Use Cases |
Areas: | |
Applications: | building foundational models for healthcare |
|
Primary Use Cases: | research purposes, stepping stone for foundational models |
|
Limitations: | not for clinical practice, not for medical diagnosis, not for direct or indirect healthcare advice, prone to error, can produce toxic content |
|
|
Training Details |
Data Sources: | argilla/dpo-mix-7k, nvidia/HelpSteer, jondurbin/airoboros-3.2, hkust-nlp/deita-10k-v0, LDJnr/Capybara, HPAI-BSC/CareQA, GBaker/MedQA-USMLE-4-options, lukaemon/mmlu, bigbio/pubmed_qa, openlifescienceai/medmcqa, bigbio/med_qa, HPAI-BSC/better-safe-than-sorry, HPAI-BSC/pubmedqa-cot, HPAI-BSC/medmcqa-cot, HPAI-BSC/medqa-cot |
|
Methodology: | Supervised fine-tuning on top of Llama 3 8B using medical and general domain datasets, model merging using DARE-TIES process, two-stage DPO process for human preference alignment |
|
|