Text Generation
Transformers
Safetensors
dbrx
conversational
text-generation-inference

Fine-tune dbrx via Hugging Face Trainer vs. LLM-Foundry

#58
by HaloHaloHottie - opened

In general, are there any blaring pros and cons between using Hugging Face Trainer vs. LLM-Foundry to fine-tune dbrx-base or dbrx-instruct?

I imagine not, but I have seen reference of using the former in this previous discussion post whereas both Model cards reference the latter..

Thank you in advance!

Sign up or log in to comment