---
license: apache-2.0
datasets:
  - 40umov/dostoevsky
language:
  - ru
base_model:
  - Vikhrmodels/Vikhr-Nemo-12B-Instruct-R-21-09-24
library_name: unsloth
---

Vikhr-Nemo fine-tuned with contrastive Russian literature.

* Base model: https://huggingface.co/Vikhrmodels/Vikhr-Nemo-12B-Instruct-R-21-09-24
* Dataset: https://huggingface.co/datasets/40umov/dostoevsky
* Method: [ORPO](https://arxiv.org/abs/2403.07691)
* Training config: https://github.com/IlyaGusev/saiga/blob/main/configs/models/doestoevsky_nemo_12b_orpo_m1.json
* WandB: https://wandb.ai/ilyagusev/rulm_self_instruct/runs/4v4pcgej