agentlans/LinguaNova

---
configs:
- config_name: all
data_files:
- path:
- all.jsonl.zst
split: train
default: true
- config_name: ar
data_files:
- path:
- ar.jsonl.zst
split: train
- config_name: az
data_files:
- path:
- az.jsonl.zst
split: train
- config_name: bg
data_files:
- path:
- bg.jsonl.zst
split: train
- config_name: bn
data_files:
- path:
- bn.jsonl.zst
split: train
- config_name: ca
data_files:
- path:
- ca.jsonl.zst
split: train
- config_name: cs
data_files:
- path:
- cs.jsonl.zst
split: train
- config_name: da
data_files:
- path:
- da.jsonl.zst
split: train
- config_name: de
data_files:
- path:
- de.jsonl.zst
split: train
- config_name: el
data_files:
- path:
- el.jsonl.zst
split: train
- config_name: en
data_files:
- path:
- en.jsonl.zst
split: train
- config_name: es
data_files:
- path:
- es.jsonl.zst
split: train
- config_name: et
data_files:
- path:
- et.jsonl.zst
split: train
- config_name: fa
data_files:
- path:
- fa.jsonl.zst
split: train
- config_name: fi
data_files:
- path:
- fi.jsonl.zst
split: train
- config_name: fr
data_files:
- path:
- fr.jsonl.zst
split: train
- config_name: he
data_files:
- path:
- he.jsonl.zst
split: train
- config_name: hi
data_files:
- path:
- hi.jsonl.zst
split: train
- config_name: hu
data_files:
- path:
- hu.jsonl.zst
split: train
- config_name: hy
data_files:
- path:
- hy.jsonl.zst
split: train
- config_name: id
data_files:
- path:
- id.jsonl.zst
split: train
- config_name: is
data_files:
- path:
- is.jsonl.zst
split: train
- config_name: it
data_files:
- path:
- it.jsonl.zst
split: train
- config_name: ja
data_files:
- path:
- ja.jsonl.zst
split: train
- config_name: ka
data_files:
- path:
- ka.jsonl.zst
split: train
- config_name: kk
data_files:
- path:
- kk.jsonl.zst
split: train
- config_name: ko
data_files:
- path:
- ko.jsonl.zst
split: train
- config_name: lt
data_files:
- path:
- lt.jsonl.zst
split: train
- config_name: lv
data_files:
- path:
- lv.jsonl.zst
split: train
- config_name: mk
data_files:
- path:
- mk.jsonl.zst
split: train
- config_name: ml
data_files:
- path:
- ml.jsonl.zst
split: train
- config_name: mr
data_files:
- path:
- mr.jsonl.zst
split: train
- config_name: ne
data_files:
- path:
- ne.jsonl.zst
split: train
- config_name: nl
data_files:
- path:
- nl.jsonl.zst
split: train
- config_name: 'no'
data_files:
- path:
- no.jsonl.zst
split: train
- config_name: pl
data_files:
- path:
- pl.jsonl.zst
split: train
- config_name: pt
data_files:
- path:
- pt.jsonl.zst
split: train
- config_name: ro
data_files:
- path:
- ro.jsonl.zst
split: train
- config_name: ru
data_files:
- path:
- ru.jsonl.zst
split: train
- config_name: sk
data_files:
- path:
- sk.jsonl.zst
split: train
- config_name: sl
data_files:
- path:
- sl.jsonl.zst
split: train
- config_name: sq
data_files:
- path:
- sq.jsonl.zst
split: train
- config_name: sr
data_files:
- path:
- sr.jsonl.zst
split: train
- config_name: sv
data_files:
- path:
- sv.jsonl.zst
split: train
- config_name: ta
data_files:
- path:
- ta.jsonl.zst
split: train
- config_name: th
data_files:
- path:
- th.jsonl.zst
split: train
- config_name: tr
data_files:
- path:
- tr.jsonl.zst
split: train
- config_name: uk
data_files:
- path:
- uk.jsonl.zst
split: train
- config_name: ur
data_files:
- path:
- ur.jsonl.zst
split: train
- config_name: vi
data_files:
- path:
- vi.jsonl.zst
split: train
- config_name: zh
data_files:
- path:
- zh.jsonl.zst
split: train
---