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

38
examples/pipelines/all_configs/Fencoding_train.json Normal file
View file

@ -0,0 +1,38 @@
[
{
"min_s_length": 5,
"max_s_length": 20,
"max_t_ratio": 0.5,
"pair_prob": 0.3
},
{
"min_s_length": 5,
"max_s_length": 20,
"max_t_ratio": 0.7,
"pair_prob": 0.5
},
{
"min_s_length": 5,
"max_s_length": 15,
"max_t_ratio": 0.4,
"pair_prob": 0.2
},
{
"min_s_length": 5,
"max_s_length": 20,
"max_t_ratio": 0.4,
"pair_prob": 0.25
},
{
"min_s_length": 5,
"max_s_length": 20,
"max_t_ratio": 0.3,
"pair_prob": 0.2
},
{
"min_s_length": 5,
"max_s_length": 25,
"max_t_ratio": 0.6,
"pair_prob": 0.5
}
]