trl/pr_3582/en/community_tutorials.html

<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Community Tutorials&quot;,&quot;local&quot;:&quot;community-tutorials&quot;,&quot;sections&quot;:[],&quot;depth&quot;:1}">
		<link href="/docs/trl/pr_3582/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
		<link rel="modulepreload" href="/docs/trl/pr_3582/en/_app/immutable/entry/start.0f0f318c.js">
		<link rel="modulepreload" href="/docs/trl/pr_3582/en/_app/immutable/chunks/scheduler.d627b047.js">
		<link rel="modulepreload" href="/docs/trl/pr_3582/en/_app/immutable/chunks/singletons.affb0d47.js">
		<link rel="modulepreload" href="/docs/trl/pr_3582/en/_app/immutable/chunks/index.a57a1c33.js">
		<link rel="modulepreload" href="/docs/trl/pr_3582/en/_app/immutable/chunks/paths.15dc14db.js">
		<link rel="modulepreload" href="/docs/trl/pr_3582/en/_app/immutable/entry/app.b27a462f.js">
		<link rel="modulepreload" href="/docs/trl/pr_3582/en/_app/immutable/chunks/index.73c51727.js">
		<link rel="modulepreload" href="/docs/trl/pr_3582/en/_app/immutable/nodes/0.8cd8e450.js">
		<link rel="modulepreload" href="/docs/trl/pr_3582/en/_app/immutable/chunks/each.e59479a4.js">
		<link rel="modulepreload" href="/docs/trl/pr_3582/en/_app/immutable/nodes/7.2bbde577.js">
		<link rel="modulepreload" href="/docs/trl/pr_3582/en/_app/immutable/chunks/getInferenceSnippets.256dfbf1.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Community Tutorials&quot;,&quot;local&quot;:&quot;community-tutorials&quot;,&quot;sections&quot;:[],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END -->      <p></p>  <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>  <h1 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></h1> <table data-svelte-h="svelte-15eb923"><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_3582/en/grpo_trainer#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_3582/en/grpo_trainer#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_3582/en/grpo_trainer#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_3582/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_3582/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_3582/en/dpo_trainer#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_3582/en/orpo_trainer#trl.ORPOTrainer">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_3582/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></tbody></table> <iframe class="w-full xl:w-4/6 h-80" src="https://www.youtube-nocookie.com/embed/cnGyyM0vOes" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe>  <h1 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></h1> <table data-svelte-h="svelte-1pjamvx"><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_3582/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_3582/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_3582/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_3582/en/dpo_trainer#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_3582/en/dpo_trainer#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_3582/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></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"><span data-svelte-h="svelte-1kd6by1">&lt;</span> <span data-svelte-h="svelte-x0xyl0">&gt;</span> <span data-svelte-h="svelte-1dajgef"><span class="underline ml-1.5">Update</span> on GitHub</span></a>  <p></p> 
			
			<script>
				{
					__sveltekit_4tczb2 = {
						assets: "/docs/trl/pr_3582/en",
						base: "/docs/trl/pr_3582/en",
						env: {}
					};

					const element = document.currentScript.parentElement;

					const data = [null,null];

					Promise.all([
						import("/docs/trl/pr_3582/en/_app/immutable/entry/start.0f0f318c.js"),
						import("/docs/trl/pr_3582/en/_app/immutable/entry/app.b27a462f.js")
					]).then(([kit, app]) => {
						kit.start(app, element, {
							node_ids: [0, 7],
							data,
							form: null,
							error: null
						});
					});
				}
			</script>