23 lines
398 B
YAML
23 lines
398 B
YAML
|
api:
|
||
|
|
type: "qwen" # "qwen" or "openai"
|
||
|
|
model: "qwen-max"
|
||
|
|
|
||
|
|
generation:
|
||
|
|
total_samples: 3000
|
||
|
|
samples_per_category: 300
|
||
|
|
delay: 0.5 # seconds between API calls
|
||
|
|
|
||
|
|
output:
|
||
|
|
raw_dir: "data/raw"
|
||
|
|
output_file: "data/raw/generated.jsonl"
|
||
|
|
|
||
|
|
annotation:
|
||
|
|
judge_model: "qwen-max"
|
||
|
|
output_file: "data/processed/annotated.jsonl"
|
||
|
|
|
||
|
|
split:
|
||
|
|
train: 0.8
|
||
|
|
val: 0.1
|
||
|
|
test: 0.1
|
||
|
|
seed: 42
|