Top-level README
Browse files
README.md
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags: [medical-imaging, fairness, lora]
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# FairLLaVA — Pretrained Checkpoints
|
| 7 |
+
|
| 8 |
+
Fairness-aware LoRA adapters for medical vision–language models, from the
|
| 9 |
+
[FairLLaVA paper](https://arxiv.org/abs/2603.26008).
|
| 10 |
+
Code: https://github.com/bhosalems/FairLLaVA
|
| 11 |
+
|
| 12 |
+
| Subdir | Dataset | Base LLM | Vision Tower |
|
| 13 |
+
|---|---|---|---|
|
| 14 |
+
| [`mimic-cxr/`](./mimic-cxr) | MIMIC-CXR | `lmsys/vicuna-7b-v1.5` | BiomedCLIP-CXR-518 |
|
| 15 |
+
| [`padchest/`](./padchest) | PadChest | `lmsys/vicuna-7b-v1.5` | BiomedCLIP-CXR-518 |
|
| 16 |
+
| [`ham10000/`](./ham10000) | HAM10000 | `liuhaotian/llava-v1.5-7b` | CLIP ViT-L/14-336 |
|