ML engineer: LLM fine-tuning and evaluation, computer vision. Own NVIDIA H100.
Popular repositories Loading
-
ml-case-studies
ml-case-studies PublicThree ML case studies with code, raw predictions and logs: LoRA vs QLoRA vs full fine-tuning, LLM screening for systematic reviews, LeRobot dataset QC
Python
-
llm-literature-screener
llm-literature-screener PublicOpen-source LLM pre-screening of titles and abstracts for systematic reviews: RIS/PubMed/Rayyan/Covidence in, calibrated high-recall decisions, PRISMA counts and an HTML report out
HTML
-
llm-finetune-evaluator
llm-finetune-evaluator PublicIs your fine-tuned LLM really better? Paired statistics, regression slices, trap-question and judge-calibrated evaluation with Markdown/HTML reports
Python
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.