Fine-tuned large language models (LLMs) excel at relatively simple code generation tasks, but struggle with more intricate code, specialized libraries, or complex application demos.

This MLCon session addresses a well-known limitation of LLM—hallucinations—by proposing an innovative dataset representation strategy. While conventional fine-tuning often employs a question-output pair format, it also sometimes leads to undesirable hallucinations. To combat these limitations, this session advocates for breaking down the training data into smaller, more descriptive components and constructing them sequentially into complex code.

By adopting this structured approach, even smaller LLMs compatible with consumer-grade GPUs can improve significantly. Before fine-tuning, LLMs tend to generate random permutations of parameters and pipelines unrelated to the target library.

However, after fine-tuning with an enhanced dataset representation, the model outputs code more aligned with the intended library, eliminating random permutations of library parameters from the output. 

Join here and learn how you can optimise LLMs to suit your needs!