Running on CPU Upgrade 1.91k 1.91k The Smol Training Playbook: The Secrets to Building World-Class LLMs 📝 Explore loss curves for training LLMs
Apertus LLM Collection Democratizing Open and Compliant LLMs for Global Language Environments: 8B and 70B open-data open-weights models, multilingual in >1000 languages • 4 items • Updated Oct 1 • 298
Harnessing Shared Relations via Multimodal Mixup Contrastive Learning for Multimodal Classification Paper • 2409.17777 • Published Sep 26, 2024 • 1
Fed-SB: A Silver Bullet for Extreme Communication Efficiency and Performance in (Private) Federated LoRA Fine-Tuning Paper • 2502.15436 • Published Feb 21 • 1
Regularization-based Framework for Quantization-, Fault- and Variability-Aware Training Paper • 2503.01297 • Published Mar 3 • 1
Initialization using Update Approximation is a Silver Bullet for Extremely Efficient Low-Rank Fine-Tuning Paper • 2411.19557 • Published Nov 29, 2024 • 1
FedEx-LoRA: Exact Aggregation for Federated and Efficient Fine-Tuning of Foundation Models Paper • 2410.09432 • Published Oct 12, 2024 • 1
ABBA: Highly Expressive Hadamard Product Adaptation for Large Language Models Paper • 2505.14238 • Published May 20 • 4