Hire this AI Trainer
Sign in or create an account to invite AI Trainers to your job.
AWS SageMaker
Text
Document
Fine-tuningLLM Fine-tuning and Instruction Data Labeling. Brings 2+ years of professional experience across legal operations, contract review, compliance, and structured analysis. Core strengths include HuggingFace Hub. Education includes Bachelor of Engineering, University of Nigeria, Nsukka (2024). AI-training focus includes data types such as Text and labeling workflows including Fine-tuning.
I was asked to write snippets of python code and label the function of the code. The snippets were mean to execute only a single task and should be classifiable.
I created a custom instruction dataset to fine-tune a large language model (LLaMA 3.1 8B) for an AI tax law assistant. The data labeling process involved supervised fine-tuning (SFT), selecting and curating prompts and responses relevant to Nigerian tax law. This work contributed to the accuracy and domain specificity of the chatbot application. • Designed and collected a domain-specific text dataset for SFT. • Labeled text data with expert-generated prompts and responses. • Used Unsloth, HuggingFace Transformers, bitsandbytes, and PEFT for model fine-tuning. • Ensured data consistency and high labeling quality through careful prompt selection.
Bachelor of Engineering, Electronic Engineering
Machine Learning Researcher
Freelance Machine Learning Developer
