DeepSeek-Coder-V2-Lite-Instruct-FP8 is a lightweight, quantized version of the DeepSeek-Coder-V2 model optimized for code generation and instruction following. Hosted on Hugging Face, it allows developers to run the model locally or via inference providers with significantly reduced memory footprint thanks to FP8 quantization. It supports standard Transformers pipelines and is intended for software development assistance and code completion tasks.
DeepSeek Coder V2 Lite Instruct sits in PulseGate's Coding AI & assistants category. It focuses on running large code models locally with reduced memory requirements. DeepSeek Coder V2 Lite Instruct is an open-source project aimed at developers. DeepSeek Coder V2 Lite Instruct is open source under the MIT license. It ships for the web, the command line, and API.
Behind DeepSeek Coder V2 Lite Instruct is RedHatAI, and it first shipped in 2024. The project is developed in the open on GitHub with 6.9k stars. PulseGate's similarity index places it among 6 comparable projects. Key capabilities include Code Generation, Instruction Following, and FP8 Quantization.
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