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

65
examples/pipelines/all_configs/korOperationUnicode0033_test.json Executable file
View file

@ -0,0 +1,65 @@
[
{
"compute_prob": 0.4,
"max_square": 12,
"operand_range": [
3,
5
],
"max_depth": 3
},
{
"compute_prob": 0.5,
"max_square": 13,
"operand_range": [
1,
4
],
"max_depth": 2
},
{
"compute_prob": 0.7,
"max_square": 8,
"operand_range": [
2,
4
],
"max_depth": 2
},
{
"compute_prob": 0.8,
"max_square": 14,
"operand_range": [
3,
6
],
"max_depth": 3
},
{
"compute_prob": 0.1,
"max_square": 9,
"operand_range": [
2,
5
],
"max_depth": 1
},
{
"compute_prob": 0.9,
"max_square": 20,
"operand_range": [
2,
6
],
"max_depth": 3
},
{
"compute_prob": 0.3,
"max_square": 15,
"operand_range": [
1,
6
],
"max_depth": 2
}
]