appvoid's picture

appvoid

appvoid

·

https://ko-fi.com/appvoid

AI & ML interests

Working on symbolic models

Recent Activity

liked a model about 8 hours ago

Eclipse-Senpai/KeyLM-75M

posted an update 3 days ago

As an advocate for small language models I just want to say. It might not actually be the end for small models. We are just getting started! Now that we have super good models we can find creative ways to replicate the behavior at small scale! I'll show you in a few weeks what a small model is capable of, you will surprised.

repliedto codelion's post 3 days ago

Inspired by the Nemotron Diffusion recipe, check out dhara-250m: a 250M experimental language model that supports three decoding modes from one set of weights: autoregressive, block-diffusion, and self-speculation. It is small, easy to try, and meant for exploring diffusion-style decoding and latency tradeoffs in compact LMs. Model: https://huggingface.co/codelion/dhara-250m Try the chat demo here: https://huggingface.co/spaces/codelion/dhara-chat

View all activity

Organizations

appvoid 's Spaces 2

Meta Arena

testing fewshot learning at small scale

carbono

web app to showcase carbono's simplicity and accesibility