llama-3 examples (#1537)

This commit is contained in:
Wing Lian
2024-04-18 14:28:03 -04:00
committed by GitHub
parent d28ba2e405
commit 15f7910d33
4 changed files with 217 additions and 0 deletions

View File

@@ -0,0 +1,13 @@
# Llama-3
https://llama.meta.com/llama3/
[8B Base Model](https://huggingface.co/meta-llama/Meta-Llama-3-8B)
- [Full Fine Tune](./fft-8b.yaml)
- Single GPU @ 48GB VRAM
- [LoRA](./lora-8b.yml)
- Single GPU @ 11GB VRAM
[70B Base Model](https://huggingface.co/meta-llama/Meta-Llama-3-70B)
- [QLORA+FSDP](./qlora-fsdp-70b.yaml)
- Dual GPU @ 21GB VRAM