Creator livestreams first post-training run, aims to open-source a multimodal model

AlchainHust · x · 2026-09-24

Creator Alchain is publicly livestreaming his first post-training attempt: building an open-source model with real multimodal capability that beats Jev on basic text classification. Training is expected to finish by tomorrow, with the model released on Hugging Face and GitHub regardless of outcome.

Original post →

More from Models

Models channel →