Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Readme Update for FSDP #980

Merged
merged 4 commits into from
Jun 6, 2024
Merged

Readme Update for FSDP #980

Changes from 1 commit
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
61cd667
Readme Update for FSDP
hlahkar May 14, 2024
733b6a7
Update README.md
hlahkar May 14, 2024
1bfd805
Update test_fsdp_examples.py
hlahkar May 21, 2024
f7f1f8b
Update test_fsdp_examples.py
hlahkar May 23, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Next Next commit
Readme Update for FSDP 
Updating Readme to  indicate flash attention support for LLama2 70b with FSDP. This improves performance as well as memory footprint
  • Loading branch information
@hlahkar
hlahkar authored May 14, 2024
commit 61cd667f40291b5f3e949ae333c6921acd7ee229
3 changes: 2 additions & 1 deletion examples/language-modeling/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -599,7 +599,8 @@ python3 ../gaudi_spawn.py --world_size 8 --use_mpi run_lora_clm.py \
--use_fused_rope False \
--torch_compile_backend hpu_backend \
--torch_compile \
--gradient_accumulation_steps 2
--gradient_accumulation_steps 2 \
--use_flash_attention True
```

- Multi-card finetuning of Falcon-180B:
Expand Down
Loading