| --- |
| license: other |
| tags: [medical-imaging, chest-xray, visual-question-answering, diff-vqa] |
| --- |
| |
| # LAP-VQA — GPT-2 Medium (pretrained, cross-attn) |
|
|
| Best checkpoint from Diff-VQA online multi-objective (reg-steps) training. |
|
|
| **Weights only** — this file contains `state_dict` + architecture config |
| (`vis_dim`, `d_model`, `num_layers`, ...). It does **not** contain optimizer or |
| LR-scheduler state, so it cannot be used to exactly resume an interrupted |
| training run (fine for eval / deployment / fine-tuning from weights). |
|
|
| ⚠️ Gated: medical-imaging model weights, access granted on request. |
|
|
