DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence Paper • 2401.14196 • Published Jan 25 • 47
The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits Paper • 2402.17764 • Published Feb 27 • 604
INT4/8 Quantized Whisper CT2 Collection Int4/8 Quantized Whisper Models by using the quanto package and the CTranslate2 package. Requires (much) less GPU resources while keeping performance. • 4 items • Updated Mar 19 • 2
FinTral: A Family of GPT-4 Level Multimodal Financial Large Language Models Paper • 2402.10986 • Published Feb 16 • 77