https://github.com/prometheus-hack/telegram-language-model-server
Этот репозиторий используется для развертывания Telegram Bot с доступом к LLM на базе GPT-4 Turbo
https://github.com/prometheus-hack/telegram-language-model-server
Last synced: 23 days ago
JSON representation
Этот репозиторий используется для развертывания Telegram Bot с доступом к LLM на базе GPT-4 Turbo
- Host: GitHub
- URL: https://github.com/prometheus-hack/telegram-language-model-server
- Owner: prometheus-hack
- Created: 2024-04-06T17:45:24.000Z (about 2 years ago)
- Default Branch: main
- Last Pushed: 2024-04-07T03:44:03.000Z (about 2 years ago)
- Last Synced: 2025-03-05T14:48:44.247Z (over 1 year ago)
- Language: Python
- Size: 17.6 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
Win:
venv v\Scripts\activate
Mac:
source venv/bin/activate
deactivate
# Run
pip install -r requirements.txt
## LLaMA 2 install
model:
Make sure you have git-lfs installed (https://git-lfs.com)
git lfs install
git clone https://huggingface.co/botato/point-alpaca-ggml-model-q4_0
if you want to clone without large files – just their pointers
prepend your git clone with the following env var:
GIT_LFS_SKIP_SMUDGE=1
mac:
CMAKE_ARGS="-DLLAMA_METAL=on" FORCE_CMAKE=1 pip install llama-cpp-python
win:
git clone --recursive -j8 https://github.com/abetlen/llama-cpp-python.git
set FORCE_CMAKE=1
set CMAKE_ARGS=-DLLAMA_CUBLAS=OFF
python setup.py clean
python setup.py install
pip freeze > requirements.txt