Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs Paper • 2412.21187 • Published 8 days ago • 27
NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models Paper • 2405.17428 • Published May 27, 2024 • 17
PreferenceShareGPT Collection Preference datasets converted to use a custom "ShareGPT-like" format. https://gist.github.com/xzuyn/87097972ab2323ced81e4d7b41c47a45 • 48 items • Updated Aug 8, 2024 • 1
PJMixers/tatsu-lab_alpaca_farm_human_preference-PreferenceShareGPT Viewer • Updated May 30, 2024 • 3.8k • 35 • 2