Instructions to use xju-arlab/vbench-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use xju-arlab/vbench-model with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
|
Download multiple_objects/README.md from xju-arlab/vbench-model: direct link, hf CLI and curl.
- Browser
- Download file 665 Bytes
-
https://huggingface.co/xju-arlab/vbench-model/resolve/main/multiple_objects/README.md
- Command line
-
hf download hf://xju-arlab/vbench-model/multiple_objects/README.md
-
curl -L -o README.md https://huggingface.co/xju-arlab/vbench-model/resolve/main/multiple_objects/README.md
665 Bytes
| # multiple_objects | |
| v6-8b, step 900; best retained checkpoint by the recorded 24-example development exact-match probe (0.916667). Ties use the latest step. | |
| Weights are byte-identical to the selected training artifact. The portable adapter configuration points to Qwen/Qwen3-8B at the revision in selection.json; the original adapter configuration is preserved separately. The frozen base model is not duplicated. | |
| These adapters require the task schemas and deterministic postprocessing from vbench-prompts-compile. Raw LoRA output alone does not reproduce the complete repaired metric. Development scores use a small probe and are not an independent test claim. | |