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

Fix fix for weight type define, refs #198 #216

Merged
merged 1 commit into from
Jun 7, 2024
Merged

Fix fix for weight type define, refs #198 #216

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
12 changes: 7 additions & 5 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -151,13 +151,15 @@ cmake -B build

**or** if you downloaded bfloat16 weights (any model *without* `-sfp` in the
name), instead of running cmake with no options as above, run cmake with
GEMMA_WEIGHT_T set to [highway's](https://github.com/google/highway)
`hwy::bfloat16_t` type. We intend to soon support all weight types without
requiring compiler flags. Note that we recommend using `-sfp` weights instead of
bfloat16 for faster inference.
WEIGHT_TYPE set to [highway's](https://github.com/google/highway)
`hwy::bfloat16_t` type. Alternatively, you can also add
`-DGEMMA_WEIGHT_T=hwy::bfloat16_t` to the C++ compiler flags.

We intend to soon support all weight types without requiring extra flags. Note
that we recommend using `-sfp` weights instead of bfloat16 for faster inference.

```sh
cmake -B build -DGEMMA_WEIGHT_T=hwy::bfloat16_t
cmake -B build -DWEIGHT_TYPE=hwy::bfloat16_t
```

After running whichever of the above `cmake` invocations that is appropriate for
Expand Down
Loading