6 lines
172 B
YAML
6 lines
172 B
YAML
model_name: "RedHatAI/Llama-3.2-1B-Instruct-quantized.w8a8"
|
|
accuracy_threshold: 0.31
|
|
num_questions: 1319
|
|
num_fewshot: 5
|
|
server_args: "--enforce-eager --max-model-len 4096"
|