Downloads · 30 days
16
2% of all-time downloads
Eku127/swiftvln-satnav-3b-1ep-f32s4-overlap4-pf-h8-pool-s2-noembed
swiftvln-satnav-3b-1ep-f32s4-overlap4-pf-h8-pool-s2-noembed 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
16
2% of all-time downloads
All-time downloads
645
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 studies a sliding-window setup in which adjacent training windows overlap by four steps.
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 actionsoverlap4: adjacent training windows overlap by four stepspf-h8: uses per-frame memory with up to eight history framespool-s2: applies average pooling with stride 2noembed: uses no embedding enhancementResults reported in the SatNav paper, memory-design ablation, row Overlap turns (N_o = 2).
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) | 68.7 | 64.0 | 81.3 | +2.9 | +8.9 |
Test Unseen (val_unseen) | 56.8 | 53.7 | 70.1 | +3.1 | +6.0 |
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 a sliding-window ablation in the SwiftVLN SatNav Ablation Model Zoo.