Is the training Qualiopi certified?

Yes, Learni is a Qualiopi-certified training organization. This certification guarantees the quality of our courses and enables funding through OPCO and other mechanisms.

What is the duration of the LoRA Fine-Tuning Training - Customizing AI Models training?

The LoRA Fine-Tuning Training - Customizing AI Models training takes place over 35 hours. The program is structured in progressive modules for optimal skill development.

How can I fund my training?

Our courses are eligible for OPCO funding. Learni supports you through the funding process. A personalized quote is available upon request.

What are the prerequisites for this training?

The prerequisites for the LoRA Fine-Tuning Training - Customizing AI Models training are: Python basics, PyTorch fundamentals, and introductory machine learning. A preliminary interview validates your eligibility.

Is the training available in person?

Yes, the LoRA Fine-Tuning Training - Customizing AI Models training is available in remote. The format can be adapted to your needs (inter, intra, custom).

LoRA Fine-Tuning Training - Customizing AI Models | Learni

The story of Learni

Founded by passionate advocates of learning and innovation, Learni set out to make professional training accessible to everyone, everywhere in the world. Our team works in the largest cities such as Paris, Lyon, Marseille, and internationally, to support talents and organizations in their skills development.

Configure your training

Response within 24hNo commitment100% free

Only 4 spots left this month

10 spots per session maximum — 7 already taken

FormatParticipantsDateDetails

Which format do you prefer?

Methods, approaches, and teaching resources

The LoRA Fine-Tuning Training - Customizing AI Models training is delivered in-person or remotely (blended-learning, e-learning, virtual classroom, remote in-person). At Learni, a Qualiopi-certified training organization, each program is designed to maximize skills acquisition, regardless of the training mode chosen.

The trainer alternates between demonstrative, interrogative, and active methods (through practical exercises and/or real-world scenarios). This pedagogical approach ensures concrete and directly applicable learning in the workplace.

Teaching resources provided

To ensure the quality of the LoRA Fine-Tuning Training - Customizing AI Models training, Learni provides the following teaching resources:

Mac or PC computers, high-speed fiber internet, whiteboard or flipchart, video projector or interactive touchscreen (for remote sessions)
Training environments installed on workstations or accessible online
Course materials, practical exercises, and supplementary resources
Post-training access to materials and teaching resources

For in-house training at a location external to Learni, the client ensures and commits to having all necessary teaching materials (IT equipment, internet connection...) for the proper conduct of the training action in accordance with the prerequisites indicated in the communicated training program.

* contact us for remote feasibility** ratio varies depending on the training followed

Assessment methods

The assessment of skills acquired during the LoRA Fine-Tuning Training - Customizing AI Models training is carried out through:

During training: case studies, practical exercises, and professional scenarios
At the end of training: self-assessment questionnaire and skills evaluation by the trainer
After training: training completion certificate detailing acquired skills

Training accessibility

Learni is committed to the accessibility of its professional training programs. All our training programs are accessible to people with disabilities. Our teams are available to adapt teaching methods to your specific needs. Do not hesitate to contact us for any accommodation request.

Training access terms and deadlines

Training objectives

Master LoRA principles for professional fine-tuning of AI models

Develop skills in preparing datasets for LoRA

Implement LoRA fine-tuning on enterprise LLMs

Optimize and evaluate LoRA models for certified performance

Design customized AI applications with LoRA fine-tuning

Deploy LoRA models in secure production environments

Training program

Module 1LoRA Fine-Tuning Fundamentals and Environment Setup

Introduction to LoRA concepts for efficient fine-tuning. Differences with full fine-tuning. Installation of Hugging Face Transformers and PEFT. GPU/CPU environment configuration. Creation of thread project on an open-source LLM. Practical exercises on concrete enterprise cases. Hands-on first LoRA tests. Understanding rank and alpha parameters. Management of introductory datasets. Preparation of boilerplate code for professional training.

Module 2Dataset Preparation for LoRA Fine-Tuning

Data collection and cleaning for LoRA fine-tuning. Tokenization techniques with LLMs. Dataset augmentation tailored to enterprise needs. Hugging Face Datasets tools. Hands-on practice on the thread project. Professional exercises on text/image datasets. Handling JSON/CSV formats. Class balancing for certifiable AI. Concrete cases in classification/summarization. Data quality verification. Integration of pre-fine-tuning metrics. Preparation of LoRA training scripts.

Module 3Practical LoRA Fine-Tuning Implementation

Launching first LoRA fine-tuning on GPU. Configuring LoRA layers and learning rate. Training monitoring with Weights & Biases. Automatic checkpoint management. Full hands-on thread project. Exercises on LLMs like Llama or Mistral. Troubleshooting common errors. Comparison before/after fine-tuning. Fast inference tests. Adaptation to specific enterprise tasks. Integration of custom hooks. Validation of practical certified skills.

Module 4LoRA Fine-Tuning Optimization and Evaluation

LoRA optimization techniques for limited resources. Quantization and adapter merging. Evaluation metrics BLEU/ROUGE/perplexity. Cross-validation on test datasets. Hands-on thread project. Professional A/B testing exercises on models. Overfitting/underfitting analysis. TensorBoard tools for visualization. Benchmarking vs full fine-tuning. Improving enterprise AI performance. Preparation of certified reports. Concrete production cases.

Module 5LoRA Fine-Tuning Deployment and Advanced Cases

Deploying LoRA models via Hugging Face Spaces. FastAPI integration for AI APIs. Security and monitoring in production. Hands-on deployment of thread project. Exercises on multi-GPU scaling. Enterprise concrete cases: customized chatbots, text generation. Best practices for certified LoRA. Final project presentation. Summary of acquired skills. Post-training resources. Action plan for professional projects.