nvidia
/

DeepSeek-V4-Pro-NVFP4

Text Generation

Model Optimizer

8-bit precision

Model card Files Files and versions

DeepSeek-V4-Pro-NVFP4 / hf_quant_config.json

jingyux-nv's picture

Un-quantize MTP block (revert to native precision)

9e7e88e verified 2 days ago

history contribute delete

7.63 MB

File too large to display, you can check the raw version instead.