BitsExplorer

BitsExplorer finds what people are building with AI, every day. See today's picks →

Preview of Weak To Strong Alignment

Weak To Strong Alignment

We train a small Reward Model Qwen2.5-0.5B-Instruct to align/steer Qwen2.5-1.5B-Instruct on HH-RLHF dataset.

Description excerpted from the original listing, which is linked below.

Open it Source code

The week in AI-built software

Every Monday: how many projects were built with AI that week, which tools built them, where they came from, and the week's picks.

Read the latest week