Skip to content

Update llama2 readme file - main branch #3340

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

Closed
wants to merge 1 commit into from
Closed

Update llama2 readme file - main branch #3340

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
19 changes: 10 additions & 9 deletions examples/models/llama2/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,21 +33,22 @@ We evaluated UncycloText perplexity using [LM Eval](https://github.com/EleutherAI/l

Note that groupsize less than 128 was not enabled, since such model were still too large. This is because our current efforts have focused on enabling FP32 and support for FP16 is under way. What this implies for model size is that 1) embedding table is in FP32 and 2) quantized weights scales are FP32.

## Enablement

We have verified running Llama 2 7B [mobile applications](#step-6-build-mobile-apps) efficiently on select devices including the iPhone 15 Pro, iPhone 15 Pro Max, Samsung Galaxy S22 and S24, and OnePlus 12.

For Llama 3 8B, we have verified so far on iPhone 15 Pro Max and OnePlus 12 (with 16GB RAM).

## Performance

Performance was measured on Samsung Galaxy S22, S24, One Plus 12 and iPhone 15 max Pro. Measurement performance is in terms of tokens/second.
Llama2 7B performance was measured on the Samsung Galaxy S22, S24, and OnePlus 12 devices. The performance measurement is expressed in terms of tokens per second using an [adb binary-based approach](#step-5-run-benchmark-on).

|Device | Groupwise 4-bit (128) | Groupwise 4-bit (256)
|--------| ---------------------- | ---------------
|Galaxy S22* | 8.15 tokens/second | 8.3 tokens/second |
|Galaxy S24* | 10.66 tokens/second | 11.26 tokens/second |
|One plus 12* | 11.55 tokens/second | 11.6 tokens/second |
|Galaxy S22** | 5.5 tokens/second | 5.9 tokens/second |
|iPhone 15 pro** | ~6 tokens/second | ~6 tokens/second |

*: Measured via adb binary based [workflow](#step-5-run-benchmark-on)
|Galaxy S22 | 8.15 tokens/second | 8.3 tokens/second |
|Galaxy S24 | 10.66 tokens/second | 11.26 tokens/second |
|OnePlus 12 | 11.55 tokens/second | 11.6 tokens/second |

**: Measured via app based [workflow](#step-6-build-mobile-apps)

# Instructions

Expand Down