EXAONE 3.5: Series of Large Language Models for Real-world Use Cases
It provides open-access models for research to address practical AI applications, but it is incremental as it builds on existing LLM frameworks.
The paper introduces EXAONE 3.5, a series of large language models (32B, 7.8B, 2.4B) designed for real-world use, achieving top scores in instruction following and long-context benchmarks and competitive results in general benchmarks.
This technical report introduces the EXAONE 3.5 instruction-tuned language models, developed and released by LG AI Research. The EXAONE 3.5 language models are offered in three configurations: 32B, 7.8B, and 2.4B. These models feature several standout capabilities: 1) exceptional instruction following capabilities in real-world scenarios, achieving the highest scores across seven benchmarks, 2) outstanding long-context comprehension, attaining the top performance in four benchmarks, and 3) competitive results compared to state-of-the-art open models of similar sizes across nine general benchmarks. The EXAONE 3.5 language models are open to anyone for research purposes and can be downloaded from https://huggingface.co/LGAI-EXAONE. For commercial use, please reach out to the official contact point of LG AI Research: contact_us@lgresearch.ai.