{"id":2783,"date":"2023-07-18T15:16:25","date_gmt":"2023-07-18T09:46:25","guid":{"rendered":"https:\/\/www.analyticsvidhya.com\/datahack-summit-2023\/?page_id=2783"},"modified":"2023-08-04T10:39:54","modified_gmt":"2023-08-04T05:09:54","slug":"training-finetuning-and-evaluating-llms","status":"publish","type":"page","link":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/workshop\/training-finetuning-and-evaluating-llms\/","title":{"rendered":"Unleashing LLMs: Training, Finetuning, and Evaluating"},"content":{"rendered":"<p><span style=\"font-weight: 400;\">There is an incredible amount of research and development in Generative AI, more specifically Large Language models (LLMs). From ChatGPT to Falcon, and countless others, their names swirl around, leaving us eager to uncover their true nature. How are these models created? How to build large language models from scratch? How do they possess the ability to answer virtually any question you throw at them? These burning questions linger in our mind, fueling curiosity. The wait is over! You are in the right place.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Join us for an immersive workshop on Large Language Models (LLMs), the magical engines behind ChatGPT and Bard. Explore the cutting-edge architectures, uncover the secrets of LLMs, and witness the future of language unfold before your eyes. Get ready to embark on an extraordinary journey that will revolutionize your understanding of NLP.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Here are the detailed module wise details-<\/span><\/p>\n<h4><span style=\"font-weight: 400;\">Module 1: Getting Started with LLMs<\/span><\/h4>\n<ul>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Recap of Generative AI and its state of the art.<\/span>\n<ul>\n<li style=\"font-weight: 400;\" aria-level=\"2\"><span style=\"font-weight: 400;\">NLP (ChatGPT)<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"2\"><span style=\"font-weight: 400;\">Computer Vision (Mid-Journey)<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"2\"><span style=\"font-weight: 400;\">Audio (Voicebox)<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"2\"><span style=\"font-weight: 400;\">Video (Make-a-video)<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"2\"><span style=\"font-weight: 400;\">Multimodal (GPT4, MUM)<\/span><\/li>\n<\/ul>\n<\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Introduction to Large Language Models (LLMs)<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Why do we need LLMs?<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Understand different types of LLMs<\/span>\n<ul>\n<li style=\"font-weight: 400;\" aria-level=\"2\"><span style=\"font-weight: 400;\">Continuing the text<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"2\"><span style=\"font-weight: 400;\">Dialogue Optimized<\/span><\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<h4><span style=\"font-weight: 400;\">Module 2: Understand the current state of the art LLMs<\/span><\/h4>\n<ul>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Transformers<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">BERT<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">GPT and its variants<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">ChatGPT<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">LIMA<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Falcon<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">OpenChat<\/span><\/li>\n<\/ul>\n<h4><span style=\"font-weight: 400;\">Module 3: Training and Evaluating LLMs and their Best Practices<\/span><\/h4>\n<ul>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Build vs Buy Pretrained LLM models?<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Understand cost and infrastructure involved<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Discuss the scaling laws<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Explore Parallel and Distributed Computing Strategies<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Understand the data collection and preprocessing steps<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Train LLMs from scratch with best practices<\/span>\n<ul>\n<li style=\"font-weight: 400;\" aria-level=\"2\"><span style=\"font-weight: 400;\">Continuing the text<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"2\"><span style=\"font-weight: 400;\">Instruction aligned<\/span><\/li>\n<\/ul>\n<\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Evaluate LLMs\u00a0<\/span><\/li>\n<\/ul>\n<h4><span style=\"font-weight: 400;\">Module 4: Finetuning and Prompt Engineering<\/span><\/h4>\n<ul>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">How can we use LLMs on the downstream tasks?<\/span>\n<ul>\n<li style=\"font-weight: 400;\" aria-level=\"2\"><span style=\"font-weight: 400;\">In Context Learning (Prompting)<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"2\"><span style=\"font-weight: 400;\">Finetuning<\/span><\/li>\n<\/ul>\n<\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Learn about prompt engineering and its different techniques.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Understand different finetuning techniques<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Finetune LLMs on downstream use cases.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">When to use prompting\/finetuning?<\/span><\/li>\n<\/ul>\n<h4><span style=\"font-weight: 400;\">Module 5: Parameter Efficient Fine Tuning methods<\/span><\/h4>\n<ul>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Understand the challenges on finetuning LLMs<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">What is Parameter Efficient Fine Tuning (PEFT)?<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Understanding different PEFT techniques<\/span>\n<ul>\n<li style=\"font-weight: 400;\" aria-level=\"2\"><span style=\"font-weight: 400;\">Prefix Tuning<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"2\"><span style=\"font-weight: 400;\">LoRA<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"2\"><span style=\"font-weight: 400;\">QLoRA<\/span><\/li>\n<\/ul>\n<\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Finetune LLM on a single GPU using PEFT techniques<\/span><\/li>\n<\/ul>\n<h4><span style=\"font-weight: 400;\">Module 6: Master LLM Tools and Frameworks<\/span><\/h4>\n<ul>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Understand LLM tools and frameworks like LlamaIndex, LangChain and Vector DBs and learn when to use them?<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Build chatbots on a private knowledge base.<\/span><\/li>\n<\/ul>\n<p><strong>Pre-requisites:<\/strong><\/p>\n<ul>\n<li>System Requirement and Setup\n<ul>\n<li>Laptop with at least 4-8 GB of RAM<\/li>\n<li>We will be using a cloud jupyter notebook powered by GPU for the workshop<\/li>\n<\/ul>\n<\/li>\n<li>Offline Setup [Optional]\n<ul>\n<li>GPU good to have!<\/li>\n<li>Install Python3.9 or higher version(<a href=\"https:\/\/www.python.org\/downloads\/\" target=\"_blank\" rel=\"noopener\">Resource<\/a>)<\/li>\n<li>Install jupyter notebook (<a href=\"https:\/\/jupyter.org\/install\" target=\"_blank\" rel=\"noopener\">Resource<\/a>)<\/li>\n<\/ul>\n<\/li>\n<li>Pre-reads\n<ul>\n<li>Programming knowledge in Python (<a href=\"https:\/\/www.analyticsvidhya.com\/blog\/2016\/01\/complete-tutorial-learn-data-science-python-scratch-2\/\" target=\"_blank\" rel=\"noopener\">Resource<\/a>)<\/li>\n<li>Jupyter Notebook Environment familiarity (<a href=\"https:\/\/www.analyticsvidhya.com\/blog\/2018\/05\/starters-guide-jupyter-notebook\/\" target=\"_blank\" rel=\"noopener\">Resource<\/a>)<\/li>\n<li>Basics of Machine Learning and Deep Learning (<a href=\"https:\/\/www.analyticsvidhya.com\/blog\/2017\/09\/common-machine-learning-algorithms\/\" target=\"_blank\" rel=\"noopener\">Resource<\/a>,<a href=\"https:\/\/www.analyticsvidhya.com\/blog\/2017\/09\/common-machine-learning-algorithms\/\" target=\"_blank\" rel=\"noopener\">Resource<\/a>)<\/li>\n<li>Fundamentals of NLP(<a href=\"https:\/\/www.analyticsvidhya.com\/blog\/2017\/01\/ultimate-guide-to-understand-implement-natural-language-processing-codes-in-python\/\" target=\"_blank\" rel=\"noopener\">Resource1<\/a>,<a href=\"https:\/\/www.analyticsvidhya.com\/blog\/2017\/06\/word-embeddings-count-word2veec\/\" target=\"_blank\" rel=\"noopener\">Resource2<\/a>)<\/li>\n<li>Familiarity with Pytorch(<a href=\"https:\/\/www.analyticsvidhya.com\/blog\/2020\/07\/how-to-train-an-image-classification-model-in-pytorch-and-tensorflow\/\" target=\"_blank\" rel=\"noopener\">Resource<\/a>)<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p><span style=\"font-weight: 400;\">Note: These are tentative details and are subject to change.<\/span><\/p>\n","protected":false},"excerpt":{"rendered":"<p>There is an incredible amount of research and development in Generative AI, more specifically Large Language models (LLMs). From ChatGPT to Falcon, and countless others, their names swirl around, leaving us eager to uncover their true nature. How are these models created? How to build large language models from scratch? How do they possess the [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":2832,"parent":890,"menu_order":-1,"comment_status":"closed","ping_status":"closed","template":"workshop-detail.php","meta":[],"acf":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v20.7 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Unleashing LLMs: Training, Finetuning, and Evaluating - DataHack Summit 2023<\/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:\/\/www.analyticsvidhya.com\/dhs-2023\/workshop\/training-finetuning-and-evaluating-llms\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Unleashing LLMs: Training, Finetuning, and Evaluating - DataHack Summit 2023\" \/>\n<meta property=\"og:description\" content=\"There is an incredible amount of research and development in Generative AI, more specifically Large Language models (LLMs). From ChatGPT to Falcon, and countless others, their names swirl around, leaving us eager to uncover their true nature. How are these models created? How to build large language models from scratch? How do they possess the [&hellip;]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.analyticsvidhya.com\/dhs-2023\/workshop\/training-finetuning-and-evaluating-llms\/\" \/>\n<meta property=\"og:site_name\" content=\"DataHack Summit 2023\" \/>\n<meta property=\"article:modified_time\" content=\"2023-08-04T05:09:54+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.analyticsvidhya.com\/dhs-2023\/wp-content\/uploads\/2023\/07\/Workshop_llm_2-2.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"500\" \/>\n\t<meta property=\"og:image:height\" content=\"250\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"3 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.analyticsvidhya.com\/dhs-2023\/workshop\/training-finetuning-and-evaluating-llms\/\",\"url\":\"https:\/\/www.analyticsvidhya.com\/dhs-2023\/workshop\/training-finetuning-and-evaluating-llms\/\",\"name\":\"Unleashing LLMs: Training, Finetuning, and Evaluating - DataHack Summit 2023\",\"isPartOf\":{\"@id\":\"https:\/\/www.analyticsvidhya.com\/dhs-2023\/#website\"},\"datePublished\":\"2023-07-18T09:46:25+00:00\",\"dateModified\":\"2023-08-04T05:09:54+00:00\",\"breadcrumb\":{\"@id\":\"https:\/\/www.analyticsvidhya.com\/dhs-2023\/workshop\/training-finetuning-and-evaluating-llms\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.analyticsvidhya.com\/dhs-2023\/workshop\/training-finetuning-and-evaluating-llms\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.analyticsvidhya.com\/dhs-2023\/workshop\/training-finetuning-and-evaluating-llms\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/www.analyticsvidhya.com\/dhs-2023\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Workshop\",\"item\":\"https:\/\/www.analyticsvidhya.com\/dhs-2023\/workshop\/\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"Unleashing LLMs: Training, Finetuning, and Evaluating\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.analyticsvidhya.com\/dhs-2023\/#website\",\"url\":\"https:\/\/www.analyticsvidhya.com\/dhs-2023\/\",\"name\":\"DataHack Summit 2023\",\"description\":\"\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.analyticsvidhya.com\/dhs-2023\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"en-US\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Unleashing LLMs: Training, Finetuning, and Evaluating - DataHack Summit 2023","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:\/\/www.analyticsvidhya.com\/dhs-2023\/workshop\/training-finetuning-and-evaluating-llms\/","og_locale":"en_US","og_type":"article","og_title":"Unleashing LLMs: Training, Finetuning, and Evaluating - DataHack Summit 2023","og_description":"There is an incredible amount of research and development in Generative AI, more specifically Large Language models (LLMs). From ChatGPT to Falcon, and countless others, their names swirl around, leaving us eager to uncover their true nature. How are these models created? How to build large language models from scratch? How do they possess the [&hellip;]","og_url":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/workshop\/training-finetuning-and-evaluating-llms\/","og_site_name":"DataHack Summit 2023","article_modified_time":"2023-08-04T05:09:54+00:00","og_image":[{"width":500,"height":250,"url":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/wp-content\/uploads\/2023\/07\/Workshop_llm_2-2.jpg","type":"image\/jpeg"}],"twitter_card":"summary_large_image","twitter_misc":{"Est. reading time":"3 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/workshop\/training-finetuning-and-evaluating-llms\/","url":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/workshop\/training-finetuning-and-evaluating-llms\/","name":"Unleashing LLMs: Training, Finetuning, and Evaluating - DataHack Summit 2023","isPartOf":{"@id":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/#website"},"datePublished":"2023-07-18T09:46:25+00:00","dateModified":"2023-08-04T05:09:54+00:00","breadcrumb":{"@id":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/workshop\/training-finetuning-and-evaluating-llms\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.analyticsvidhya.com\/dhs-2023\/workshop\/training-finetuning-and-evaluating-llms\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/workshop\/training-finetuning-and-evaluating-llms\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/"},{"@type":"ListItem","position":2,"name":"Workshop","item":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/workshop\/"},{"@type":"ListItem","position":3,"name":"Unleashing LLMs: Training, Finetuning, and Evaluating"}]},{"@type":"WebSite","@id":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/#website","url":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/","name":"DataHack Summit 2023","description":"","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"en-US"}]}},"_links":{"self":[{"href":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/wp-json\/wp\/v2\/pages\/2783"}],"collection":[{"href":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/wp-json\/wp\/v2\/comments?post=2783"}],"version-history":[{"count":10,"href":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/wp-json\/wp\/v2\/pages\/2783\/revisions"}],"predecessor-version":[{"id":3315,"href":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/wp-json\/wp\/v2\/pages\/2783\/revisions\/3315"}],"up":[{"embeddable":true,"href":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/wp-json\/wp\/v2\/pages\/890"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/wp-json\/wp\/v2\/media\/2832"}],"wp:attachment":[{"href":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/wp-json\/wp\/v2\/media?parent=2783"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}