Downloads · 30 days
0
manihani4/portal-vlm-qwen3vl-ported
portal-vlm-qwen3vl-ported is a machine learning model from manihani4. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
Same-family converter-only port: qwen25vl-hypernet with a fresh Qwen3-VL converter refit on ~1k calibration examples; latent and core frozen.
Downloads · 30 days
0
Access
Public
Updated Aug 2, 2026
Repo size
686 MB
Likes
0
Public
Click a slice to open those files.
.pt686 MB · 100%
From the Hugging Face model README
Same-family converter-only port: qwen25vl-hypernet with a fresh Qwen3-VL converter refit on ~1k calibration examples; latent and core frozen.
Part of the portal-vlm release - an independent replication of Ramp Labs' PorTAL (portable task adapters via hypernet-generated LoRA) extended to vision-language models on GUI grounding.
| ScreenSpot-v2 overall | web split | |
|---|---|---|
| this artifact | 91.4% | 88.3% |
Qwen/Qwen3-VL-4B-Instruct @ ebb281ec70b05090aa6165b016eac8ec08e71b17configs/qwen3vl_ported.yamlresults/qwen3vl_ported.jsongit clone https://github.com/robbym-dev/portal-vlm && cd portal-vlm && uv sync
uv run python scripts/eval.py --config configs/qwen3vl_ported.yaml --adapter hf:manihani4/portal-vlm-qwen3vl-ported
hypernet.pt is a PorTAL hypernet checkpoint (task latent + decoder core + per-base converters), not a PEFT adapter: at eval time the hypernet generates r8 LoRA factors for the target base, which scripts/eval.py injects on the fly.