Buckets:

hf-doc-build
/

doc-dev

Files

xet

hf-doc-build/doc-dev / trl /pr_5607 /en /community_tutorials.html

HuggingFaceDocBuilder

22 days ago

download

raw

31 kB

	<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Community Tutorials","local":"community-tutorials","sections":[{"title":"Language Models","local":"language-models","sections":[{"title":"Tutorials","local":"tutorials","sections":[],"depth":3},{"title":"Videos","local":"videos","sections":[],"depth":3}],"depth":2},{"title":"Vision Language Models","local":"vision-language-models","sections":[{"title":"Tutorials","local":"tutorials","sections":[],"depth":3}],"depth":2},{"title":"Speech Language Models","local":"speech-language-models","sections":[{"title":"Tutorials","local":"tutorials","sections":[],"depth":3}],"depth":2},{"title":"Contributing","local":"contributing","sections":[],"depth":2}],"depth":1}">
	<link href="/docs/trl/pr_5607/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
	<link rel="modulepreload" href="/docs/trl/pr_5607/en/_app/immutable/entry/start.151d81bd.js">
	<link rel="modulepreload" href="/docs/trl/pr_5607/en/_app/immutable/chunks/scheduler.7b731bd4.js">
	<link rel="modulepreload" href="/docs/trl/pr_5607/en/_app/immutable/chunks/singletons.2cf51804.js">
	<link rel="modulepreload" href="/docs/trl/pr_5607/en/_app/immutable/chunks/index.ac28c20f.js">
	<link rel="modulepreload" href="/docs/trl/pr_5607/en/_app/immutable/chunks/paths.ba01f37d.js">
	<link rel="modulepreload" href="/docs/trl/pr_5607/en/_app/immutable/entry/app.3d9a91c0.js">
	<link rel="modulepreload" href="/docs/trl/pr_5607/en/_app/immutable/chunks/preload-helper.e1689b3a.js">
	<link rel="modulepreload" href="/docs/trl/pr_5607/en/_app/immutable/chunks/index.cc268345.js">
	<link rel="modulepreload" href="/docs/trl/pr_5607/en/_app/immutable/nodes/0.cd288160.js">
	<link rel="modulepreload" href="/docs/trl/pr_5607/en/_app/immutable/chunks/each.e59479a4.js">
	<link rel="modulepreload" href="/docs/trl/pr_5607/en/_app/immutable/nodes/8.70effca0.js">
	<link rel="modulepreload" href="/docs/trl/pr_5607/en/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.f0d99f98.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"Community Tutorials","local":"community-tutorials","sections":[{"title":"Language Models","local":"language-models","sections":[{"title":"Tutorials","local":"tutorials","sections":[],"depth":3},{"title":"Videos","local":"videos","sections":[],"depth":3}],"depth":2},{"title":"Vision Language Models","local":"vision-language-models","sections":[{"title":"Tutorials","local":"tutorials","sections":[],"depth":3}],"depth":2},{"title":"Speech Language Models","local":"speech-language-models","sections":[{"title":"Tutorials","local":"tutorials","sections":[],"depth":3}],"depth":2},{"title":"Contributing","local":"contributing","sections":[],"depth":2}],"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> <h1 class="relative group"><a id="community-tutorials" 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="#community-tutorials"><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>Community Tutorials</span></h1> <p data-svelte-h="svelte-10f5vz4">Community tutorials are made by active members of the Hugging Face community who want to share their knowledge and expertise with others. They are a great way to learn about the library and its features, and to get started with core classes and modalities.</p> <h2 class="relative group"><a id="language-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="#language-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>Language Models</span></h2> <h3 class="relative group"><a id="tutorials" 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="#tutorials"><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>Tutorials</span></h3> <table data-svelte-h="svelte-636rw"><thead><tr><th>Task</th> <th>Class</th> <th>Description</th> <th>Author</th> <th>Tutorial</th> <th>Colab</th></tr></thead> <tbody><tr><td>Reinforcement Learning</td> <td><a href="/docs/trl/pr_5607/en/gspo_token#trl.GRPOTrainer">GRPOTrainer</a></td> <td>Efficient Online Training with GRPO and vLLM in TRL</td> <td><a href="https://huggingface.co/sergiopaniego" rel="nofollow">Sergio Paniego</a></td> <td><a href="https://huggingface.co/learn/cookbook/grpo_vllm_online_training" rel="nofollow">Link</a></td> <td><a href="https://colab.research.google.com/github/huggingface/cookbook/blob/main/notebooks/en/grpo_vllm_online_training.ipynb" rel="nofollow"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a></td></tr> <tr><td>Reinforcement Learning</td> <td><a href="/docs/trl/pr_5607/en/gspo_token#trl.GRPOTrainer">GRPOTrainer</a></td> <td>Post training an LLM for reasoning with GRPO in TRL</td> <td><a href="https://huggingface.co/sergiopaniego" rel="nofollow">Sergio Paniego</a></td> <td><a href="https://huggingface.co/learn/cookbook/fine_tuning_llm_grpo_trl" rel="nofollow">Link</a></td> <td><a href="https://colab.research.google.com/github/huggingface/cookbook/blob/main/notebooks/en/fine_tuning_llm_grpo_trl.ipynb" rel="nofollow"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a></td></tr> <tr><td>Reinforcement Learning</td> <td><a href="/docs/trl/pr_5607/en/gspo_token#trl.GRPOTrainer">GRPOTrainer</a></td> <td>Mini-R1: Reproduce Deepseek R1 „aha moment“ a RL tutorial</td> <td><a href="https://huggingface.co/philschmid" rel="nofollow">Philipp Schmid</a></td> <td><a href="https://www.philschmid.de/mini-deepseek-r1" rel="nofollow">Link</a></td> <td><a href="https://colab.research.google.com/github/philschmid/deep-learning-pytorch-huggingface/blob/main/training/mini-deepseek-r1-aha-grpo.ipynb" rel="nofollow"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a></td></tr> <tr><td>Reinforcement Learning</td> <td><a href="/docs/trl/pr_5607/en/gspo_token#trl.GRPOTrainer">GRPOTrainer</a></td> <td>RL on LLaMA 3.1-8B with GRPO and Unsloth optimizations</td> <td><a href="https://huggingface.co/AManzoni" rel="nofollow">Andrea Manzoni</a></td> <td><a href="https://colab.research.google.com/github/amanzoni1/fine_tuning/blob/main/RL_LLama3_1_8B_GRPO.ipynb" rel="nofollow">Link</a></td> <td><a href="https://colab.research.google.com/github/amanzoni1/fine_tuning/blob/main/RL_LLama3_1_8B_GRPO.ipynb" rel="nofollow"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a></td></tr> <tr><td>Instruction tuning</td> <td><a href="/docs/trl/pr_5607/en/sft_trainer#trl.SFTTrainer">SFTTrainer</a></td> <td>Fine-tuning Google Gemma LLMs using ChatML format with QLoRA</td> <td><a href="https://huggingface.co/philschmid" rel="nofollow">Philipp Schmid</a></td> <td><a href="https://www.philschmid.de/fine-tune-google-gemma" rel="nofollow">Link</a></td> <td><a href="https://colab.research.google.com/github/philschmid/deep-learning-pytorch-huggingface/blob/main/training/gemma-lora-example.ipynb" rel="nofollow"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a></td></tr> <tr><td>Structured Generation</td> <td><a href="/docs/trl/pr_5607/en/sft_trainer#trl.SFTTrainer">SFTTrainer</a></td> <td>Fine-tuning Llama-2-7B to generate Persian product catalogs in JSON using QLoRA and PEFT</td> <td><a href="https://huggingface.co/Mohammadreza" rel="nofollow">Mohammadreza Esmaeilian</a></td> <td><a href="https://huggingface.co/learn/cookbook/en/fine_tuning_llm_to_generate_persian_product_catalogs_in_json_format" rel="nofollow">Link</a></td> <td><a href="https://colab.research.google.com/github/huggingface/cookbook/blob/main/notebooks/en/fine_tuning_llm_to_generate_persian_product_catalogs_in_json_format.ipynb" rel="nofollow"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a></td></tr> <tr><td>Preference Optimization</td> <td><a href="/docs/trl/pr_5607/en/bema_for_reference_model#trl.DPOTrainer">DPOTrainer</a></td> <td>Align Mistral-7b using Direct Preference Optimization for human preference alignment</td> <td><a href="https://huggingface.co/mlabonne" rel="nofollow">Maxime Labonne</a></td> <td><a href="https://mlabonne.github.io/blog/posts/Fine_tune_Mistral_7b_with_DPO.html" rel="nofollow">Link</a></td> <td><a href="https://colab.research.google.com/github/mlabonne/llm-course/blob/main/Fine_tune_a_Mistral_7b_model_with_DPO.ipynb" rel="nofollow"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a></td></tr> <tr><td>Preference Optimization</td> <td><a href="/docs/trl/pr_5607/en/orpo_trainer#trl.experimental.orpo.ORPOTrainer">experimental.orpo.ORPOTrainer</a></td> <td>Fine-tuning Llama 3 with ORPO combining instruction tuning and preference alignment</td> <td><a href="https://huggingface.co/mlabonne" rel="nofollow">Maxime Labonne</a></td> <td><a href="https://mlabonne.github.io/blog/posts/2024-04-19_Fine_tune_Llama_3_with_ORPO.html" rel="nofollow">Link</a></td> <td><a href="https://colab.research.google.com/drive/1eHNWg9gnaXErdAa8_mcvjMupbSS6rDvi" rel="nofollow"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a></td></tr> <tr><td>Instruction tuning</td> <td><a href="/docs/trl/pr_5607/en/sft_trainer#trl.SFTTrainer">SFTTrainer</a></td> <td>How to fine-tune open LLMs in 2025 with Hugging Face</td> <td><a href="https://huggingface.co/philschmid" rel="nofollow">Philipp Schmid</a></td> <td><a href="https://www.philschmid.de/fine-tune-llms-in-2025" rel="nofollow">Link</a></td> <td><a href="https://colab.research.google.com/github/philschmid/deep-learning-pytorch-huggingface/blob/main/training/fine-tune-llms-in-2025.ipynb" rel="nofollow"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a></td></tr> <tr><td>Step-Level Reasoning</td> <td><a href="/docs/trl/pr_5607/en/gspo_token#trl.GRPOTrainer">GRPOTrainer</a></td> <td>Supervised Reinforcement Learning (SRL) for step-by-step reasoning with vLLM</td> <td><a href="https://huggingface.co/s23deepak" rel="nofollow">Deepak Swaminathan</a></td> <td><a href="https://github.com/s23deepak/Supervised-Reinforcement-Learning" rel="nofollow">Link</a></td> <td><a href="https://colab.research.google.com/github/s23deepak/Supervised-Reinforcement-Learning/blob/main/notebooks/srl_grpo_tutorial.ipynb" rel="nofollow"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a></td></tr></tbody></table> <h3 class="relative group"><a id="videos" 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="#videos"><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>Videos</span></h3> <table data-svelte-h="svelte-buf3gt"><thead><tr><th>Task</th> <th>Title</th> <th>Author</th> <th>Video</th></tr></thead> <tbody><tr><td>Instruction tuning</td> <td>Fine-tuning open AI models using Hugging Face TRL</td> <td><a href="https://huggingface.co/wietsevenema" rel="nofollow">Wietse Venema</a></td> <td><a href="https://youtu.be/cnGyyM0vOes" rel="nofollow"><img src="https://img.youtube.com/vi/cnGyyM0vOes/0.jpg"></a></td></tr> <tr><td>Instruction tuning</td> <td>How to fine-tune a smol-LM with Hugging Face, TRL, and the smoltalk Dataset</td> <td><a href="https://huggingface.co/iammayur" rel="nofollow">Mayurji</a></td> <td><a href="https://youtu.be/jKdXv3BiLu0" rel="nofollow"><img src="https://img.youtube.com/vi/jKdXv3BiLu0/0.jpg"></a></td></tr></tbody></table> <details data-svelte-h="svelte-1t15qc"><summary>⚠️ Deprecated features notice for "How to fine-tune a smol-LM with Hugging Face, TRL, and the smoltalk Dataset" (click to expand)</summary> <blockquote class="warning"><p>The tutorial uses two deprecated features:</p> <ul><li><code>SFTTrainer(..., tokenizer=tokenizer)</code>: Use <code>SFTTrainer(..., processing_class=tokenizer)</code> instead, or simply omit it (it will be inferred from the model).</li> <li><code>setup_chat_format(model, tokenizer)</code>: Use <code>SFTConfig(..., chat_template_path="Qwen/Qwen3-0.6B")</code>, where <code>chat_template_path</code> specifies the model whose chat template you want to copy.</li></ul></blockquote></details> <h2 class="relative group"><a id="vision-language-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="#vision-language-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>Vision Language Models</span></h2> <h3 class="relative group"><a id="tutorials" 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="#tutorials"><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>Tutorials</span></h3> <table data-svelte-h="svelte-12btm2r"><thead><tr><th>Task</th> <th>Class</th> <th>Description</th> <th>Author</th> <th>Tutorial</th> <th>Colab</th></tr></thead> <tbody><tr><td>Visual QA</td> <td><a href="/docs/trl/pr_5607/en/sft_trainer#trl.SFTTrainer">SFTTrainer</a></td> <td>Fine-tuning Qwen2-VL-7B for visual question answering on ChartQA dataset</td> <td><a href="https://huggingface.co/sergiopaniego" rel="nofollow">Sergio Paniego</a></td> <td><a href="https://huggingface.co/learn/cookbook/fine_tuning_vlm_trl" rel="nofollow">Link</a></td> <td><a href="https://colab.research.google.com/github/huggingface/cookbook/blob/main/notebooks/en/fine_tuning_vlm_trl.ipynb" rel="nofollow"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a></td></tr> <tr><td>Visual QA</td> <td><a href="/docs/trl/pr_5607/en/sft_trainer#trl.SFTTrainer">SFTTrainer</a></td> <td>Fine-tuning SmolVLM with TRL on a consumer GPU</td> <td><a href="https://huggingface.co/sergiopaniego" rel="nofollow">Sergio Paniego</a></td> <td><a href="https://huggingface.co/learn/cookbook/fine_tuning_smol_vlm_sft_trl" rel="nofollow">Link</a></td> <td><a href="https://colab.research.google.com/github/huggingface/cookbook/blob/main/notebooks/en/fine_tuning_smol_vlm_sft_trl.ipynb" rel="nofollow"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a></td></tr> <tr><td>SEO Description</td> <td><a href="/docs/trl/pr_5607/en/sft_trainer#trl.SFTTrainer">SFTTrainer</a></td> <td>Fine-tuning Qwen2-VL-7B for generating SEO-friendly descriptions from images</td> <td><a href="https://huggingface.co/philschmid" rel="nofollow">Philipp Schmid</a></td> <td><a href="https://www.philschmid.de/fine-tune-multimodal-llms-with-trl" rel="nofollow">Link</a></td> <td><a href="https://colab.research.google.com/github/philschmid/deep-learning-pytorch-huggingface/blob/main/training/fine-tune-multimodal-llms-with-trl.ipynb" rel="nofollow"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a></td></tr> <tr><td>Visual QA</td> <td><a href="/docs/trl/pr_5607/en/bema_for_reference_model#trl.DPOTrainer">DPOTrainer</a></td> <td>PaliGemma 🤝 Direct Preference Optimization</td> <td><a href="https://huggingface.co/merve" rel="nofollow">Merve Noyan</a></td> <td><a href="https://github.com/merveenoyan/smol-vision/blob/main/PaliGemma_DPO.ipynb" rel="nofollow">Link</a></td> <td><a href="https://colab.research.google.com/github/merveenoyan/smol-vision/blob/main/PaliGemma_DPO.ipynb" rel="nofollow"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a></td></tr> <tr><td>Visual QA</td> <td><a href="/docs/trl/pr_5607/en/bema_for_reference_model#trl.DPOTrainer">DPOTrainer</a></td> <td>Fine-tuning SmolVLM using direct preference optimization (DPO) with TRL on a consumer GPU</td> <td><a href="https://huggingface.co/sergiopaniego" rel="nofollow">Sergio Paniego</a></td> <td><a href="https://huggingface.co/learn/cookbook/fine_tuning_vlm_dpo_smolvlm_instruct" rel="nofollow">Link</a></td> <td><a href="https://colab.research.google.com/github/huggingface/cookbook/blob/main/notebooks/en/fine_tuning_vlm_dpo_smolvlm_instruct.ipynb" rel="nofollow"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a></td></tr> <tr><td>Object Detection Grounding</td> <td><a href="/docs/trl/pr_5607/en/sft_trainer#trl.SFTTrainer">SFTTrainer</a></td> <td>Fine tuning a VLM for Object Detection Grounding using TRL</td> <td><a href="https://huggingface.co/sergiopaniego" rel="nofollow">Sergio Paniego</a></td> <td><a href="https://huggingface.co/learn/cookbook/fine_tuning_vlm_object_detection_grounding" rel="nofollow">Link</a></td> <td><a href="https://colab.research.google.com/github/huggingface/cookbook/blob/main/notebooks/en/fine_tuning_vlm_object_detection_grounding.ipynb" rel="nofollow"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a></td></tr> <tr><td>Visual QA</td> <td><a href="/docs/trl/pr_5607/en/bema_for_reference_model#trl.DPOTrainer">DPOTrainer</a></td> <td>Fine-Tuning a Vision Language Model with TRL using MPO</td> <td><a href="https://huggingface.co/sergiopaniego" rel="nofollow">Sergio Paniego</a></td> <td><a href="https://huggingface.co/learn/cookbook/fine_tuning_vlm_mpo" rel="nofollow">Link</a></td> <td><a href="https://colab.research.google.com/github/huggingface/cookbook/blob/main/notebooks/en/fine_tuning_vlm_mpo.ipynb" rel="nofollow"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a></td></tr> <tr><td>Reinforcement Learning</td> <td><a href="/docs/trl/pr_5607/en/gspo_token#trl.GRPOTrainer">GRPOTrainer</a></td> <td>Post training a VLM for reasoning with GRPO using TRL</td> <td><a href="https://huggingface.co/sergiopaniego" rel="nofollow">Sergio Paniego</a></td> <td><a href="https://huggingface.co/learn/cookbook/fine_tuning_vlm_grpo_trl" rel="nofollow">Link</a></td> <td><a href="https://colab.research.google.com/github/huggingface/cookbook/blob/main/notebooks/en/fine_tuning_vlm_grpo_trl.ipynb" rel="nofollow"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a></td></tr></tbody></table> <h2 class="relative group"><a id="speech-language-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="#speech-language-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>Speech Language Models</span></h2> <h3 class="relative group"><a id="tutorials" 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="#tutorials"><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>Tutorials</span></h3> <table data-svelte-h="svelte-k81hb6"><thead><tr><th>Task</th> <th>Class</th> <th>Description</th> <th>Author</th> <th>Tutorial</th></tr></thead> <tbody><tr><td>Text-to-Speech</td> <td><a href="/docs/trl/pr_5607/en/gspo_token#trl.GRPOTrainer">GRPOTrainer</a></td> <td>Post training a Speech Language Model with GRPO using TRL</td> <td><a href="https://huggingface.co/Steveeeeeeen" rel="nofollow">Steven Zheng</a></td> <td><a href="https://huggingface.co/blog/Steveeeeeeen/llasa-grpo" rel="nofollow">Link</a></td></tr></tbody></table> <h2 class="relative group"><a id="contributing" 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="#contributing"><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>Contributing</span></h2> <p data-svelte-h="svelte-2rgict">If you have a tutorial that you would like to add to this list, please open a PR to add it. We will review it and merge it if it is relevant to the community.</p> <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/community_tutorials.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_1hqaf25 = {
	assets: "/docs/trl/pr_5607/en",
	base: "/docs/trl/pr_5607/en",
	env: {}
	};

	const element = document.currentScript.parentElement;

	const data = [null,null];

	Promise.all([
	import("/docs/trl/pr_5607/en/_app/immutable/entry/start.151d81bd.js"),
	import("/docs/trl/pr_5607/en/_app/immutable/entry/app.3d9a91c0.js")
	]).then(([kit, app]) => {
	kit.start(app, element, {
	node_ids: [0, 8],
	data,
	form: null,
	error: null
	});
	});
	}
	</script>

Xet Storage Details

Size:: 31 kB
Xet hash:: edd6dff2021e5733b857a5c4f5734244c1d7b845bb72d40edbea4b582a171610

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