---
datasets:
- teknium/OpenHermes-2.5
license: llama2
---

**Finetuned over openhermes-2.5 dataset for 1 epoch**

- Follows the llama-3 instruction format described in https://llama.meta.com/docs/model-cards-and-prompt-formats/meta-llama-3

**Training Details**

https://medium.com/@sumandas0/fine-tune-llama3-on-million-scale-dataset-in-consumer-gpu-using-qlora-deepspeed-3ae8ad75299a