You Only Cache Once: Decoder-Decoder Architectures for Language Models
Paper
•
2405.05254
•
Published
•
9
Papers - BitNet
Additional paper with faq, code and tips on: https://github.com/microsoft/unilm/blob/master/bitnet/The-Era-of-1-bit-LLMs__Training_Tips_Code_FAQ.pdf
-
-
The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits
Paper • 2402.17764 • Published • 603 -
BitsFusion: 1.99 bits Weight Quantization of Diffusion Model
Paper • 2406.04333 • Published • 36 -
1-bit AI Infra: Part 1.1, Fast and Lossless BitNet b1.58 Inference on CPUs
Paper • 2410.16144 • Published • 2