Instructions to use okamototk/Gemma-2-Llama-Swallow-9b-it-v0.1-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use okamototk/Gemma-2-Llama-Swallow-9b-it-v0.1-gguf with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="okamototk/Gemma-2-Llama-Swallow-9b-it-v0.1-gguf")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("okamototk/Gemma-2-Llama-Swallow-9b-it-v0.1-gguf", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use okamototk/Gemma-2-Llama-Swallow-9b-it-v0.1-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 okamototk/Gemma-2-Llama-Swallow-9b-it-v0.1-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf okamototk/Gemma-2-Llama-Swallow-9b-it-v0.1-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 okamototk/Gemma-2-Llama-Swallow-9b-it-v0.1-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf okamototk/Gemma-2-Llama-Swallow-9b-it-v0.1-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 okamototk/Gemma-2-Llama-Swallow-9b-it-v0.1-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf okamototk/Gemma-2-Llama-Swallow-9b-it-v0.1-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 okamototk/Gemma-2-Llama-Swallow-9b-it-v0.1-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf okamototk/Gemma-2-Llama-Swallow-9b-it-v0.1-gguf:Q4_K_M

Use Docker

docker model run hf.co/okamototk/Gemma-2-Llama-Swallow-9b-it-v0.1-gguf:Q4_K_M

LM Studio
Jan

vLLM

How to use okamototk/Gemma-2-Llama-Swallow-9b-it-v0.1-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "okamototk/Gemma-2-Llama-Swallow-9b-it-v0.1-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": "okamototk/Gemma-2-Llama-Swallow-9b-it-v0.1-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/okamototk/Gemma-2-Llama-Swallow-9b-it-v0.1-gguf:Q4_K_M

SGLang

How to use okamototk/Gemma-2-Llama-Swallow-9b-it-v0.1-gguf with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "okamototk/Gemma-2-Llama-Swallow-9b-it-v0.1-gguf" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "okamototk/Gemma-2-Llama-Swallow-9b-it-v0.1-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "okamototk/Gemma-2-Llama-Swallow-9b-it-v0.1-gguf" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "okamototk/Gemma-2-Llama-Swallow-9b-it-v0.1-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use okamototk/Gemma-2-Llama-Swallow-9b-it-v0.1-gguf with Ollama:
```
ollama run hf.co/okamototk/Gemma-2-Llama-Swallow-9b-it-v0.1-gguf:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use okamototk/Gemma-2-Llama-Swallow-9b-it-v0.1-gguf with Docker Model Runner:
```
docker model run hf.co/okamototk/Gemma-2-Llama-Swallow-9b-it-v0.1-gguf:Q4_K_M
```

Lemonade

How to use okamototk/Gemma-2-Llama-Swallow-9b-it-v0.1-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull okamototk/Gemma-2-Llama-Swallow-9b-it-v0.1-gguf:Q4_K_M

Run and chat with the model

lemonade run user.Gemma-2-Llama-Swallow-9b-it-v0.1-gguf-Q4_K_M

List all available models

lemonade list

Atomic Chat

Gemma-2-Llama-Swallow-9b-it-v0.1-gguf / README.md

okamototk

Update README.md

06fd2cd verified about 1 year ago

preview code

Raw

History Blame Contribute Delete

697 Bytes

	---
	language:
	- en
	- ja
	library_name: transformers
	pipeline_tag: text-generation
	license:
	- gemma
	- llama3.3
	datasets:
	- TFMC/imatrix-dataset-for-japanese-llm
	base_model:
	- tokyotech-llm/Gemma-2-Llama-Swallow-9b-it-v0.1
	---
	# Gemma-2-Llama-Swallow GGUF

	This model is quantized GGUF version of Gemma-2-Llama-Swallow. Performance degradation compared to the original model.
	Please check original information at [Gemma-2-Llama Swallow](https://swallow-llm.github.io/gemma2-llama-swallow.ja.html).

	## License

	[Gemma Terms of Use](https://ai.google.dev/gemma/terms) and [META LLAMA 3.3 COMMUNITY LICENSE](https://www.llama.com/llama3_3/license/)

	This model is built with Gemma and built with Llama.