--- title: Fine-tuning Llama-3 with ORPO: A Deep Dive | daily.dev description: This post provides a deep dive into fine-tuning Llama-3 with ORPO. It covers the code breakdown, customization, notebook login, defining tasks and preferences,... canonical: https://daily.dev/posts/fine-tuning-llama-3-with-orpo-a-deep-dive-vnvjoourr twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Fine-tuning Llama-3 with ORPO: A Deep Dive | daily.dev og:description: This post provides a deep dive into fine-tuning Llama-3 with ORPO. It covers the code breakdown, customization, notebook login, defining tasks and preferences,... og:url: https://daily.dev/posts/fine-tuning-llama-3-with-orpo-a-deep-dive-vnvjoourr og:image: https://api.daily.dev/og/posts/vNvjoOURR.png og:image:alt: Fine-tuning Llama-3 with ORPO: A Deep Dive og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Fine-tuning Llama-3 with ORPO: A Deep Dive **[GoPenAI](https://daily.dev/sources/gopenai)** · 6 min read · 2 upvotes · 0 comments ## Summary This post provides a deep dive into fine-tuning Llama-3 with ORPO. It covers the code breakdown, customization, notebook login, defining tasks and preferences, loading tokenizer and model, preparing ORPO trainer, training the model, and merging the QLoRA adapter with the base model. The post also mentions additional considerations such as evaluation and hardware requirements. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: --- Tags: [#transformers](https://daily.dev/tags/transformers) [View this post on daily.dev](https://daily.dev/posts/fine-tuning-llama-3-with-orpo-a-deep-dive-vnvjoourr) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Fine-tuning Llama-3 with ORPO: A Deep Dive","url":"https://daily.dev/posts/fine-tuning-llama-3-with-orpo-a-deep-dive-vnvjoourr","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/fine-tuning-llama-3-with-orpo-a-deep-dive-vnvjoourr"},"datePublished":"2024-04-26T10:56:40.638Z","dateModified":"2024-05-09T09:27:15.675Z","description":"This post provides a deep dive into fine-tuning Llama-3 with ORPO. It covers the code breakdown, customization, notebook login, defining tasks and preferences,...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/16f8ce12a30a955e7bad7ae114c2b3ae?_a=AQAEuiZ","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/16f8ce12a30a955e7bad7ae114c2b3ae?_a=AQAEuiZ","isAccessibleForFree":true,"articleSection":"GoPenAI","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"GoPenAI","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/f34dfd0c312c4a59b897eb64ad28d895","url":"https://daily.dev/sources/gopenai"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/fine-tuning-llama-3-with-orpo-a-deep-dive-vnvjoourr","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":2},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"transformers","timeRequired":"PT6M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"GoPenAI","item":"https://daily.dev/sources/gopenai"},{"@type":"ListItem","position":3,"name":"Fine-tuning Llama-3 with ORPO: A Deep Dive"}]} ```