Qwen2.5 Collection Qwen2.5 language models, including pretrained and instruction-tuned models of 7 sizes, including 0.5B, 1.5B, 3B, 7B, 14B, 32B, and 72B. ā¢ 45 items ā¢ Updated Sep 18 ā¢ 382
From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline Paper ā¢ 2406.11939 ā¢ Published Jun 17 ā¢ 6
Principled Reinforcement Learning with Human Feedback from Pairwise or K-wise Comparisons Paper ā¢ 2301.11270 ā¢ Published Jan 26, 2023 ā¢ 2
Online Learning in Stackelberg Games with an Omniscient Follower Paper ā¢ 2301.11518 ā¢ Published Jan 27, 2023 ā¢ 1
On Optimal Caching and Model Multiplexing for Large Model Inference Paper ā¢ 2306.02003 ā¢ Published Jun 3, 2023 ā¢ 1
Fine-Tuning Language Models with Advantage-Induced Policy Alignment Paper ā¢ 2306.02231 ā¢ Published Jun 4, 2023 ā¢ 2