Descriptions
Fine-Tuning Open-Weight LLMs for Engineers, Fine-Tuning Open-Weight LLMs for Engineers is a practical, live workshop led by Daniel Voigt Godoy that teaches engineers how to build, fine-tune, and evaluate large language models using open-weight models. Instead of relying on overly theoretical approaches or expensive infrastructure, you will learn a focused workflow: select a narrow task suitable for fine-tuning, prepare a clean task-specific dataset, train a LoRA/QLoRA adapter using accessible hardware, and evaluate whether the results justify the effort. You will learn to compare fine-tuning with prompting and retrieval-augmented generation (RAG), assess tasks based on repetition, output clarity, evaluation, data availability, and cost, and turn broad ideas into specific, trainable tasks. The workshop also covers formatting examples into consistent instruction/input/output structures, removing ambiguous or low-value examples, configuring training parameters such as target modules, rank, learning rate, batch size, and sequence length, and saving adapters for reuse.
What you’ll learn
- Determine when fine-tuning is more appropriate than prompting or retrieval-augmented generation (RAG) by using a structured scorecard.
- Evaluate candidate tasks based on repetition, output clarity, evaluation feasibility, data availability, and cost.
- Transform broad AI use cases into narrow, clearly defined tasks suitable for fine-tuning.
- Prepare a clean, task-specific dataset using a consistent instruction/input/output format and remove ambiguous or low-value examples.
- Configure and train LoRA/QLoRA adapters, including target modules, rank, learning rate, batch size, and sequence length.
- Evaluate fine-tuning results by comparing the base and fine-tuned models on a held-out evaluation set.
- Assess improvements in output format consistency, task accuracy, and failure patterns.
- Diagnose common fine-tuning problems and determine whether to improve the data, task definition, model choice, or training settings.
- Use a reusable notebook for dataset preparation, training, inference, and evaluation in future experiments.
- Decide whether to continue fine-tuning, collect better examples, switch to RAG, or stop based on measured results.
Who this course is for
- Technical founders prototyping AI products.
- Applied AI and machine learning engineers.
- Backend engineers building features powered by large language models.
Specificatoin of Fine-Tuning Open-Weight LLMs for Engineers
- Publisher : Maven
- Teacher : Daniel Voigt Godoy
- Language : English
- Level : All Levels
- Number of Course :
- Duration : 4 hours and 46 minutes
Content of Fine-Tuning Open-Weight LLMs for Engineers

Pictures

Sample Clip
Installation Guide
Extract the files and watch with your favorite player
Subtitle : Not Available
Quality: 1080p
Download Links
Downloadly
Rapidgator
File(s) password: www.downloadly.ir
File size
1.02 GB



2 Comments. Leave new
Hi. please add rapidgator link. Thanks.
Hi
Added