17 lines
387 B
YAML
17 lines
387 B
YAML
|
model_name: "vllm-ascend/Qwen3-30B-A3B-W8A8"
|
||
|
|
hardware: "Atlas A2 Series"
|
||
|
|
tasks:
|
||
|
|
- name: "gsm8k"
|
||
|
|
metrics:
|
||
|
|
- name: "exact_match,strict-match"
|
||
|
|
value: 0.9
|
||
|
|
- name: "exact_match,flexible-extract"
|
||
|
|
value: 0.8
|
||
|
|
num_fewshot: 5
|
||
|
|
gpu_memory_utilization: 0.7
|
||
|
|
enable_expert_parallel: True
|
||
|
|
tensor_parallel_size: 2
|
||
|
|
apply_chat_template: False
|
||
|
|
fewshot_as_multiturn: False
|
||
|
|
quantization: ascend
|