| | --- |
| | license: apache-2.0 |
| | base_model: Qwen/Qwen3-VL-4B-Instruct |
| | tags: |
| | - reward_model |
| | - rfm |
| | - preference_comparisons |
| | library_name: transformers |
| | --- |
| | |
| | # rewardfm/libero_90_prog_pref_fail_4frames_fixdata |
| |
|
| | ## Model Details |
| |
|
| | - **Base Model**: Qwen/Qwen3-VL-4B-Instruct |
| | - **Model Type**: qwen3_vl |
| | |
| | ## Training Run |
| | |
| | - **Wandb Run**: [libero_ablation_prog_pref_fail_4frames_fixdata](https://wandb.ai/clvr/rfm/runs/gw667gsc) |
| | - **Wandb ID**: `gw667gsc` |
| | - **Project**: rfm |
| | - **Notes**: libero prog_pref_fail only |
| | |
| | ## Citation |
| | |
| | If you use this model, please cite: |
| | |
