inf.sh

python benchmarks/benchmark_generation_mamba_simple.py --model-name "/public/mamba-2.2.2/AI-ModelScope/mamba-130m-hf" --prompt "My cat wrote all this CUDA code for a new language model and" --topp 0.9 --temperature 0.7 --repetition-penalty 1.2

python benchmarks/benchmark_generation_mamba_simple.py --model-name "/public/mamba-2.2.2/AI-ModelScope/mamba-130m-hf" --batch 64