Downloads · 30 days
0
llama3-8b-calm
zeuxcg/llama3-8b-calm
llama3-8b-calm is a machine learning model from zeuxcg. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
After downloading both .calm files and the run binary, run:
Access
Public
Updated Apr 24, 2024
Repo size
12.1 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.calm12.1 GB · 100%
At a glance
- Access
- Public
- Created
- Apr 19, 2024
- Updated
- Apr 24, 2024
- SHA
- 38df1d4a
Model card
From the Hugging Face model README
After downloading both .calm files and the run binary, run:
chmod a+x run
and then:
./run llama3-8b-fp8.calm -i "?" -n 32 -r 5
CALM_POSO=4000 ./run llama3-8b-fp8.calm -i "?" -n 32 -r 5
./run llama3-8b-gf4.calm -i "?" -n 32 -r 5
CALM_POSO=4000 ./run llama3-8b-gf4.calm -i "?" -n 32 -r 5
Note: the run binary is not signed, so macOS will refuse to run it by default, but you can ctrl+click the binary and press "Open", which will show a dialog where you need to press "Open" again.
After this the binary should be fine to run from terminal.
If you'd rather build the binary yourself, you can do it like this:
git clone https://github.com/zeux/calm
make -C calm
... but you'll need Xcode installed for this to work.
- Created
- Apr 19, 2024
- Updated
- Apr 24, 2024