Instructions to use rinrin0413/sarashina2.2-vision-3b-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use rinrin0413/sarashina2.2-vision-3b-GGUF 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 rinrin0413/sarashina2.2-vision-3b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf rinrin0413/sarashina2.2-vision-3b-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf rinrin0413/sarashina2.2-vision-3b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf rinrin0413/sarashina2.2-vision-3b-GGUF: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 rinrin0413/sarashina2.2-vision-3b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf rinrin0413/sarashina2.2-vision-3b-GGUF: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 rinrin0413/sarashina2.2-vision-3b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf rinrin0413/sarashina2.2-vision-3b-GGUF:Q4_K_M

Use Docker

docker model run hf.co/rinrin0413/sarashina2.2-vision-3b-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use rinrin0413/sarashina2.2-vision-3b-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rinrin0413/sarashina2.2-vision-3b-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rinrin0413/sarashina2.2-vision-3b-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/rinrin0413/sarashina2.2-vision-3b-GGUF:Q4_K_M

Ollama
How to use rinrin0413/sarashina2.2-vision-3b-GGUF with Ollama:
```
ollama run hf.co/rinrin0413/sarashina2.2-vision-3b-GGUF:Q4_K_M
```

Unsloth Studio

How to use rinrin0413/sarashina2.2-vision-3b-GGUF 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 rinrin0413/sarashina2.2-vision-3b-GGUF 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 rinrin0413/sarashina2.2-vision-3b-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for rinrin0413/sarashina2.2-vision-3b-GGUF to start chatting

Docker Model Runner
How to use rinrin0413/sarashina2.2-vision-3b-GGUF with Docker Model Runner:
```
docker model run hf.co/rinrin0413/sarashina2.2-vision-3b-GGUF:Q4_K_M
```

Lemonade

How to use rinrin0413/sarashina2.2-vision-3b-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull rinrin0413/sarashina2.2-vision-3b-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.sarashina2.2-vision-3b-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

Sarashina2.2-Vision 3B (GGUF)

These are quantized GGUF versions of sbintuitions/sarashina2.2-vision-3b, converted and quantized with TFMC/imatrix-dataset-for-japanese-llm using llama.cpp version 9093 (1e5ad35d5).

How to Use (llama-cli)

llama-cli -m Sarashina2.2-Vision-3B_Q8_0.gguf -mm mmproj-BF16_Sarashina2.2-Vision-3B.gguf -c 8192 --image /path/to/image.png -p "この画像は何ですか？"

Limitations

This model has limited safety training. Therefore, it might generate some meaningless sequences, some inaccurate instances, or biased/objectionable outputs. Before using it, we would like developers to tune models based on human preferences and safety considerations.

License

MIT License— same as the base model.

Downloads last month: 81

GGUF

Model size

3B params

Architecture

llama

Hardware compatibility

4-bit

8-bit

Model tree for rinrin0413/sarashina2.2-vision-3b-GGUF

Base model

sbintuitions/sarashina2.2-3b

Finetuned

sbintuitions/sarashina2.2-3b-instruct-v0.1

Finetuned

sbintuitions/sarashina2.2-vision-3b

Quantized

(4)

this model

rinrin0413
/

sarashina2.2-vision-3b-GGUF

Sarashina2.2-Vision 3B (GGUF)

How to Use (llama-cli)

Limitations

License

Model tree for rinrin0413/sarashina2.2-vision-3b-GGUF

Dataset used to train rinrin0413/sarashina2.2-vision-3b-GGUF