6 lines
176 B
YAML
6 lines
176 B
YAML
model_name: "nm-testing/Qwen1.5-MoE-A2.7B-Chat-quantized.w4a16"
|
|
accuracy_threshold: 0.45
|
|
num_questions: 1319
|
|
num_fewshot: 5
|
|
server_args: "--enforce-eager --max-model-len 4096"
|