Quick Links
aliangdw/qwen4b_pref_prog_succ_8_frames_all_part2
Model Details
- Base Model: Qwen/Qwen3-VL-4B-Instruct
- Model Type: qwen3_vl
Training Run
- Wandb Run: ant_rfm_qwen4b_4gpu_bs64_pref_prog_succ_8_frames_all_discrete_part2
- Wandb ID:
qcgqdioj - Project: rfm
- Notes: all run with prog_token per frame, qwen 4b, discrete progress, 32 bins
Citation
If you use this model, please cite:
- Downloads last month
- 19
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for aliangdw/qwen4b_pref_prog_succ_8_frames_all_part2
Base model
Qwen/Qwen3-VL-4B-Instruct
# Load model directly from transformers import AutoProcessor, RFM processor = AutoProcessor.from_pretrained("aliangdw/qwen4b_pref_prog_succ_8_frames_all_part2") model = RFM.from_pretrained("aliangdw/qwen4b_pref_prog_succ_8_frames_all_part2", device_map="auto")