Instructions to use ddtsoftware/gemma3-jarvic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use ddtsoftware/gemma3-jarvic 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 ddtsoftware/gemma3-jarvic
# Run inference directly in the terminal:
llama cli -hf ddtsoftware/gemma3-jarvic

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ddtsoftware/gemma3-jarvic
# Run inference directly in the terminal:
llama cli -hf ddtsoftware/gemma3-jarvic

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 ddtsoftware/gemma3-jarvic
# Run inference directly in the terminal:
./llama-cli -hf ddtsoftware/gemma3-jarvic

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 ddtsoftware/gemma3-jarvic
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ddtsoftware/gemma3-jarvic

Use Docker

docker model run hf.co/ddtsoftware/gemma3-jarvic

LM Studio
Jan
Ollama
How to use ddtsoftware/gemma3-jarvic with Ollama:
```
ollama run hf.co/ddtsoftware/gemma3-jarvic
```

Unsloth Studio

How to use ddtsoftware/gemma3-jarvic with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for ddtsoftware/gemma3-jarvic to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for ddtsoftware/gemma3-jarvic to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ddtsoftware/gemma3-jarvic to start chatting

Docker Model Runner
How to use ddtsoftware/gemma3-jarvic with Docker Model Runner:
```
docker model run hf.co/ddtsoftware/gemma3-jarvic
```

Lemonade

How to use ddtsoftware/gemma3-jarvic with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ddtsoftware/gemma3-jarvic

Run and chat with the model

lemonade run user.gemma3-jarvic-{{QUANT_TAG}}

List all available models

lemonade list

Atomic Chat

gemma3-jarvic / Note.txt

ddtsoftware

Update Note.txt

a5008d2 verified 8 months ago

Raw

History Blame Contribute Delete

1.34 kB

	qsnich-it@MacBook-Air-khxng-Qsnich-IT Finetune % python3 -m venv mlx_env
	qsnich-it@MacBook-Air-khxng-Qsnich-IT Finetune % source mlx_env/bin/activate
	(mlx_env) qsnich-it@MacBook-Air-khxng-Qsnich-IT Finetune % git clone https://github.com/ggerganov/llama.cpp.git
	(mlx_env) qsnich-it@MacBook-Air-khxng-Qsnich-IT Finetune % pip install -r llama.cpp/requirements.txt
	(mlx_env) qsnich-it@MacBook-Air-khxng-Qsnich-IT Finetune % pip install torch sentencepiece
	(mlx_env) qsnich-it@MacBook-Air-khxng-Qsnich-IT Finetune % pip install -U mlx-lm

	(mlx_env) qsnich-it@MacBook-Air-khxng-Qsnich-IT Finetune % python -m mlx_lm lora \
	--model google/gemma-3-4b-it \
	--data ./data \
	--train \
	--iters 200 \
	--batch-size 1 \
	--learning-rate 1e-5 \
	--mask-prompt \
	--num-layers 8 \
	--adapter-path ./adapters

	(mlx_env) qsnich-it@MacBook-Air-khxng-Qsnich-IT Finetune % mlx_lm.fuse \
	--model google/gemma-3-4b-it \
	--adapter-path adapters \
	--save-path ./gemma3-fused-f16

	(mlx_env) qsnich-it@MacBook-Air-khxng-Qsnich-IT Finetune % python llama.cpp/convert_hf_to_gguf.py ./gemma3-fused-f16 \
	--outfile gemma3-custom.gguf \
	--outtype f16

	(mlx_env) qsnich-it@MacBook-Air-khxng-Qsnich-IT Finetune % nano Modelfile2
	(mlx_env) qsnich-it@MacBook-Air-khxng-Qsnich-IT Finetune % ollama create gemma3-jarvic -f Modelfile2