Llama 2 7B
Emerging6papers using it
2025first seen
'LLaMA-2-7B' is a large language model used to evaluate the effectiveness of a tensor-structured compression scheme called Tensor Mixture (MixT) in preserving accuracy while reducing model parameters and computational overhead.
Papers using Llama 2 7B (5)
- SoLA: Leveraging Soft Activation Sparsity and Low-Rank Decomposition for Large Language Model CompressionA general tensor-structured compression scheme for efficient large language modelsAnchors in the Machine: Behavioral and Attributional Evidence of Anchoring Bias in LLMsFairy2i: Training Complex LLMs from Real LLMs with All Parameters in {pm 1, pm i}RoRA: Efficient Fine-Tuning of LLM with Reliability Optimization for
Rank Adaptation