<?xml version="1.0" encoding="utf-8" ?>
<!DOCTYPE FL_Course SYSTEM "https://www.flane.de/dtd/fl_course095.dtd"><?xml-stylesheet type="text/xsl" href="https://portal.flane.ch/css/xml-course.xsl"?><course productid="34498" language="fr" source="https://portal.flane.ch/swisscom/fr/xml-course/nvidia-ellmc" lastchanged="2025-07-29T12:18:27+02:00" parent="https://portal.flane.ch/swisscom/fr/xml-courses"><title>Efficient Large Language Model (LLM) Customization</title><productcode>ELLMC</productcode><vendorcode>NV</vendorcode><vendorname>Nvidia</vendorname><fullproductcode>NV-ELLMC</fullproductcode><version>1.0</version><objective>&lt;p&gt;By the time you complete this course you will be able to:
&lt;/p&gt;
&lt;ul&gt;
&lt;li&gt;Apply parameter-efficient fine-tuning techniques with limited data to accomplish tasks specific to your use cases&lt;/li&gt;&lt;li&gt;Use LLMs to create synthetic data in the service of fine-tuning smaller LLMs to perform a desired task&lt;/li&gt;&lt;li&gt;Drive down model size requirements through a virtuous cycle of combining synthetic data generation and model customization.&lt;/li&gt;&lt;li&gt;Build a generative application composed of multiple customized models you generate data for and create throughout the workshop.&lt;/li&gt;&lt;/ul&gt;</objective><essentials>&lt;ul&gt;
&lt;li&gt;Professional experience with the Python programming language.&lt;/li&gt;&lt;li&gt;Familiarity with fundamental deep learning topics like model architecture, training and inference.&lt;/li&gt;&lt;li&gt;Familiarity with a modern Python-based deep learning framework (PyTorch preferred).&lt;/li&gt;&lt;li&gt;Familiarity working with out-of-the-box pretrained LLMs.&lt;/li&gt;&lt;/ul&gt;</essentials><objective_plain>By the time you complete this course you will be able to:



- Apply parameter-efficient fine-tuning techniques with limited data to accomplish tasks specific to your use cases
- Use LLMs to create synthetic data in the service of fine-tuning smaller LLMs to perform a desired task
- Drive down model size requirements through a virtuous cycle of combining synthetic data generation and model customization.
- Build a generative application composed of multiple customized models you generate data for and create throughout the workshop.</objective_plain><essentials_plain>- Professional experience with the Python programming language.
- Familiarity with fundamental deep learning topics like model architecture, training and inference.
- Familiarity with a modern Python-based deep learning framework (PyTorch preferred).
- Familiarity working with out-of-the-box pretrained LLMs.</essentials_plain><duration unit="d" days="1">1 jour</duration><pricelist><price country="US" currency="USD">500.00</price><price country="DE" currency="EUR">500.00</price><price country="AT" currency="EUR">500.00</price><price country="SE" currency="EUR">500.00</price><price country="SI" currency="EUR">500.00</price><price country="GB" currency="GBP">420.00</price><price country="IT" currency="EUR">500.00</price><price country="CA" currency="CAD">690.00</price></pricelist><miles/></course>