OpenVINO-Llama
Collection
7 items
•
Updated
This model was converted to the OpenVINO IR format using the following command:
optimum-cli export openvino -m "input/path" --task text-generation-with-past --weight-format int4 --ratio 1 --group-size 128 --dataset wikitext2 --awq --scale-estimation --sensitivity-metric weight_quantization_error "output/path"
Base model
lolzinventor/Meta-Llama-3.1-8B-SurviveV3