GaleneAI/llama-3.1-nemoguard-8b-content-safety-merged-NVFP4
Quantization vs meta-llama/Llama-3.1-8B-Instruct. GaleneAI/llama-3.1-nemoguard-8b-content-safety-merged-NVFP4 is a quantized version of the other (F32/U8).
Quantization vs meta-llama/Llama-3.1-8B-Instruct. GaleneAI/llama-3.1-nemoguard-8b-content-safety-merged-NVFP4 is a quantized version of the other (F32/U8).