rewardfm/jesse-alldata-rfm-qwen-4gpu-bs16-pref-prog-sim-succ

Model Details

  • Base Model: Qwen/Qwen3-VL-4B-Instruct
  • Model Type: qwen3_vl

Training Run

Citation

If you use this model, please cite:

Downloads last month
71
Safetensors
Model size
4B params
Tensor type
BF16
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for rewardfm/jesse-alldata-rfm-qwen-4gpu-bs16-pref-prog-sim-succ

Finetuned
(123)
this model