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

refactor(data_pipeline): optimize data generation pipeline; add multiple preset configurations for data generation

Browse source
This commit is contained in:
chenyongkang 2025-08-26 18:40:21 +08:00
parent 1a8477c8d8
commit 8d493b35a0
2160 changed files with 69199 additions and 154 deletions
Download patch file Download diff file Expand all files Collapse all files

42
examples/pipelines/all_configs/Cbeaver_test.json Normal file
View file

@ -0,0 +1,42 @@
[
{
"s_min_length": 10,
"s_max_length": 50,
"target_min_len": 3,
"target_max_len": 10,
"boring_count": 3,
"boring_substr_min_len": 1,
"boring_substr_max_len": 3,
"special_case_prob": 0.1
},
{
"s_min_length": 50,
"s_max_length": 200,
"target_min_len": 6,
"target_max_len": 30,
"boring_count": 9,
"boring_substr_min_len": 3,
"boring_substr_max_len": 6,
"special_case_prob": 0.3
},
{
"s_min_length": 15,
"s_max_length": 80,
"target_min_len": 4,
"target_max_len": 15,
"boring_count": 5,
"boring_substr_min_len": 1,
"boring_substr_max_len": 4,
"special_case_prob": 0.25
},
{
"s_min_length": 25,
"s_max_length": 75,
"target_min_len": 5,
"target_max_len": 20,
"boring_count": 4,
"boring_substr_min_len": 1,
"boring_substr_max_len": 5,
"special_case_prob": 0.2
}
]