EXAONE-3.5-2.4B-Instruct-AWQ
EXAONE models, optimized for resource-constrained devices, offer advanced long-context understanding in English and Korean, supporting up to 32K tokens.
What is EXAONE-3.5-2.4B-Instruct-AWQ?
EXAONE-3.5-2.4B-Instruct-AWQ is a series of bilingual instruction-tuned models developed by LG AI Research. These models support long context processing up to 32K tokens and are optimized for deployment on resource-constrained devices. They offer advanced performance in handling long texts and multilingual tasks, with support for English and Korean. The AWQ quantization technique enables efficient deployment while maintaining high accuracy.