view post Post 2394 Amazing work👏Introduces Dream 7B - a discrete diffusion reasoning model, fully opensourced with weights on 🤗- it outperforms existing non-autoregressive models and matches or beats frontier autoregressive of similar size on reasoning tasks. Models: - base: Dream-org/Dream-v0-Base-7B- SFT: Dream-org/Dream-v0-Instruct-7BCode: https://github.com/HKUNLP/DreamProject: https://hkunlp.github.io/blog/2025/dream/ See translation 1 reply · 🔥 8 8 + Reply
Running 2.68k 2.68k The Ultra-Scale Playbook 🌌 The ultimate guide to training LLM on large GPU Clusters