Ankit Ranjan

Data Science Intern @Art - Abstinent Research & Technologies

Bhopal, IN

For this position, my major duties will include: 1. Training and Fine-tuning LLM Models • Assist in data preparation, model training, and fine-tuning using specialized datasets. • Run experiments, tune hyperparameters, and optimize training processes. • Track and document training experiments for improvement. Human Feedback Loop for LLM Models • Participate in annotating and reviewing model outputs for quality. • Involve in human-in-the-loop (HITL) processes to provide feedback during training. • Conduct error analysis and assist with user testing to gather real-world feedback. Creating SFTs and RLHF • Help prepare datasets for supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF). • Collaborate with researchers to ensure data alignment and improve model behavior through SFT and RLHF methods. Evaluation of LLM Models • Assist in defining and tracking evaluation metrics. • Perform both qualitative and quantitative evaluation of models and document performance issues. • Report results and provide recommendations for model improvements

LNCT Group of Colleges

Bachelor's degree, Computer Science(AI,ML)