Project 01 / Case study
Tax LLM SFT & Evaluation
A structured case study for supervised fine-tuning and comparing a base model with its fine-tuned counterpart in a tax-domain setting.
Problem
Coming soon — add verified project details here.
Context
Coming soon — add verified project details here.
My Role
Coming soon — add verified project details here.
Approach
Planned scope: document the QLoRA-based supervised fine-tuning workflow and the controlled comparison between the base and fine-tuned models.
Architecture / Workflow
Coming soon — add verified project details here.
Experiments
Coming soon — add verified project details here.
Results
Coming soon — add verified project details here.
Lessons Learned
Coming soon — add verified project details here.