bluesky333/medphi2
TEXT GENERATIONConcurrency Cost:1Model Size:3BQuant:BF16Ctx Length:2kPublished:Jun 9, 2024License:mitArchitecture:Transformer0.0K Open Weights Cold

MedPhi-2 is a 2.7 billion parameter Phi-2 model, further trained by bluesky333 for the biomedical domain. This clinical Large Language Model (LLM) is specifically designed for medical question answering, as proposed in the MedExQA paper. It excels at processing and generating English language responses relevant to medical contexts, leveraging its specialized fine-tuning.

Loading preview...

Popular Sampler Settings

Top 3 parameter combinations used by Featherless users for this model. Click a tab to see each config.

temperature
top_p
top_k
frequency_penalty
presence_penalty
repetition_penalty
min_p