Text Generation
PEFT
Safetensors
rare-disease
clinical-nlp
phenotype-extraction
hpo
lora
llama-2
conversational
Instructions to use shyrcathy/rare-phenix-llama2-70b-raredis with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use shyrcathy/rare-phenix-llama2-70b-raredis with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-70b-chat-hf") model = PeftModel.from_pretrained(base_model, "shyrcathy/rare-phenix-llama2-70b-raredis") - Notebooks
- Google Colab
- Kaggle
Define UDN and add citation
Browse files
README.md
CHANGED
|
@@ -50,7 +50,7 @@ The full RARE-PHENIX workflow includes additional downstream modules for HPO sta
|
|
| 50 |
|
| 51 |
This adapter was fine-tuned on the public RareDis corpus.
|
| 52 |
|
| 53 |
-
It is **not** the full UDN-trained RARE-PHENIX model described in the manuscript. Controlled-access UDN data and UDN-trained model artifacts are not included.
|
| 54 |
|
| 55 |
## Base model
|
| 56 |
|
|
@@ -123,4 +123,7 @@ This adapter is intended for research use in rare disease phenotype extraction w
|
|
| 123 |
|
| 124 |
## Citation
|
| 125 |
|
| 126 |
-
If you use this
|
|
|
|
|
|
|
|
|
|
|
|
| 50 |
|
| 51 |
This adapter was fine-tuned on the public RareDis corpus.
|
| 52 |
|
| 53 |
+
It is **not** the full Undiagnosed Diseases Network (UDN)-trained RARE-PHENIX model described in the manuscript. Controlled-access Undiagnosed Diseases Network (UDN) data and UDN-trained model artifacts are not included.
|
| 54 |
|
| 55 |
## Base model
|
| 56 |
|
|
|
|
| 123 |
|
| 124 |
## Citation
|
| 125 |
|
| 126 |
+
If you use this adapter, please cite:
|
| 127 |
+
|
| 128 |
+
Shyr, C., Hu, Y., Tinker, R.J., Cassini, T.A., Byram, K.W., Hamid, R., Fabbri, D.V., Wright, A., Peterson, J.F., Bastarache, L., and Xu, H. 2026. *An artificial intelligence framework for end-to-end rare disease phenotyping from clinical notes using large language models*. arXiv preprint arXiv:2602.20324.
|
| 129 |
+
|