EXAONE-3.5-7.8B-Instruct is a 7.8 billion parameter transformer model developed by LG AI Research. It is instruction-tuned for conversational use, text generation, and following user prompts. The model is fully open-weight, available on Hugging Face with support for Transformers, vLLM, and custom code, enabling local inference, fine-tuning, and integration into developer applications.
EXAONE 3.5 7.8B Instruct is a Foundation models & chat project. It focuses on running and fine-tuning a capable open-weight instruction-tuned language model locally or in custom environments without relying on proprietary APIs. It is built as an open-source project for developers. The project is open source (Open Source). It ships for the web, the command line, and API.
It is developed by LG AI Research (South Korea), and it first shipped in 2024. Development happens publicly on GitHub with 209 stars. Among its 5 catalogued features are Text Generation, Instruction Following, and Conversational AI.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do