Instructions to use sdzt/ForgeLoc-R1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use sdzt/ForgeLoc-R1 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("sdzt/ForgeLoc-R1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| license: apache-2.0 | |
| base_model: Qwen/Qwen2.5-VL-7B-Instruct | |
| pipeline_tag: video-text-to-text | |
| library_name: transformers | |
| tags: | |
| - temporal-forgery-localization | |
| - video-forensics | |
| - grpo | |
| # ForgeLoc-R1 checkpoints | |
| Qwen2.5-VL-7B-Instruct fine-tuned with GRPO to localize the manipulated segments of a video. | |
| Every folder holds a full checkpoint in Hugging Face format. | |
| | Folder | Model | Training data | Test mIoU (%) | | |
| |---|---|---|---| | |
| | `af` | ForgeLoc-R1 | ActivityForensics | 64.27 | | |
| | `ddl` | ForgeLoc-R1 | DDL | 53.03 | | |
| | `baselines/af_grpo` | GRPO | ActivityForensics | 51.28 | | |
| | `baselines/af_video-r1` | Video-R1 | ActivityForensics | 54.29 | | |
| | `baselines/af_tempsamp-r1` | TempSamp-R1 | ActivityForensics | 59.93 | | |
| | `baselines/ddl_grpo` | GRPO | DDL | 31.89 | | |
| | `baselines/ddl_video-r1` | Video-R1 | DDL | 33.25 | | |
| | `baselines/ddl_tempsamp-r1` | TempSamp-R1 | DDL | 50.92 | | |
| | `ablations/af_noanchor` | without anchor injection | ActivityForensics | 58.61 | | |
| | `ablations/af_noprune` | without advantage pruning | ActivityForensics | 62.05 | | |
| | `ablations/af_noos` | without count balancing (m=1) | ActivityForensics | 59.53 | | |
| | `ablations/af_notransform` | without the asymmetric advantage transform | ActivityForensics | 62.90 | | |
| | `ablations/af_bestoverlap` | set term replaced by the best-overlap soft F1 | ActivityForensics | 65.35 | | |
| | `ablations/af_g16` | G'=16 | ActivityForensics | 63.53 | | |
| | `ablations/af_eps0.01` | Sinkhorn coefficient 0.01 | ActivityForensics | 63.49 | | |
| | `ablations/af_seed7` | ForgeLoc-R1, seed 7 | ActivityForensics | 63.27 | | |
| | `ablations/ddl_noos` | without count balancing (m=1) | DDL | 50.17 | | |
| mIoU is measured on the test splits: 1,565 ActivityForensics videos and 1,500 DDL videos. | |
| ```python | |
| from transformers import AutoProcessor, Qwen2_5_VLForConditionalGeneration | |
| model = Qwen2_5_VLForConditionalGeneration.from_pretrained( | |
| "sdzt/ForgeLoc-R1", subfolder="af", torch_dtype="bfloat16", device_map="auto" | |
| ) | |
| processor = AutoProcessor.from_pretrained("sdzt/ForgeLoc-R1", subfolder="af") | |
| ``` | |