|
|
--- |
|
|
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_4frames_fixdata |
|
|
|
|
|
## Model Details |
|
|
|
|
|
- **Base Model**: Qwen/Qwen3-VL-4B-Instruct |
|
|
- **Model Type**: qwen3_vl |
|
|
|
|
|
## Training Run |
|
|
|
|
|
- **Wandb Run**: [libero_ablation_prog_pref_4frames_fixeddata](https://wandb.ai/clvr/rfm/runs/r7yk4zqg) |
|
|
- **Wandb ID**: `r7yk4zqg` |
|
|
- **Project**: rfm |
|
|
- **Notes**: libero prog only |
|
|
|
|
|
## Citation |
|
|
|
|
|
If you use this model, please cite: |
|
|
|
