Instructions to use begulagg/Celeste-GF-Q8_0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use begulagg/Celeste-GF-Q8_0 with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf begulagg/Celeste-GF-Q8_0:Q8_0 # Run inference directly in the terminal: llama cli -hf begulagg/Celeste-GF-Q8_0:Q8_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf begulagg/Celeste-GF-Q8_0:Q8_0 # Run inference directly in the terminal: llama cli -hf begulagg/Celeste-GF-Q8_0:Q8_0
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf begulagg/Celeste-GF-Q8_0:Q8_0 # Run inference directly in the terminal: ./llama-cli -hf begulagg/Celeste-GF-Q8_0:Q8_0
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf begulagg/Celeste-GF-Q8_0:Q8_0 # Run inference directly in the terminal: ./build/bin/llama-cli -hf begulagg/Celeste-GF-Q8_0:Q8_0
Use Docker
docker model run hf.co/begulagg/Celeste-GF-Q8_0:Q8_0
- LM Studio
- Jan
- Ollama
How to use begulagg/Celeste-GF-Q8_0 with Ollama:
ollama run hf.co/begulagg/Celeste-GF-Q8_0:Q8_0
- Unsloth Desktop
- Docker Model Runner
How to use begulagg/Celeste-GF-Q8_0 with Docker Model Runner:
docker model run hf.co/begulagg/Celeste-GF-Q8_0:Q8_0
- Lemonade
How to use begulagg/Celeste-GF-Q8_0 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull begulagg/Celeste-GF-Q8_0:Q8_0
Run and chat with the model
lemonade run user.Celeste-GF-Q8_0-Q8_0
List all available models
lemonade list
- Atomic Chat
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
I just forked Celeste V1.5 ( 8B Q8_0 llama 3.1 ) BUT
I trained this AI to talk like a girl.. NO! I trained it to talk like myself but a girl version. so what I do is I asked gemini-3.8-flash from Google AI Studio to create me a lot of guy chats in couples, I acted like a girl in that thing and answered all the question so I will have a dataset to give my AI a feminine behaviour
kinda gay but I don't have a girlfriend neither got into any relationship, so I cannot use any chats with my non existent girlfriend to train this AI... so I acted like the girlfriend itself
why am I doing this bullshit? its cool. ill have a AI girlfriend running on my PCs RAM
im 100% straight btw.
BIG THANKS TO GOOGLE COLAB and KAGGLE for giving free trials! I used Googles datacenter to train this shit. such a waste of fresh water...
- Downloads last month
- 19
8-bit