Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters Paper • 2408.03314 • Published Aug 6 • 33
Improving Text Embeddings for Smaller Language Models Using Contrastive Fine-tuning Paper • 2408.00690 • Published Aug 1 • 23
Small LMs Text Embedding Collection Contrastive fine-tuned version of Language Models up to 2B parameters using LoRA • 3 items • Updated May 8 • 4