Downloads · 30 days
13
13% of all-time downloads
majdabd33/trialmatchai-gemma2-reranker-lora
trialmatchai-gemma2-reranker-lora is a text generation model from majdabd33. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as gemma.
A LoRA adapter for the google/gemma-2-2b family, fine-tuned for the second-level criterion reranking stage of TrialMatchAI, an end-to-end system that matches patients to the clinical trials they are eligible for.
Downloads · 30 days
13
13% of all-time downloads
All-time downloads
100
Public
Repo size
64.2 MB
Likes
0
Public
Click a slice to open those files.
.json34.4 MB · 54%
From the Hugging Face model README
A LoRA adapter for the google/gemma-2-2b family, fine-tuned for the second-level criterion reranking stage of TrialMatchAI, an end-to-end system that matches patients to the clinical trials they are eligible for.
After first-level retrieval surfaces candidate trials, this adapter scores each (patient, trial criterion) pair so the most relevant trials are reranked to the top and shortlisted for the downstream eligibility-reasoning stage.
TrialMatchAI loads this adapter automatically. In config.json it sits on top of the instruct base:
"reranker_model_path": "google/gemma-2-2b-it",
"reranker_adapter_path": "majdabd33/trialmatchai-gemma2-reranker-lora"
It downloads on first use, so no separate model download step is needed. See the TrialMatchAI repository for the full pipeline and configuration.
This is an adapter of google/gemma-2-2b, governed by the
Gemma license; accept it on the base model page before use. For
research and informational use only. It is not medical advice, not a medical device, and must not
replace review by qualified healthcare professionals.
Abdallah, M. et al. TrialMatchAI: an end-to-end AI-powered clinical trial recommendation system to streamline patient-to-trial matching. Nature Communications 17, 4472 (2026). https://doi.org/10.1038/s41467-026-70509-w