Fine-tuning Mixtral with different types of datasets
#214
by
ziko11
- opened
I possess a diverse collection of datasets consisting of CSV files,
code sources, text documents, and more. I aim to perform fine-tuning on
Mixtral using these datasets. To achieve this, I need guidance on how to
create embeddings for each dataset type.
hey @ziko11 you might find Impulse AI (https://www.impulselabs.ai/) useful. we make it super easy to fine-tune and deploy open source models. hopefully you find it helpful! i know not relevant to your problem above but might be easier to use us to fine tune and deploy
docs: https://docs.impulselabs.ai/introduction
python sdk: https://pypi.org/project/impulse-api-sdk-python/