booydar/RMT-Llama-3.2-1B-Instruct-2x1024-mem16-lora-smol_qa1-5-1_9-qa1-5-distill_1.0-1000_steps Updated 16 days ago • 8
booydar/RMT-Llama-3.2-1B-Instruct-2x1024-mem16-lora-smol_qa1-5-1_9-qa1-5-distill_1.0-1000_steps Updated 16 days ago • 8
booydar/RMT-Llama-3.2-1B-Instruct-2x1024-mem16-lora-dolly_qa1-5-1_9-qa1-5-distill_1.0-1000_steps Updated 16 days ago • 9
booydar/RMT-Llama-3.2-1B-Instruct-2x1024-mem16-lora-dolly_qa1-5-1_9-qa1-5-distill_1.0-1000_steps Updated 16 days ago • 9
LLM-Microscope: Uncovering the Hidden Role of Punctuation in Context Memory of Transformers Paper • 2502.15007 • Published 22 days ago • 162
Cramming 1568 Tokens into a Single Vector and Back Again: Exploring the Limits of Embedding Space Capacity Paper • 2502.13063 • Published 24 days ago • 67
Cramming 1568 Tokens into a Single Vector and Back Again: Exploring the Limits of Embedding Space Capacity Paper • 2502.13063 • Published 24 days ago • 67