Llama-3.1

Llama-3.1 is a benchmark dataset used to evaluate the performance of large language models and vision-language models, particularly in the context of their computational efficiency and accuracy during inference.

Papers using Llama-3.1 (6)

Improving Quantized Model Performance in Qualitative Analysis with Multi-Pass Prompt Verification2026POP: Prefill-Only Pruning for Efficient Large Model Inference2026SCAN: Sparse Circuit Anchor Interpretable Neuron for Lifelong Knowledge Editing2026Garbage Attention in Large Language Models: BOS Sink Heads and Sink-aware Pruning2026Decomposing MLP Activations into Interpretable Features via Semi-Nonnegative Matrix Factorization2025Precise In-Parameter Concept Erasure in Large Language Models2025