CountingSheep/vev-9b
Image-Text-to-Text • 9B • Updated • 87 • 1
Wang Xiaolong PRO
CountingSheep
AI & ML interests
Large Language Model
Recent Activity
reacted to theirpost with 🔥 about 24 hours ago
Vev: Jev-style decisions about images, from a 4B or 9B model you can run yourself.
Give it a screenshot or photo plus a yes/no, multiple-choice, or scoring question, and it returns a probability for every option instead of generating text.
It serves TypeSafe's `/v1/systemone` format, so the official SDK works by changing the base URL, including requests with images.
The clip shows `vev-4b` playing Doom in real time. On each look, the image is split into 8 vertical slices, and Vev answers 8 yes/no questions in a single request, one per slice. A small fixed-rule harness turns those probabilities into turning and firing.
Try it in the browser:
https://huggingface.co/spaces/CountingSheep/vev
Weights:
https://huggingface.co/CountingSheep/vev-4b
https://huggingface.co/CountingSheep/vev-9b
LoRA adapters are also available in the collection.
Code:
https://github.com/Xiaooolong/vev
Fine-tuned from Qwen3.5. Tested on NVIDIA GPUs so far. updated a model 2 days ago
CountingSheep/vev-9b-lora updated a model 2 days ago
CountingSheep/vev-9bOrganizations
liked 2
models 6 days ago
liked 2
datasets over 2 years ago