InternLM/InternBootcamp
1
0
Fork 0
mirror of https://github.com/InternLM/InternBootcamp.git synced 2026-04-19 12:58:04 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

pjli-dev

Browse source
This commit is contained in:
lipeiji 2025-06-12 12:45:31 +08:00
parent e5d5e53728
commit b379c541bf
11 changed files with 239 additions and 223 deletions
Download patch file Download diff file Expand all files Collapse all files

14
examples/verl_usage/verl_data_preprocess.py
View file

@ -91,17 +91,21 @@ def convert_to_parquet(src_jsonl, tgt_parquet, split, shuffle=True):
# 构造目标格式的数据结构
formatted_data = {
"data_source": 'bootcamp/' + data_source,
"prompt": [{
"role": "user",
"content": prompt
"prompt": [
{
"role": "system",
"content": "You are an expert reasoner with extensive experience in mathematical and code competitions. You approach problems through systematic thinking and rigorous reasoning. Your response should reflect deep understanding and precise logical thinking, making your solution path and reasoning clear to others. Please put your thinking process within <think>...</think> tags. After careful thought, present your final solution or answer clearly."
},
{
"role": "user",
"content": prompt
}],
"reward_model": {
"style": "rule",
"ground_truth": json.dumps(ground_truth, ensure_ascii=False)
},
"extra_info": {
'split': split, # 使用传入的 split 值
'index': idx
'index': str(idx), # modify this to make it consistent with current verl format
}
}