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

78
examples/pipelines/all_configs/Cwetsharkandflowers_test.json Normal file
View file

@ -0,0 +1,78 @@
[
{
"n_min": 3,
"n_max": 20,
"p_primes": [
2,
3,
5,
7,
11,
13,
17,
19,
23,
29,
101,
1009,
10007,
100003,
1000003
],
"l_max": 1000000000000
},
{
"n_min": 5,
"n_max": 20,
"p_primes": [
2,
3,
5,
7,
11,
13,
17,
19,
23,
29,
101,
1009,
10007
],
"l_max": 10000000000
},
{
"n_min": 3,
"n_max": 15,
"p_primes": [
2,
3,
5,
7,
11,
13
],
"l_max": 1000000
},
{
"n_min": 4,
"n_max": 25,
"p_primes": [
2,
3,
5,
7,
11,
13,
17,
19,
23,
29,
101,
1009,
10007,
100003
],
"l_max": 100000000000
}
]