---
library_name: transformers
license: apache-2.0
datasets:
- Atsunori/HelpSteer2-DPO
- nbeerbower/Schule-DPO
- nbeerbower/Purpura-DPO
- nbeerbower/Arkhaios-DPO
- jondurbin/truthy-dpo-v0.1
- antiven0m/physical-reasoning-dpo
- flammenai/Date-DPO-NoAsterisks
base_model:
- nbeerbower/Nemoties-ChatML-12B
---

![image/png](https://huggingface.co/nbeerbower/CaptainNemo-ChatML-12B/resolve/main/capnemo.png)

# CaptainNemo-ChatML-12B

[Nemoties-ChatML-12B](https://huggingface.co/nbeerbower/Nemoties-ChatML-12B) finetuned on: 
* [Atsunori/HelpSteer2-DPO](https://huggingface.co/datasets/Atsunori/HelpSteer2-DPO)
* [nbeerbower/Schule-DPO](https://huggingface.co/datasets/nbeerbower/Schule-DPO)
* [nbeerbower/Purpura-DPO](https://huggingface.co/datasets/nbeerbower/Purpura-DPO)
* [nbeerbower/Arkhaios-DPO](https://huggingface.co/datasets/nbeerbower/Arkhaios-DPO)
* [jondurbin/truthy-dpo-v0.1](https://huggingface.co/datasets/jondurbin/truthy-dpo-v0.1)
* [antiven0m/physical-reasoning-dpo](https://huggingface.co/datasets/antiven0m/physical-reasoning-dpo)
* [flammenai/Date-DPO-NoAsterisks](https://huggingface.co/datasets/flammenai/Date-DPO-NoAsterisks)

### Method

[QLoRA ORPO tuned](https://mlabonne.github.io/blog/posts/2024-04-19_Fine_tune_Llama_3_with_ORPO.html) with 1x RTX A6000 for 2 epochs. Rank 64 LoRA, 2e-5 learning rate.