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.
In the Coding AI & assistants space, DeepSeek Coder V2 Lite Instruct takes a focused approach. It focuses on running large code models locally with reduced memory requirements. It is built as an open-source project for developers. DeepSeek Coder V2 Lite Instruct is open source under the MIT license. DeepSeek Coder V2 Lite Instruct is available on the web, the command line, and API.
It is developed by RedHatAI, and the product first shipped in 2024. Development happens publicly on GitHub with 6.9k stars. It operates in a well-populated space: PulseGate tracks 6 similar tools. Key capabilities include Code Generation, Instruction Following, and FP8 Quantization.
Latest indexed changes and source events
RedHatAI/DeepSeek-Coder-V2-Lite-Instruct-FP8 verified by the PulseGate indexer
Other apps tracked under the same category.
