Usage
# pip install "transformers>=5.12" "peft>=0.19.1" qwen-vl-utilsimport torchfrom transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessorfrom peft import PeftModel base = "OpenGVLab/VideoChat-R1_7B"model = Qwen2_5_VLForConditionalGeneration.from_pretrained(base, torch_dtype=torch.bfloat16, device_map="auto")processor = AutoProcessor.from_pretrained(base)model = PeftModel.from_pretrained(model, "iclropen/evidence-audit-videochatr1-7b-sft-textfirst-s0")
The evaluation and audit scripts of the code repository take --model <base> --adapter <this repository or folder>.
Training
Supervised fine-tuning with the same trainer and data as the placebo-controlled models: the answer likelihood only, with the margin terms switched off.
Table with columns: Setting, Value| Setting | Value |
|---|
| Training pairs | 2,400 from the Charades-STA training split |
| Optimizer steps | 300 |
| Gradient accumulation | 8 |
| Learning rate | 5e-6 |
| Seed | 0 |
| LoRA | r=16, alpha=32, dropout 0.05, on q/k/v/o and gate/up/down projections |
| Video input | 2 fps, at most 768 frames |
| Prompt template | vchat |
| Message order | text first, then video |
| Trainer | code/27_papo_train_qcdro_v3seln_r5.py |
Citation
Anonymous. Accuracy Is Not Evidence: Measuring and Training Evidence Dependence in Video Temporal Grounding. ICLR 2027 submission, under review.