Entities · Models
Llama-2-7B
6 articles tagged with this entity.
-
Optimizing LLM Inference: Fluid-Guided Online Scheduling with Memory Constraints
-
OrpQuant: Geometric Orthogonal Residual Projection for Multiplier-Free Power-of-Two Transformer Quantization
-
Understanding and Improving Noisy Embedding Techniques in Instruction Finetuning
-
Model Collapse as Cultural Evolution
-
Brain-LLM Alignment Tracks Training Data, Not Typology
-
Structural Sensitivity in Compressed Transformers: Relative Error Propagation and Layer Removal