11 lines
395 B
Markdown
11 lines
395 B
Markdown
|
# Open LLaMA
|
||
|
|
|
||
|
|
Run [OpenLLaMA](https://github.com/openlm-research/open_llama) in a GPU environment with a single command. 📡
|
||
|
|
|
||
|
|
## Speed Run
|
||
|
|
|
||
|
|
1. Signup for [Beam](http://beam.cloud)
|
||
|
|
2. Download the CLI and Python SDK
|
||
|
|
3. Clone this template locally: `beam create-app openllama`
|
||
|
|
4. Spin up a GPU environment to run inference: `beam start app.py`
|
||
|
|
5. Deploy the app as a web API: `beam deploy app.py`
|