😀 ¯\_( ͡° ͜ʖ ͡°)_/¯
OpenEngineer
Monster-Code
AI & ML interests
I like to train models on free compute.
Recent Activity
updated a model about 7 hours ago
Monster-Code/Merlin-600M reacted to CountingSheep's post with 🔥 about 8 hours ago
I've released vev-4b-v2, an updated version of Vev, my open-weight model for making decisions from text and images.
On the Jev Decision Index vision leaderboard (November 12 snapshot):
- 64.80 Full score (including private evaluations)
- 🥇 #1 among ≤5B entries listed as LoRA-trained
vev-4b-v2 is based on Qwen3.5-4B, fine-tuned with LoRA while keeping the vision encoder frozen.
Vev returns probabilities for yes/no, multiple-choice, and scoring questions. It supports text, JSON, and images through a Jev-compatible API.
Model: https://huggingface.co/CountingSheep/vev-4b-v2
Demo: https://huggingface.co/spaces/CountingSheep/vev
Code: https://github.com/Xiaooolong/vev
Leaderboard: https://huggingface.co/spaces/multimodalart/jev-decision-index
Feedback and comparisons are welcome!