LoopRPT: Reinforcement Pre-Training for Looped Language Models Paper • 2603.19714 • Published 10 days ago • 13
view post Post Hi!We release a series of LLMs named GraphWiz https://huggingface.co/GraphWiz/, which is designed for solving different graph problems and outputs their CoT. GraphWiz has surpassed GPT-4 by a large margin in 9 tasks.Let us have a try! 👍 7 7 🚀 1 1 + Reply
GraphWiz: An Instruction-Following Language Model for Graph Problems Paper • 2402.16029 • Published Feb 25, 2024 • 3
Compress to Impress: Unleashing the Potential of Compressive Memory in Real-World Long-Term Conversations Paper • 2402.11975 • Published Feb 19, 2024 • 1
What would Harry say? Building Dialogue Agents for Characters in a Story Paper • 2211.06869 • Published Nov 13, 2022 • 1
Breaking Language Barriers in Multilingual Mathematical Reasoning: Insights and Observations Paper • 2310.20246 • Published Oct 31, 2023 • 1
Beyond Surface: Probing LLaMA Across Scales and Layers Paper • 2312.04333 • Published Dec 7, 2023 • 19