Article
Fine-tune Llama 2 with DPO
- +1
kashif, ybelkada, lvwerra
• • 69zp
zepxue
·
AI & ML interests
None yet
Organizations
None yet
upvoted 3
articles about 1 year ago
Article
Accelerate Large Model Training using PyTorch Fully Sharded Data Parallel
smangrul, sgugger
• • 9 Article
Fine-tuning Llama 2 70B using PyTorch FSDP
- +2
smangrul, sgugger, lewtun, philschmid
• • 32 upvoted a collection over 1 year ago