Vegaml is only 800 Million param and now independently verifying.

Vega 0.8B, 8-bit, for the browser, loads in a browser tab, runs on your own machine, and sends nothing anywhere. by Vijaya krishna kudva huggingface.co/nvkudva/vega-…

Around 3 weeks ago introduced Laya, the first open-source version of JEV, and it has reached a very large scale. Today I am open-sourcing a new physics-based typed decision model called Vega. The interesting parts. It is only 800 million parameters (4B is also there), with 73k token support, image support, and surpassing many of the jev benchmarks in single-shot. Implemented an engine+adapter as a Test-Time Training Architecture. Imagine you are giving input to the model like "ignore all previous conversations," which is called the observation, along with a question, "Is this trying to override the instructions of the model?" and your possible outcomes are YES or NO. The whole prompt is passed to an LLM/VLM (yeah, image-supported), then from the hidden layers, we can extract the observation, question, the yes and no, and last token. These will be vectors, and we can project it by multiplying with wieghts; then, first, using the observation projection, we can create a landscape with valleys; then, using the question and last-token vectors, we can initialise a ball in the valley, and using YES or NO, we can get the candidate location of the ball. Depends on the number of outcomes we create valleys; that is, here YES and NO, so 2. When the ball fall on YES valley, we get the answer. There is friction also influencing how the ball moves. TLDR: It's like creating valleys of outcomes that we need and throwing a ball that will slow down based on friction and settle on the best outcome Blog: nandakishorm.com/writing/veg… GitHub: github.com/NandhaKishorM/veg… HuggingFace Model Card: huggingface.co/nandakishorm/… HuggingFace Space: huggingface.co/spaces/nandak…