DJLougen
/

DeepSeek-Coder-V2-Lite-Instruct-NVFP4

Text Generation

4-bit precision

Mixture of Experts

Model card Files Files and versions

DeepSeek-Coder-V2-Lite-Instruct-NVFP4

9.44 GB

1 contributor

History: 2 commits

DJLougen's picture

Upload NV_FP4 quantized model

086284e verified 9 days ago