rewardfm/libero_90_prog_pref_4frames_fixdata
Model Details
- Base Model: Qwen/Qwen3-VL-4B-Instruct
- Model Type: qwen3_vl
Training Run
- Wandb Run: libero_90_prog_pref_4frames_fixdata
- Wandb ID:
vyvzk21n - Project: rfm
- Notes: libero prog_pref_fail only
Citation
If you use this model, please cite:
- Downloads last month
- 29
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for rewardfm/libero_90_prog_pref_4frames_fixdata
Base model
Qwen/Qwen3-VL-4B-Instruct