https://github.com/p1ayer-1/llama-libtorch
Llama causal LM fully recreated in LibTorch. Designed to be used in Unreal Engine 5
https://github.com/p1ayer-1/llama-libtorch
libtorch llama2 llamacpp machine-learning pytorch
Last synced: 9 months ago
JSON representation
Llama causal LM fully recreated in LibTorch. Designed to be used in Unreal Engine 5
- Host: GitHub
- URL: https://github.com/p1ayer-1/llama-libtorch
- Owner: P1ayer-1
- License: mit
- Created: 2023-12-09T00:47:43.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2024-09-19T22:23:53.000Z (almost 2 years ago)
- Last Synced: 2025-04-04T20:36:09.505Z (about 1 year ago)
- Topics: libtorch, llama2, llamacpp, machine-learning, pytorch
- Language: C++
- Homepage:
- Size: 18.6 KB
- Stars: 13
- Watchers: 1
- Forks: 3
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Llama-LibTorch
Llama causal LM fully recreated in LibTorch. Designed to be used in Unreal Engine 5
## Usage
Navigate to the root of this repo.
Then run these commands:
1. `mkdir build && cd build`
2. `cmake -DCMAKE_PREFIX_PATH=$PATH_TO_LIBTORCH ..` # ".." tells cmake what you are trying to compile. In this case, ".." points to the root of the Llama-LibTorch project. ".."= path to the parent of current directory
3. `cmake --build . --config Release ` # this actually builds the project and creates the .exe file