Downloads · 30 days
0
medgaze-adapters
abhijit2k01/medgaze-adapters
medgaze-adapters is a machine learning model from abhijit2k01. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for medgaze. The card lists the license as mit.
Decode-only, rank-8 LoRA adapters on the query rows of each model's top-100 fixation heads (the attention heads that look where a question points), trained on SLAKE closed questions with an answer loss plus a mask-sup…
Access
Public
Updated Sep 23, 2026
Repo size
35.1 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt35.1 MB · 100%
At a glance
- Library
- medgaze
- License
- mit
- Access
- Public
- Created
- Sep 23, 2026
- Updated
- Sep 23, 2026
- SHA
- 0842fef9
Model card
From the Hugging Face model README
MedGaze adapters
Decode-only, rank-8 LoRA adapters on the query rows of each model's top-100 fixation heads (the attention heads that look where a question points), trained on SLAKE closed questions with an answer loss plus a mask-supervised attention term (recipe "V-g", 400 steps).
import os
from huggingface_hub import snapshot_download
os.environ["GAZEMED_ADAPTERS"] = snapshot_download("abhijit2k01/medgaze-adapters")
from medgaze import GazeModel
gm = GazeModel.from_pretrained("Qwen/Qwen3-VL-2B-Instruct", gaze="auto")
print(gm.describe())
index.json lists every adapter with its checksum, what it was measured to do and its caveats
(the accuracy gain is in-domain; it does not transfer to VQA-RAD). rankings/ holds the
fixation-head rankings the adapters were trained on. Research use only; not a medical device.
Paper, code and project page: https://aj-das-research.github.io/GazeHeads-Medical-VLMs/
- Library
- medgaze
- License
- mit
- Created
- Sep 23, 2026
- Updated
- Sep 23, 2026