Downloads · 30 days
15
2% of all-time downloads
Eku127/swiftvln-satnav-3b-1ep-f32s4-overlap0-pf-h8-pool-s2-posefilm
swiftvln-satnav-3b-1ep-f32s4-overlap0-pf-h8-pool-s2-posefilm is a image-text-to-text model from Eku127. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers.
- SwiftVLN: training and evaluation code for these checkpoints. - SatNav: satellite-image navigation environments, datasets, and evaluation tools.
Downloads · 30 days
15
2% of all-time downloads
All-time downloads
717
Public
Parameters
3.8B
8.1 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors8.1 GB · 100%
From the Hugging Face model README
This checkpoint is designed for SwiftVLN on SatNav, the continuous-state vision-and-language navigation benchmark over satellite imagery. It augments visual tokens with relative pose through feature-wise linear modulation.
Qwen/Qwen2.5-VL-3B-Instruct2e-5swiftvln-satnav: SwiftVLN trained and evaluated on SatNav3b: Qwen2.5-VL 3B backbone1ep: trained for one epochf32s4: uses a 32-frame window and predicts four actionsoverlap0: uses non-overlapping training windowspf-h8-pool-s2: uses the reference per-frame memory configurationposefilm: injects relative pose into visual tokens with FiLMResults reported in the SatNav paper, memory-design ablation, row Relative pose.
SR, SPL, and OS are percentages. Changes in SR and OS are percentage points relative to the SwiftVLN reference model.
| Split | SR (%) | SPL (%) | OS (%) | Delta SR (pp) | Delta OS (pp) |
|---|---|---|---|---|---|
Test Seen (val_seen) | 67.8 | 67.5 | 76.3 | +2.0 | +3.9 |
Test Unseen (val_unseen) | 55.4 | 55.2 | 65.0 | +1.7 | +0.9 |
Use this checkpoint with the SwiftVLN evaluation guide. Keep the full repository name unchanged because SwiftVLN derives the evaluation configuration from it.
This checkpoint is an input-augmentation ablation in the SwiftVLN SatNav Ablation Model Zoo.