14 lines
262 B
YAML
14 lines
262 B
YAML
|
model_name: "Qwen/Qwen3-8B-Base"
|
||
|
|
tasks:
|
||
|
|
- name: "gsm8k"
|
||
|
|
metrics:
|
||
|
|
- name: "exact_match,strict-match"
|
||
|
|
value: 0.82
|
||
|
|
- name: "exact_match,flexible-extract"
|
||
|
|
value: 0.83
|
||
|
|
- name: "ceval-valid"
|
||
|
|
metrics:
|
||
|
|
- name: "acc,none"
|
||
|
|
value: 0.82
|
||
|
|
num_fewshot: 5
|