Attention Saturation and Gradient Suppression at Inflection Layers: Diagnosing and Mitigating Bottlenecks in Transformer Adaptation
"微调" 相关文章
FlashEVA: Accelerating LLM inference via Efficient Attention
Loquetier: A Virtualized Multi-LoRA Framework for Unified LLM Fine-tuning and Serving
综述238篇遥感微调！清华院士团队指出9大方向 | CVMJ
Defeating the Training-Inference Mismatch via FP16
苹果提出新型反向传播：一台iPhone 15 Pro Max就能微调LLM
苹果提出新型反向传播：一台iPhone 15 Pro Max就能微调LLM
Don't Blind Your VLA: Aligning Visual Representations for OOD Generalization
Preventing Catastrophic Forgetting: Behavior-Aware Sampling for Safer Language Model Fine-Tuning
Memory-Efficient Backpropagation for Fine-Tuning LLMs on Resource-Constrained Mobile Devices
$\alpha$-LoRA: Effective Fine-Tuning via Base Model Rescaling
PLAN: Proactive Low-Rank Allocation for Continual Learning
Compress to Impress: Efficient LLM Adaptation Using a Single Gradient Step on 100 Samples
QKCV Attention: Enhancing Time Series Forecasting with Static Categorical Embeddings for Both Lightweight and Pre-trained Foundation Models
Train an LLM on an NVIDIA Blackwell Desktop with Unsloth—and Scale It
LLM Training Data Optimization: Fine-Tuning, RLHF & Red Teaming
LLM Training Data Optimization: Fine-Tuning, RLHF & Red Teaming
Data Efficient Adaptation in Large Language Models via Continuous Low-Rank Fine-Tuning
Data Efficient Adaptation in Large Language Models via Continuous Low-Rank Fine-Tuning
Unraveling Emotions with Pre-Trained Models
