Argilla distilabel Capybara-DPO
Fresh
A high-quality DPO derivative of LDJnr's Capybara, with chosen/rejected pairs synthesized and rated using Argilla's distilabel pipeline.
- Type
- DPO Dataset
- Publisher
- Argilla
- Runtime
hf_parquet- License
- Apache-2.0
- Size
- 7.5k preference pairs
- Published
- May 2026
Cite
Notes
Only stored in your browser.
Lift evidence
2| Eval | Tools known to lift | Source paper |
|---|---|---|
| MT-Bench | Argilla distilabel Capybara-DPO | - |
| Arena-Hard | Argilla distilabel Capybara-DPO | - |
Models
Notable models trained on it
CapybaraHermes-2.5-Mistral-7Bmany Argilla and community DPO fine-tunes in early 2024