|
1
|
# TODO(rob): enable |
|
2
|
# model_name: "amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV" |
|
3
|
# accuracy_threshold: 0.62 |
|
4
|
# num_questions: 1319 |
|
5
|
# num_fewshot: 5 |
|
6
|
# server_args: "--enforce-eager --max-model-len 8192 --tensor-parallel-size 2 --moe-backend=flashinfer_cutlass" |