piotrkosecki
/

Naive-N0.5-Flash-NVFP4

Text Generation

naive_n05_flash

mixture-of-experts

8-bit precision

Model card Files Files and versions

Naive-N0.5-Flash-NVFP4 / runtime /requirements.txt

piotrkosecki's picture

Add tested native vLLM TP4 runtime, RTX PRO instructions and validation

36e36f3 verified 16 days ago

Raw History Blame Contribute Delete

177 Bytes

	# Install into an isolated target over the pinned CUDA/PyTorch base image.
	transformers==5.17.0
	accelerate==1.15.0
	tokenizers==0.23.2
	huggingface-hub==1.33.0
	safetensors==0.8.0