MoEITS is an information-theoretic algorithm for pruning experts in MoE-LLMs that produces models with higher accuracy and greater size reduction than prior state-of-the-art methods on Mixtral 8x7B, Qwen1.5-2.7B, and DeepSeek-V2-Lite.
Title resolution pending
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
Pre-trained MoE models exhibit up to 90% intra-expert activation sparsity that enables up to 2.5x faster MoE layer execution when exploited in the vLLM inference system.
Agent Q integrates MCTS-guided search, self-critique, and off-policy DPO to train LLM agents that outperform behavior cloning and reinforced fine-tuning baselines in WebShop and achieve up to 95.4% success in real-world booking scenarios.
FineWeb is a curated 15T-token web dataset that produces stronger LLMs than prior open collections, while its educational subset sharply improves performance on MMLU and ARC benchmarks.
The paper compiles practical lessons on reproducible LM evaluation and introduces the lm-eval library to mitigate common methodological problems in NLP.
citing papers explorer
-
MoEITS: A Green AI approach for simplifying MoE-LLMs
MoEITS is an information-theoretic algorithm for pruning experts in MoE-LLMs that produces models with higher accuracy and greater size reduction than prior state-of-the-art methods on Mixtral 8x7B, Qwen1.5-2.7B, and DeepSeek-V2-Lite.
-
Uncovering Intra-expert Activation Sparsity for Efficient Mixture-of-Expert Model Execution
Pre-trained MoE models exhibit up to 90% intra-expert activation sparsity that enables up to 2.5x faster MoE layer execution when exploited in the vLLM inference system.
-
Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents
Agent Q integrates MCTS-guided search, self-critique, and off-policy DPO to train LLM agents that outperform behavior cloning and reinforced fine-tuning baselines in WebShop and achieve up to 95.4% success in real-world booking scenarios.
-
The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale
FineWeb is a curated 15T-token web dataset that produces stronger LLMs than prior open collections, while its educational subset sharply improves performance on MMLU and ARC benchmarks.
-
Lessons from the Trenches on Reproducible Evaluation of Language Models
The paper compiles practical lessons on reproducible LM evaluation and introduces the lm-eval library to mitigate common methodological problems in NLP.