| --- |
| license: apache-2.0 |
| language: |
| - cs |
| - de |
| - el |
| - es |
| - fr |
| - it |
| - nl |
| - pl |
| - pt |
| - ro |
| - uk |
| task_categories: |
| - text-generation |
| size_categories: |
| - 1M<n<10M |
| tags: |
| - synthetic |
| - instruction-following |
| - multilingual |
| pretty_name: EU Instruct Synthetic |
| configs: |
| - config_name: all |
| data_files: "*/train.parquet" |
| default: true |
| - config_name: cs |
| data_files: cs/train.parquet |
| - config_name: de |
| data_files: de/train.parquet |
| - config_name: el |
| data_files: el/train.parquet |
| - config_name: es |
| data_files: es/train.parquet |
| - config_name: fr |
| data_files: fr/train.parquet |
| - config_name: it |
| data_files: it/train.parquet |
| - config_name: nl |
| data_files: nl/train.parquet |
| - config_name: pl |
| data_files: pl/train.parquet |
| - config_name: pt |
| data_files: pt/train.parquet |
| - config_name: ro |
| data_files: ro/train.parquet |
| - config_name: uk |
| data_files: uk/train.parquet |
| --- |
| |
| # EU Instruct Synthetic |
|
|
| Synthetically generated **instruction-following** SFT data for 11 European |
| languages. Each example is a single-turn chat (`messages`: a user instruction |
| and an assistant response) with a `language` field. |
|
|
| This is the synthetic counterpart to |
| [`openeurollm/Dolci-Instruct-SFT-translated`](https://huggingface.co/datasets/openeurollm/Dolci-Instruct-SFT-translated). |
|
|
| ## Languages and sizes |
|
|
| | Code | Language | Examples | |
| |------|----------|---------:| |
| | cs | Czech | 150,129 | |
| | de | German | 135,786 | |
| | el | Greek | 138,048 | |
| | es | Spanish | 132,736 | |
| | fr | French | 119,497 | |
| | it | Italian | 136,407 | |
| | nl | Dutch | 131,515 | |
| | pl | Polish | 146,247 | |
| | pt | Portuguese | 131,707 | |
| | ro | Romanian | 129,112 | |
| | uk | Ukrainian | 146,092 | |
| | **Total** | | **1,497,276** | |
|
|
| ## Usage |
|
|
| ```python |
| from datasets import load_dataset |
| |
| # a single language |
| es = load_dataset("openeurollm/EU-Instruct-Synthetic", "es") |
| |
| # all languages combined (default config) |
| ds = load_dataset("openeurollm/EU-Instruct-Synthetic") |
| ``` |
|
|
| ## Format |
|
|
| Each row: |
|
|
| ```json |
| {"messages": [{"role": "user", "content": "..."}, |
| {"role": "assistant", "content": "..."}], |
| "language": "es"} |
| ``` |
|
|
| ## Source |
|
|
| Generated with the `synthgen-if` synthetic instruction-following pipeline. |
|
|
