Power-LM Collection Dense & MoE LLMs trained with power learning rate scheduler. • 4 items • Updated 3 days ago • 15
Power Scheduler: A Batch Size and Token Number Agnostic Learning Rate Scheduler Paper • 2408.13359 • Published Aug 23 • 21
Octo-planner: On-device Language Model for Planner-Action Agents Paper • 2406.18082 • Published Jun 26 • 47
Efficient Continual Pre-training by Mitigating the Stability Gap Paper • 2406.14833 • Published Jun 21 • 19
Granite Code Models Collection A series of code models trained by IBM licensed under Apache 2.0 license. We release both the base pretrained and instruct models. • 23 items • Updated Aug 30 • 169
Aligning Large Multimodal Models with Factually Augmented RLHF Paper • 2309.14525 • Published Sep 25, 2023 • 29
The Consensus Game: Language Model Generation via Equilibrium Search Paper • 2310.09139 • Published Oct 13, 2023 • 12