Running
2
Monster-Code
🌿
Personal site for ML researcher Monster-Code
🧐 Are SDMs AGI?
Lightbender
Monster-Code
P(doom) Rejects the premise
AI & ML interests
@Lightbend
Recent Activity
liked a model about 5 hours ago
saicr/ACR-1.0 reacted to CountingSheep's post with 🔥 about 16 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. liked a Space about 19 hours ago
lmarena-ai/arena-leaderboardOrganizations
