Initialize SCOPE research checkpoint repository
Browse files
README.md
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
- vi
|
| 5 |
+
base_model: Qwen/Qwen3-8B
|
| 6 |
+
tags:
|
| 7 |
+
- multimodal-question-answering
|
| 8 |
+
- knowledge-graph
|
| 9 |
+
- research-checkpoints
|
| 10 |
+
- work-in-progress
|
| 11 |
+
---
|
| 12 |
+
# SCOPE
|
| 13 |
+
|
| 14 |
+
Research checkpoint repository for the SCOPE-KG project and its controlled baseline comparisons on ScienceQA and a documented Text–Image resplit of MultiModalQA.
|
| 15 |
+
|
| 16 |
+
Experiments are in progress. A checkpoint is not evidence that SCOPE outperforms MIRA or that the paper is complete. Validation and test results are distinguished in each run manifest. Checkpoint selection uses validation only; test scores must not guide subsequent training or model selection.
|
| 17 |
+
|
| 18 |
+
Uploads contain project-trained reader heads/adapters and, when applicable, project-trained retriever/selector weights, with configuration and SHA-256 provenance. They are not standalone Qwen models unless explicitly described as such. Base-model checkpoints, dataset images/text and third-party papers are not included in this initial release.
|
| 19 |
+
|
| 20 |
+
Each released run records the model, dataset, seed, selected epoch, evaluation scope and any required upstream dependencies. Controlled adaptations use a shared Qwen3-8B backbone and should not be interpreted as exact reproduction of every original paper's native setup.
|
| 21 |
+
|
| 22 |
+
The repository is public at the project owner's request. No credentials or private environment files belong in this repository.
|