Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama3 for WhatsApp & Messenger.
🚀 The feature, motivation and pitch
Is it possible to adapt the fine-tuning script for DPO finetuning? The current version seems to only work for next token prediction fine-tuning.
Alternatives
No response
Additional context
No response