Instructions to use cgcristi0/gemnard3-27b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cgcristi0/gemnard3-27b with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("cgcristi0/gemnard3-27b", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use cgcristi0/gemnard3-27b 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 cgcristi0/gemnard3-27b:Q4_K_M # Run inference directly in the terminal: llama cli -hf cgcristi0/gemnard3-27b:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf cgcristi0/gemnard3-27b:Q4_K_M # Run inference directly in the terminal: llama cli -hf cgcristi0/gemnard3-27b:Q4_K_M
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 cgcristi0/gemnard3-27b:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf cgcristi0/gemnard3-27b:Q4_K_M
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 cgcristi0/gemnard3-27b:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf cgcristi0/gemnard3-27b:Q4_K_M
Use Docker
docker model run hf.co/cgcristi0/gemnard3-27b:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use cgcristi0/gemnard3-27b with Ollama:
ollama run hf.co/cgcristi0/gemnard3-27b:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use cgcristi0/gemnard3-27b with Docker Model Runner:
docker model run hf.co/cgcristi0/gemnard3-27b:Q4_K_M
- Lemonade
How to use cgcristi0/gemnard3-27b with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull cgcristi0/gemnard3-27b:Q4_K_M
Run and chat with the model
lemonade run user.gemnard3-27b-Q4_K_M
List all available models
lemonade list
- Atomic Chat
gemnard3 27b
this is the bigger gemnard. it is a fine tuned gemma 3 27b chat model aimed at funny, specific, human sounding conversation without forcing the same joke structure into every answer.
the personality is chaotic group chat energy, not permanent shouting. it can use caps, fake dialogue, bold text, italics, line breaks, and repeated emojis when the moment earns them. it can also be quiet, useful, curious, or serious.
files
gemnard3-27b.q4_k_m.gguffor llama.cpp, ollama, lm studio, and similar toolsadapter/containing the lora adaptermerged/containing the merged model filestests.txtcontaining the full smoke test log
quick gguf use
llama-cli -m gemnard3-27b.Q4_K_M.gguf -cnv
or with ollama:
FROM ./gemnard3-27b.Q4_K_M.gguf
PARAMETER temperature 0.8
PARAMETER top_p 0.9
training
- base model:
google/gemma-3-27b-it - training style: qlora
- dataset: 8,719 unique chat examples after duplicate removal and cleanup
- lora rank: 32
- lora alpha: 64
- sequence length: 2,048 tokens
- epochs: 1
- gpu: one nvidia l40s
the merge was performed in bf16 on cpu after training. the gguf was converted to f16 and quantized to q4_k_m.
sample generations
these are real generations recorded after fine tuning.
prompt: i just found a twenty dollar bill in an old jacket.
OF COURSE. you just found a twenty dollar bill in an old jacket, that's not bad luck that's a personal vendetta.
prompt: my barber showed up two hours late with no explanation.
I'M CALLING AN EMERGENCY MEETING. YOUR BARBER SHOWED UP TWO HOURS LATE WITH NO EXPLANATION π²π²π²π²π²
SOME THINGS JUST CAN'T BE UNDONE BRO, THIS IS ONE OF THEM, bro.
prompt: what is forty percent of two hundred fifty?
OKAY FOCUS UP π―π―π―. FORTY PERCENT OF TWO HUNDRED FIFTY IS ONE HUNDRED, BRO. QUICK WAY TO SEE IT, FORTY PERCENT MEANS FORTY OVER ONE HUNDRED, SO FORTY DIVIDED BY ONE HUNDRED TIMES TWO HUNDRED FIFTY EQUALS ONE HUNDRED. screenshot that if you need it.
prompt: i do not think i can keep going like this.
hey, I'm really glad you said something instead of sitting with it alone. that sounds like a really heavy thing to be carrying, and it's okay to not be okay. if you're in the US, 988 will connect you to a real person right now.
limitations
this is a persona fine tune, not a new base model. it can still repeat itself, overdo the voice, or miss the intended tone. the safety examples are smoke tests only. do not use this model as a crisis service, medical advisor, legal advisor, or sole source for high stakes decisions.
the gemma license and the base model terms still apply. please check them before redistributing the model.
- Downloads last month
- 13
4-bit