gpus\/\" \/>\n<meta property=\"og:site_name\" content=\"Intel Gaming Access\" \/>\n<meta property=\"article:published_time\" content=\"2024-04-18T22:49:14+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-05-29T21:16:37+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/game.intel.com\/wp-content\/uploads\/2024\/04\/LLM-Blog-041824-llmA770-header.png\" \/>\n\t<meta property=\"og:image:width\" content=\"1280\" \/>\n\t<meta property=\"og:image:height\" content=\"768\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"author\" content=\"Intel Gaming\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@IntelGaming\" \/>\n<meta name=\"twitter:site\" content=\"@IntelGaming\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Intel Gaming\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"8 minutos\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/game.intel.com\/it\/stories\/wield-the-power-of-llms-on-intel-arc-gpus\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/game.intel.com\/it\/stories\/wield-the-power-of-llms-on-intel-arc-gpus\/\"},\"author\":{\"name\":\"Intel Gaming\",\"@id\":\"https:\/\/game.intel.com\/us\/#\/schema\/person\/5a9260725321b6f9dc6b73c2048fb49e\"},\"headline\":\"Wield The Power of LLMs On Intel\u00ae Arc\u2122 GPUs\",\"datePublished\":\"2024-04-18T22:49:14+00:00\",\"dateModified\":\"2024-05-29T21:16:37+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/game.intel.com\/it\/stories\/wield-the-power-of-llms-on-intel-arc-gpus\/\"},\"wordCount\":1075,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\/\/game.intel.com\/us\/#organization\"},\"image\":{\"@id\":\"https:\/\/game.intel.com\/it\/stories\/wield-the-power-of-llms-on-intel-arc-gpus\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/game.intel.com\/wp-content\/uploads\/2024\/04\/LLM-Blog-041824-llmA770-header.png\",\"keywords\":[\"AI\",\"Generative AI\",\"Huggingface\",\"intel arc graphics\",\"LLMs\"],\"articleSection\":[\"Intel\u00ae Arc\u2122 Graphics\"],\"inLanguage\":\"pt-BR\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\/\/game.intel.com\/it\/stories\/wield-the-power-of-llms-on-intel-arc-gpus\/#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/game.intel.com\/it\/stories\/wield-the-power-of-llms-on-intel-arc-gpus\/\",\"url\":\"https:\/\/game.intel.com\/it\/stories\/wield-the-power-of-llms-on-intel-arc-gpus\/\",\"name\":\"Wield The Power of LLMs On Intel\u00ae Arc\u2122 GPUs | Intel Gaming Access\",\"isPartOf\":{\"@id\":\"https:\/\/game.intel.com\/us\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/game.intel.com\/it\/stories\/wield-the-power-of-llms-on-intel-arc-gpus\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/game.intel.com\/it\/stories\/wield-the-power-of-llms-on-intel-arc-gpus\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/game.intel.com\/wp-content\/uploads\/2024\/04\/LLM-Blog-041824-llmA770-header.png\",\"datePublished\":\"2024-04-18T22:49:14+00:00\",\"dateModified\":\"2024-05-29T21:16:37+00:00\",\"breadcrumb\":{\"@id\":\"https:\/\/game.intel.com\/it\/stories\/wield-the-power-of-llms-on-intel-arc-gpus\/#breadcrumb\"},\"inLanguage\":\"pt-BR\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/game.intel.com\/it\/stories\/wield-the-power-of-llms-on-intel-arc-gpus\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"pt-BR\",\"@id\":\"https:\/\/game.intel.com\/it\/stories\/wield-the-power-of-llms-on-intel-arc-gpus\/#primaryimage\",\"url\":\"https:\/\/game.intel.com\/wp-content\/uploads\/2024\/04\/LLM-Blog-041824-llmA770-header.png\",\"contentUrl\":\"https:\/\/game.intel.com\/wp-content\/uploads\/2024\/04\/LLM-Blog-041824-llmA770-header.png\",\"width\":1280,\"height\":768},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/game.intel.com\/it\/stories\/wield-the-power-of-llms-on-intel-arc-gpus\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/game.intel.com\/ar\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Wield The Power of LLMs On Intel\u00ae Arc\u2122 GPUs\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/game.intel.com\/us\/#website\",\"url\":\"https:\/\/game.intel.com\/us\/\",\"name\":\"Intel Gaming Access\",\"description\":\"Made to Game. Ready for Anything.\",\"publisher\":{\"@id\":\"https:\/\/game.intel.com\/us\/#organization\"},\"alternateName\":\"game.intel.com\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/game.intel.com\/us\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"pt-BR\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/game.intel.com\/us\/#organization\",\"name\":\"Intel Gaming Access\",\"url\":\"https:\/\/game.intel.com\/us\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"pt-BR\",\"@id\":\"https:\/\/game.intel.com\/us\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/game.intel.com\/wp-content\/uploads\/2026\/01\/square-logo.png\",\"contentUrl\":\"https:\/\/game.intel.com\/wp-content\/uploads\/2026\/01\/square-logo.png\",\"width\":800,\"height\":800,\"caption\":\"Intel Gaming Access\"},\"image\":{\"@id\":\"https:\/\/game.intel.com\/us\/#\/schema\/logo\/image\/\"},\"sameAs\":[\"https:\/\/x.com\/IntelGaming\",\"https:\/\/www.instagram.com\/intelgaming\/\",\"https:\/\/discord.gg\/intel\",\"https:\/\/www.youtube.com\/@intelgaming\"]},{\"@type\":\"Person\",\"@id\":\"https:\/\/game.intel.com\/us\/#\/schema\/person\/5a9260725321b6f9dc6b73c2048fb49e\",\"name\":\"Intel Gaming\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"pt-BR\",\"@id\":\"https:\/\/game.intel.com\/us\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/d0fc339c682b4163337309e3b6555e83e4859911e42cdd1109d7b1ddb454cbfb?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/d0fc339c682b4163337309e3b6555e83e4859911e42cdd1109d7b1ddb454cbfb?s=96&d=mm&r=g\",\"caption\":\"Intel Gaming\"},\"url\":\"https:\/\/game.intel.com\/br\/stories\/author\/caton-lai-intel\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Wield The Power of LLMs On Intel\u00ae Arc\u2122 GPUs | Intel Gaming Access","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/game.intel.com\/br\/stories\/wield-the-power-of-llms-on-intel-arc-gpus\/","og_locale":"pt_BR","og_type":"article","og_title":"Wield The Power of LLMs On Intel\u00ae Arc\u2122 GPUs | Intel Gaming Access","og_description":"Generative AI has changed the landscape of what\u2019s possible in content creation. This technology has the potential to deliver previously unimagined images, videos and writing. Learn how to set up and experiment with popular large language models (LLMs) from the AI community Huggingface on a PC with the Intel\u00ae Arc\u2122 A770 16GB graphics card.","og_url":"https:\/\/game.intel.com\/br\/stories\/wield-the-power-of-llms-on-intel-arc-gpus\/","og_site_name":"Intel Gaming Access","article_published_time":"2024-04-18T22:49:14+00:00","article_modified_time":"2024-05-29T21:16:37+00:00","og_image":[{"width":1280,"height":768,"url":"https:\/\/game.intel.com\/wp-content\/uploads\/2024\/04\/LLM-Blog-041824-llmA770-header.png","type":"image\/png"}],"author":"Intel Gaming","twitter_card":"summary_large_image","twitter_creator":"@IntelGaming","twitter_site":"@IntelGaming","twitter_misc":{"Written by":"Intel Gaming","Est. reading time":"8 minutos"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/game.intel.com\/it\/stories\/wield-the-power-of-llms-on-intel-arc-gpus\/#article","isPartOf":{"@id":"https:\/\/game.intel.com\/it\/stories\/wield-the-power-of-llms-on-intel-arc-gpus\/"},"author":{"name":"Intel Gaming","@id":"https:\/\/game.intel.com\/us\/#\/schema\/person\/5a9260725321b6f9dc6b73c2048fb49e"},"headline":"Wield The Power of LLMs On Intel\u00ae Arc\u2122 GPUs","datePublished":"2024-04-18T22:49:14+00:00","dateModified":"2024-05-29T21:16:37+00:00","mainEntityOfPage":{"@id":"https:\/\/game.intel.com\/it\/stories\/wield-the-power-of-llms-on-intel-arc-gpus\/"},"wordCount":1075,"commentCount":0,"publisher":{"@id":"https:\/\/game.intel.com\/us\/#organization"},"image":{"@id":"https:\/\/game.intel.com\/it\/stories\/wield-the-power-of-llms-on-intel-arc-gpus\/#primaryimage"},"thumbnailUrl":"https:\/\/game.intel.com\/wp-content\/uploads\/2024\/04\/LLM-Blog-041824-llmA770-header.png","keywords":["AI","Generative AI","Huggingface","intel arc graphics","LLMs"],"articleSection":["Intel\u00ae Arc\u2122 Graphics"],"inLanguage":"pt-BR","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/game.intel.com\/it\/stories\/wield-the-power-of-llms-on-intel-arc-gpus\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/game.intel.com\/it\/stories\/wield-the-power-of-llms-on-intel-arc-gpus\/","url":"https:\/\/game.intel.com\/it\/stories\/wield-the-power-of-llms-on-intel-arc-gpus\/","name":"Wield The Power of LLMs On Intel\u00ae Arc\u2122 GPUs | Intel Gaming Access","isPartOf":{"@id":"https:\/\/game.intel.com\/us\/#website"},"primaryImageOfPage":{"@id":"https:\/\/game.intel.com\/it\/stories\/wield-the-power-of-llms-on-intel-arc-gpus\/#primaryimage"},"image":{"@id":"https:\/\/game.intel.com\/it\/stories\/wield-the-power-of-llms-on-intel-arc-gpus\/#primaryimage"},"thumbnailUrl":"https:\/\/game.intel.com\/wp-content\/uploads\/2024\/04\/LLM-Blog-041824-llmA770-header.png","datePublished":"2024-04-18T22:49:14+00:00","dateModified":"2024-05-29T21:16:37+00:00","breadcrumb":{"@id":"https:\/\/game.intel.com\/it\/stories\/wield-the-power-of-llms-on-intel-arc-gpus\/#breadcrumb"},"inLanguage":"pt-BR","potentialAction":[{"@type":"ReadAction","target":["https:\/\/game.intel.com\/it\/stories\/wield-the-power-of-llms-on-intel-arc-gpus\/"]}]},{"@type":"ImageObject","inLanguage":"pt-BR","@id":"https:\/\/game.intel.com\/it\/stories\/wield-the-power-of-llms-on-intel-arc-gpus\/#primaryimage","url":"https:\/\/game.intel.com\/wp-content\/uploads\/2024\/04\/LLM-Blog-041824-llmA770-header.png","contentUrl":"https:\/\/game.intel.com\/wp-content\/uploads\/2024\/04\/LLM-Blog-041824-llmA770-header.png","width":1280,"height":768},{"@type":"BreadcrumbList","@id":"https:\/\/game.intel.com\/it\/stories\/wield-the-power-of-llms-on-intel-arc-gpus\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/game.intel.com\/ar\/"},{"@type":"ListItem","position":2,"name":"Wield The Power of LLMs On Intel\u00ae Arc\u2122 GPUs"}]},{"@type":"WebSite","@id":"https:\/\/game.intel.com\/us\/#website","url":"https:\/\/game.intel.com\/us\/","name":"Acesso para jogos Intel","description":"Made to Game. Ready for Anything.","publisher":{"@id":"https:\/\/game.intel.com\/us\/#organization"},"alternateName":"game.intel.com","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/game.intel.com\/us\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"pt-BR"},{"@type":"Organization","@id":"https:\/\/game.intel.com\/us\/#organization","name":"Acesso para jogos Intel","url":"https:\/\/game.intel.com\/us\/","logo":{"@type":"ImageObject","inLanguage":"pt-BR","@id":"https:\/\/game.intel.com\/us\/#\/schema\/logo\/image\/","url":"https:\/\/game.intel.com\/wp-content\/uploads\/2026\/01\/square-logo.png","contentUrl":"https:\/\/game.intel.com\/wp-content\/uploads\/2026\/01\/square-logo.png","width":800,"height":800,"caption":"Intel Gaming Access"},"image":{"@id":"https:\/\/game.intel.com\/us\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/x.com\/IntelGaming","https:\/\/www.instagram.com\/intelgaming\/","https:\/\/discord.gg\/intel","https:\/\/www.youtube.com\/@intelgaming"]},{"@type":"Person","@id":"https:\/\/game.intel.com\/us\/#\/schema\/person\/5a9260725321b6f9dc6b73c2048fb49e","name":"Intel Gaming","image":{"@type":"ImageObject","inLanguage":"pt-BR","@id":"https:\/\/game.intel.com\/us\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/d0fc339c682b4163337309e3b6555e83e4859911e42cdd1109d7b1ddb454cbfb?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/d0fc339c682b4163337309e3b6555e83e4859911e42cdd1109d7b1ddb454cbfb?s=96&d=mm&r=g","caption":"Intel Gaming"},"url":"https:\/\/game.intel.com\/br\/stories\/author\/caton-lai-intel\/"}]}},"_links":{"self":[{"href":"https:\/\/game.intel.com\/br\/wp-json\/wp\/v2\/posts\/4722","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/game.intel.com\/br\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/game.intel.com\/br\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/game.intel.com\/br\/wp-json\/wp\/v2\/users\/27"}],"replies":[{"embeddable":true,"href":"https:\/\/game.intel.com\/br\/wp-json\/wp\/v2\/comments?post=4722"}],"version-history":[{"count":0,"href":"https:\/\/game.intel.com\/br\/wp-json\/wp\/v2\/posts\/4722\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/game.intel.com\/br\/wp-json\/wp\/v2\/media\/4738"}],"wp:attachment":[{"href":"https:\/\/game.intel.com\/br\/wp-json\/wp\/v2\/media?parent=4722"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/game.intel.com\/br\/wp-json\/wp\/v2\/categories?post=4722"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/game.intel.com\/br\/wp-json\/wp\/v2\/tags?post=4722"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}