Downloads · 30 days
5
11% of all-time downloads
namhokaist/appgen-qwen3-vl-8b-sft-ngc-v1-frozen-ground2x-default-proven-lr5e7-1ep
appgen-qwen3-vl-8b-sft-ngc-v1-frozen-ground2x-default-proven-lr5e7-1ep is a image-text-to-text model from namhokaist. 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. The card lists the license as apache-2.0.
This is sweep arm ground2xdefault from a four-arm controlled SFT study for Android GUI use. The language model was fully fine-tuned while the complete Qwen3-VL visual tower, merger, and deep-stack mergers remained fro…
Downloads · 30 days
5
11% of all-time downloads
All-time downloads
45
Public
Parameters
8.8B
17.5 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors17.5 GB · 100%
From the Hugging Face model README
This is sweep arm ground2x_default from a four-arm controlled SFT study for
Android GUI use. The language model was fully fine-tuned while the complete
Qwen3-VL visual tower, merger, and deep-stack mergers remained frozen. The
uploaded weights were verified byte-for-byte against the pinned base for every
model.visual* tensor, while at least one language-model tensor was verified
to have changed.
Qwen/Qwen3-VL-8B-Instruct at commit 0c351dd01ed87e9c1b53cbc748cba10e6187ff3bluca0621/appgen-sft-ngc-v1, config ngc-f-qwen3-normalized, revision 769ea99dbc4ff190048ae0db37eb6310dba595e0grounding2x1879d231697554ca0960366e3db9f70a97180694b9638720c1158dd9f32e6c9bproven; SHA-256 67ff8adb0e78a617f3d0edcf196d4e4cc3239967a8c30619fc5afc14484ee8c05e-7, cosine schedule, 5% warmupdefault loss scale was used.Only the final checkpoint (checkpoint-125) is published in
this repository. The exact training system prompt is included as
appgen_system_prompt.txt; run_manifest.json records hashes and verification
evidence. Intermediate 25-step checkpoints remain local for controlled eval.
The images are synthetic AppGen HTML-to-PNG screenshots from 50 generated training environments. They are not real-user or real-device captures. The pinned dataset declares no AndroidWorld, held-out, or public grounding benchmark images. No AndroidWorld or real-world benchmark score is claimed in this card; evaluate all four arms under the same decoding and benchmark setup.
This model is for Android visual-agent research, not safety-critical autonomous deployment.