datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
russian-colloquial-sft-50k
Russian colloquial SFT (50k, mat-free)
English: ~50,000 chat SFT examples: rewrite formal Russian into casual Telegram-style Russian without profanity.
Format
Each line is JSON with a messages array (ShareGPT / TRL):
{
"messages": [
{
"role": "user",
"content": "Перепиши простым разговорным русским, как в переписке. Без мата и грубости. Сохрани смысл:\n<формальный текст>"
},
{
"role": "assistant",
"content": "<разговорный ответ>"… See the full description on the dataset page: https://huggingface.co/datasets/pavelfedortsov/russian-colloquial-sft-50k.english-to-colloquial-tamil
English to Colloquial Tamil
"instruction":"Translate provided English text into colloquial Tamil."
"input": "Their players played well."
"output": "அவங்க players நல்லா விளையாண்டாங்க."