Step-by-step guide to fine-tuning Llama 3 70B using PyTorch FSDP (Fully Sharded Data Parallel) combined with Q-LoRA, enabling training on consumer-grade GPUs. Covers environment setup, dataset preparation using the HuggingFaceH4/no_robots dataset, distributed training configuration with torchrun, memory usage trade-offs (from 4x24GB GPUs with CPU offloading to 4x H100s), cost estimates (~$255 on A10G vs ~$25-50 on H100s), and inference testing. Uses Hugging Face TRL's SFTTrainer, PEFT, Transformers, and Flash Attention v2 via PyTorch SDPA.

8m read timeFrom philschmid.de
Post cover image
Table of contents
1. Setup development environment2. Create and prepare the dataset3. Fine-tune the LLM with PyTorch FSDP, Q-Lora and SDPA4. Test Model and run Inference
3 Impressions