amburger66's picture
LoRA fine-tune on RobotSmith task03 after fixing dataset
aea53cd verified
---
license: apache-2.0
base_model: Qwen/Qwen3-VL-4B-Instruct
tags:
- reward_model
- rbm
- preference_comparisons
library_name: transformers
---
# amburger66/robometer-4b-lora-robotsmith-task03
## Model Details
- **Base Model**: Qwen/Qwen3-VL-4B-Instruct
- **Model Type**: qwen3_vl
## Training Run
- **Wandb Run**: [lora_task03_data_fixed](https://wandb.ai/r-pad/rbm-finetune-robotsmith/runs/6ihsmc6l)
- **Wandb ID**: `6ihsmc6l`
- **Project**: rbm-finetune-robotsmith
- **Notes**: fine-tuning Robometer on RobotSmith
## Citation
If you use this model, please cite: