Made with https://github.com/neuralmagic/AutoFP8:

python quantize.py --model-id facebook/opt-125m --save-dir opt-125m-fp8-dynamic --activation-scheme dynamic
Downloads last month
7
Safetensors
Model size
125M params
Tensor type
FP16
·
F8_E4M3
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.