Buckets:
| <meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Video-text-to-text","local":"video-text-to-text","sections":[],"depth":1}"> | |
| <link href="/docs/transformers/pr_43265/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_43265/en/_app/immutable/entry/start.1dae3980.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_43265/en/_app/immutable/chunks/scheduler.31fdf58d.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_43265/en/_app/immutable/chunks/singletons.5fcb8d34.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_43265/en/_app/immutable/chunks/index.252883d5.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_43265/en/_app/immutable/chunks/paths.e648cef5.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_43265/en/_app/immutable/entry/app.66dba7a3.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_43265/en/_app/immutable/chunks/preload-helper.5b8be175.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_43265/en/_app/immutable/chunks/index.2f76fdf0.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_43265/en/_app/immutable/nodes/0.4837e553.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_43265/en/_app/immutable/chunks/each.e59479a4.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_43265/en/_app/immutable/nodes/701.e3f79f0d.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_43265/en/_app/immutable/chunks/CopyLLMTxtMenu.53b607bf.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_43265/en/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.08750ec0.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_43265/en/_app/immutable/chunks/IconCopy.ac192424.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_43265/en/_app/immutable/chunks/CodeBlock.e52df5d6.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_43265/en/_app/immutable/chunks/DocNotebookDropdown.dd28433e.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"Video-text-to-text","local":"video-text-to-text","sections":[],"depth":1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <div class="items-center shrink-0 min-w-[100px] max-sm:min-w-[50px] justify-end ml-auto flex" style="float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"><div class="inline-flex rounded-md max-sm:rounded-sm"><button class="inline-flex items-center gap-1 h-7 max-sm:h-7 px-2 max-sm:px-1.5 text-sm font-medium text-gray-800 border border-r-0 rounded-l-md max-sm:rounded-l-sm border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-live="polite"><span class="inline-flex items-center justify-center rounded-md p-0.5 max-sm:p-0 hover:text-gray-800 dark:hover:text-gray-200"><svg class="sm:size-3.5 size-3" 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></span> <span>Copy page</span></button> <button class="inline-flex items-center justify-center w-6 max-sm:w-5 h-7 max-sm:h-7 disabled:pointer-events-none text-sm text-gray-500 hover:text-gray-700 dark:hover:text-white rounded-r-md max-sm:rounded-r-sm border border-l transition border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-haspopup="menu" aria-expanded="false" aria-label="Open copy menu"><svg class="transition-transform text-gray-400 overflow-visible sm:size-3.5 size-3 rotate-0" width="1em" height="1em" viewBox="0 0 12 7" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M1 1L6 6L11 1" stroke="currentColor"></path></svg></button></div> </div> <div class="flex space-x-1 " style="float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"> <div class="relative colab-dropdown "> <button class=" " type="button"> <img alt="Open In Colab" class="!m-0" src="https://colab.research.google.com/assets/colab-badge.svg"> </button> </div> <div class="relative colab-dropdown "> <button class=" " type="button"> <img alt="Open In Studio Lab" class="!m-0" src="https://studiolab.sagemaker.aws/studiolab.svg"> </button> </div></div> <h1 class="relative group"><a id="video-text-to-text" 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="#video-text-to-text"><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>Video-text-to-text</span></h1> <p data-svelte-h="svelte-1cn10kz">Video-text-to-text, also known as video language models are models that can process video and output text. These models can tackle various tasks, from video question answering to video captioning.</p> <p data-svelte-h="svelte-1s32ql5">These models have nearly the same architecture as <a href="../image_text_to_text">image-text-to-text</a> models except for some changes to accept video data, since video data is essentially image frames with temporal dependencies. Some image-text-to-text models take in multiple images, but this alone is inadequate for a model to accept videos.</p> <p data-svelte-h="svelte-1t09of">Moreover, video-text-to-text models are often trained with all vision modalities. Each example might have videos, multiple videos, images and multiple images. Some of these models can also take interleaved inputs. For example, you can refer to a specific video inside a string of text by adding a video token in text like “What is happening in this video? <code><video></code>“.</p> <p data-svelte-h="svelte-bxhj57">Note that these models process videos with no audio. <a href="../any-to-any">Any-to-any</a> models on the other hand can process videos with audio in them.</p> <p data-svelte-h="svelte-srvvgy">In this guide, we provide a brief overview of video LMs and show how to use them with Transformers for inference.</p> <p data-svelte-h="svelte-jc4sjd">To begin with, there are multiple types of video LMs:</p> <ul data-svelte-h="svelte-1vpzkb0"><li>base models used for fine-tuning</li> <li>chat fine-tuned models for conversation</li> <li>instruction fine-tuned models</li></ul> <p data-svelte-h="svelte-mjsdh5">This guide focuses on inference with an instruction-tuned model, <a href="https://huggingface.co/llava-hf/llava-interleave-qwen-7b-hf" rel="nofollow">llava-hf/llava-onevision-qwen2-0.5b-ov-hf</a> which can take in interleaved data. Alternatively, you can try <a href="https://huggingface.co/llava-hf/llava-interleave-qwen-0.5b-hf" rel="nofollow">llava-interleave-qwen-0.5b-hf</a> if your hardware doesn’t allow running a 7B model.</p> <p data-svelte-h="svelte-5jp6fp">Let’s begin installing the dependencies.</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="language-bash "><!-- HTML_TAG_START -->pip install -q transformers accelerate flash_attn torchcodec<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1rw69r9">Let’s initialize the model and the processor.</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="language-python "><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoProcessor, LlavaOnevisionForConditionalGeneration | |
| <span class="hljs-keyword">import</span> torch | |
| model_id = <span class="hljs-string">"llava-hf/llava-onevision-qwen2-0.5b-ov-hf"</span> | |
| processor = AutoProcessor.from_pretrained(model_id, device=<span class="hljs-string">"cuda"</span>) | |
| model = LlavaForConditionalGeneration.from_pretrained(model_id, device_map=<span class="hljs-string">"auto"</span>, dtype=torch.float16)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-d2bxfg">We will infer with two videos, both have cats.</p> <div class="container" data-svelte-h="svelte-1a6pc9g"><div class="video-container"><video width="400" controls=""><source src="https://huggingface.co/spaces/merve/llava-interleave/resolve/main/cats_1.mp4" type="video/mp4"></video></div></div> <div class="video-container" data-svelte-h="svelte-1jly6uy"><video width="400" controls=""><source src="https://huggingface.co/spaces/merve/llava-interleave/resolve/main/cats_2.mp4" type="video/mp4"></video></div> <p data-svelte-h="svelte-als0jy">Videos are series of image frames. Depending on the hardware limitations, downsampling is required. If the number of downsampled frames are too little, predictions will be low quality.</p> <p data-svelte-h="svelte-9bhunv">Video-text-to-text models have processors with video processor abstracted in them. You can pass video inference related arguments to <a href="/docs/transformers/pr_43265/en/main_classes/processors#transformers.ProcessorMixin.apply_chat_template">apply_chat_template()</a> function.</p> <blockquote class="warning" data-svelte-h="svelte-106gruq"><p>You can learn more about video processors <a href="../main_classes/video_processor">here</a>.</p></blockquote> <p data-svelte-h="svelte-1om0w4c">We can define our chat history, passing in video with a URL like below.</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="language-python "><!-- HTML_TAG_START -->messages = [ | |
| { | |
| <span class="hljs-string">"role"</span>: <span class="hljs-string">"user"</span>, | |
| <span class="hljs-string">"content"</span>: [ | |
| {<span class="hljs-string">"type"</span>: <span class="hljs-string">"video"</span>, <span class="hljs-string">"video"</span>: <span class="hljs-string">"https://huggingface.co/spaces/merve/llava-interleave/resolve/main/cats_1.mp4"</span>}, | |
| {<span class="hljs-string">"type"</span>: <span class="hljs-string">"text"</span>, <span class="hljs-string">"text"</span>: <span class="hljs-string">"Describe what is happening in this video."</span>}, | |
| ], | |
| } | |
| ]<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1emgnyc">You can preprocess the videos by passing in messages, setting <code>do_sample_frames</code> to True and passing in <code>num_frames</code>. Here we sample 10 frames.</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="language-python "><!-- HTML_TAG_START -->inputs = processor.apply_chat_template( | |
| messages, | |
| tokenize=<span class="hljs-literal">True</span>, | |
| add_generation_prompt=<span class="hljs-literal">True</span>, | |
| return_dict=<span class="hljs-literal">True</span>, | |
| return_tensors=<span class="hljs-string">"pt"</span>, | |
| num_frames=<span class="hljs-number">10</span>, | |
| do_sample_frames=<span class="hljs-literal">True</span> | |
| ) | |
| inputs.to(model.device)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-juasfz">The inputs contain <code>input_ids</code> for tokenized text, <code>pixel_values_videos</code> for 10 frames and <code>attention_mask</code> for which tokens .</p> <p data-svelte-h="svelte-1gsqerf">We can now infer with our preprocessed inputs and decode them.</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="language-python "><!-- HTML_TAG_START -->generated_ids = model.generate(**inputs, max_new_tokens=<span class="hljs-number">128</span>) | |
| input_length = <span class="hljs-built_in">len</span>(inputs[<span class="hljs-string">"input_ids"</span>][<span class="hljs-number">0</span>]) | |
| output_text = processor.batch_decode( | |
| generated_ids[:, input_length:], skip_special_tokens=<span class="hljs-literal">True</span>, clean_up_tokenization_spaces=<span class="hljs-literal">False</span> | |
| ) | |
| output_text = processor.batch_decode( | |
| generated_ids, skip_special_tokens=<span class="hljs-literal">True</span>, clean_up_tokenization_spaces=<span class="hljs-literal">False</span> | |
| ) | |
| <span class="hljs-built_in">print</span>(output_text[<span class="hljs-number">0</span>]) | |
| <span class="hljs-comment">#"The video features a fluffy, long-haired cat with a mix of brown and white fur, lying on a beige carpeted floor. The cat's eyes are wide open, and its whiskers are prominently visible. The cat appears to be in a relaxed state, with its head slightly"</span><!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-gm0e9f">You can also interleave multiple videos with text directly in chat template like below.</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="language-python "><!-- HTML_TAG_START -->messages = [ | |
| { | |
| <span class="hljs-string">"role"</span>: <span class="hljs-string">"user"</span>, | |
| <span class="hljs-string">"content"</span>: [ | |
| {<span class="hljs-string">"type"</span>: <span class="hljs-string">"text"</span>, <span class="hljs-string">"text"</span>: <span class="hljs-string">"Here's a video."</span>}, | |
| {<span class="hljs-string">"type"</span>: <span class="hljs-string">"video"</span>, <span class="hljs-string">"video"</span>: <span class="hljs-string">"https://huggingface.co/spaces/merve/llava-interleave/resolve/main/cats_1.mp4"</span>}, | |
| {<span class="hljs-string">"type"</span>: <span class="hljs-string">"text"</span>, <span class="hljs-string">"text"</span>: <span class="hljs-string">"Here's another video."</span>}, | |
| {<span class="hljs-string">"type"</span>: <span class="hljs-string">"video"</span>, <span class="hljs-string">"video"</span>: <span class="hljs-string">"https://huggingface.co/spaces/merve/llava-interleave/resolve/main/cats_2.mp4"</span>}, | |
| {<span class="hljs-string">"type"</span>: <span class="hljs-string">"text"</span>, <span class="hljs-string">"text"</span>: <span class="hljs-string">"Describe similarities in these videos."</span>}, | |
| ], | |
| } | |
| ]<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1futg4k">The inference remains the same as the previous example.</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="language-python "><!-- HTML_TAG_START -->inputs = processor.apply_chat_template( | |
| messages, | |
| tokenize=<span class="hljs-literal">True</span>, | |
| add_generation_prompt=<span class="hljs-literal">True</span>, | |
| return_dict=<span class="hljs-literal">True</span>, | |
| return_tensors=<span class="hljs-string">"pt"</span>, | |
| num_frames=<span class="hljs-number">100</span>, | |
| do_sample_frames=<span class="hljs-literal">True</span> | |
| ) | |
| inputs.to(model.device) | |
| generated_ids = model.generate(**inputs, max_new_tokens=<span class="hljs-number">50</span>) | |
| input_length = <span class="hljs-built_in">len</span>(inputs[<span class="hljs-string">"input_ids"</span>][<span class="hljs-number">0</span>]) | |
| output_text = processor.batch_decode( | |
| generated_ids[:, input_length:], skip_special_tokens=<span class="hljs-literal">True</span>, clean_up_tokenization_spaces=<span class="hljs-literal">False</span> | |
| ) | |
| <span class="hljs-built_in">print</span>(output_text) | |
| <span class="hljs-comment">#['Both videos feature a cat with a similar appearance, characterized by a fluffy white coat with black markings, a pink nose, and a pink tongue. The cat\'s eyes are wide open, and it appears to be in a state of alertness or excitement. ']</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/tasks/video_text_to_text.md" target="_blank"><svg class="mr-1" 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="M31,16l-7,7l-1.41-1.41L28.17,16l-5.58-5.59L24,9l7,7z"></path><path d="M1,16l7-7l1.41,1.41L3.83,16l5.58,5.59L8,23l-7-7z"></path><path d="M12.419,25.484L17.639,6.552l1.932,0.518L14.351,26.002z"></path></svg> <span data-svelte-h="svelte-zjs2n5"><span class="underline">Update</span> on GitHub</span></a> <p></p> | |
| <script> | |
| { | |
| __sveltekit_1gaarxw = { | |
| assets: "/docs/transformers/pr_43265/en", | |
| base: "/docs/transformers/pr_43265/en", | |
| env: {} | |
| }; | |
| const element = document.currentScript.parentElement; | |
| const data = [null,null]; | |
| Promise.all([ | |
| import("/docs/transformers/pr_43265/en/_app/immutable/entry/start.1dae3980.js"), | |
| import("/docs/transformers/pr_43265/en/_app/immutable/entry/app.66dba7a3.js") | |
| ]).then(([kit, app]) => { | |
| kit.start(app, element, { | |
| node_ids: [0, 701], | |
| data, | |
| form: null, | |
| error: null | |
| }); | |
| }); | |
| } | |
| </script> | |
Xet Storage Details
- Size:
- 26 kB
- Xet hash:
- ece7b333a7c609d9dbfb27276879f335b9d16f51c8fb668df3fa0d8cbf59c932
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.