RegMix: Data Mixture as Regression for Language Model Pre-training Paper โข 2407.01492 โข Published Jul 1 โข 35
view article Article Introducing the Ultimate SEC LLM: Revolutionizing Financial Insights with Llama-3-70B By Crystalcareai โข Jun 19 โข 7
Contra (Bottleneck T5) Collection Text autoencoders capable of embedding and generating text in a fixed-size latent space, useful for embeddings and latent space text editing. โข 4 items โข Updated Oct 3, 2023 โข 27
Trained Models ๐๏ธ Collection They may be small, but they're training like giants! โข 8 items โข Updated 19 days ago โข 16