Consultation on how to fine-tune the model
Hi，
I am currently exploring the fine-tuning methods for the model evo-1-8k-base and would like to apply it to other datasets. However, my knowledge of large language models is quite limited, and I am unsure where to begin with the implementation.
Fortunately, I came across your work on this site, and I would like to ask if you could provide some guidance on how to fine-tune this model. I have found some documentation for AutoTrain (AutoTrain Advanced) and PEFT (Parameter-Efficient Fine-Tuning) on Hugging Face, and I am reviewing it. However, the documentation mentions that these methods are typically used for transformer-based models, while the evo-1-8k-base model utilizes the StripedHyena architecture. Therefore, I am uncertain whether these simplified fine-tuning methods can be applied to this model.
Thank you for your assistance!