Instructions to use QuantFactory/gemma-2-baku-2b-it-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use QuantFactory/gemma-2-baku-2b-it-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="QuantFactory/gemma-2-baku-2b-it-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("QuantFactory/gemma-2-baku-2b-it-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use QuantFactory/gemma-2-baku-2b-it-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 QuantFactory/gemma-2-baku-2b-it-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf QuantFactory/gemma-2-baku-2b-it-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 QuantFactory/gemma-2-baku-2b-it-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf QuantFactory/gemma-2-baku-2b-it-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 QuantFactory/gemma-2-baku-2b-it-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf QuantFactory/gemma-2-baku-2b-it-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 QuantFactory/gemma-2-baku-2b-it-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf QuantFactory/gemma-2-baku-2b-it-GGUF:Q4_K_M

Use Docker

docker model run hf.co/QuantFactory/gemma-2-baku-2b-it-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use QuantFactory/gemma-2-baku-2b-it-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "QuantFactory/gemma-2-baku-2b-it-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": "QuantFactory/gemma-2-baku-2b-it-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/QuantFactory/gemma-2-baku-2b-it-GGUF:Q4_K_M

SGLang

How to use QuantFactory/gemma-2-baku-2b-it-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 "QuantFactory/gemma-2-baku-2b-it-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": "QuantFactory/gemma-2-baku-2b-it-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 "QuantFactory/gemma-2-baku-2b-it-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": "QuantFactory/gemma-2-baku-2b-it-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use QuantFactory/gemma-2-baku-2b-it-GGUF with Ollama:
```
ollama run hf.co/QuantFactory/gemma-2-baku-2b-it-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use QuantFactory/gemma-2-baku-2b-it-GGUF with Docker Model Runner:
```
docker model run hf.co/QuantFactory/gemma-2-baku-2b-it-GGUF:Q4_K_M
```

Lemonade

How to use QuantFactory/gemma-2-baku-2b-it-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull QuantFactory/gemma-2-baku-2b-it-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.gemma-2-baku-2b-it-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

QuantFactory/gemma-2-baku-2b-it-GGUF

This is quantized version of rinna/gemma-2-baku-2b-it created using llama.cpp

Original Model Card

`Gemma 2 Baku 2B Instruct (rinna/gemma-2-baku-2b-it)`

Overview

The model is an instruction-tuned variant of rinna/gemma-2-baku-2b, utilizing Chat Vector and Odds Ratio Preference Optimization (ORPO) for fine-tuning. It adheres to the gemma-2 chat format.

Size	Continual Pre-Training	Instruction-Tuning
2B	Gemma 2 Baku 2B [HF]	Gemma 2 Baku 2B Instruct [HF]

Model architecture

A 26-layer, 2304-hidden-size transformer-based language model. Please refer to the Gemma 2 Model Card for detailed information on the model's architecture.
Training

Model merging. The base model was endowed with instruction-following capabilities through a chat vector addition process. The chat vector was derived by subtracting the parameter vectors of google/gemma-2-2b from google/gemma-2-2b-it, as follows.
```
  rinna/gemma-2-baku-2b + 1.0 * (google/gemma-2-2b-it - google/gemma-2-2b)
```
During this process, the embedding layer was excluded during the subtraction and addition of parameter vectors.

OPRO was applied using a subset of the following dataset to further refine the performance of the merged model.
- rinna's internal dataset
Contributors

Benchmarking

Please refer to rinna's LM benchmark page.

How to use the model

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "rinna/gemma-2-baku-2b-it"
dtype = torch.bfloat16

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="cuda",
    torch_dtype=dtype,
    attn_implementation="eager",
)

chat = [
    { "role": "user", "content": "西田幾多郎とはどんな人物ですか？" },
]
prompt = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)

input_ids = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt").to(model.device)
outputs = model.generate(
    input_ids,
    max_new_tokens=512,
)

response = tokenizer.decode(outputs[0][input_ids.shape[-1]:], skip_special_tokens=True)
print(response)

It is recommended to use eager attention when conducting batch inference under bfloat16 precision. Currently, Gemma 2 yields NaN values for input sequences with padding when the default attention mechanism (torch.scaled_dot_product_attention) is employed in conjunction with bfloat16.

Tokenization

The model uses the original google/gemma-2-2b-it tokenizer.

How to cite

@misc{rinna-gemma-2-baku-2b-it,
    title = {rinna/gemma-2-baku-2b-it},
    author = {Chen, Xinqi and Wakatsuki, Toshiaki and Sawada, Kei},
    url = {https://huggingface.co/rinna/gemma-2-baku-2b-it}
}

@inproceedings{sawada2024release,
    title = {Release of Pre-Trained Models for the {J}apanese Language},
    author = {Sawada, Kei and Zhao, Tianyu and Shing, Makoto and Mitsui, Kentaro and Kaga, Akio and Hono, Yukiya and Wakatsuki, Toshiaki and Mitsuda, Koh},
    booktitle = {Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)},
    month = {5},
    year = {2024},
    pages = {13898--13905},
    url = {https://aclanthology.org/2024.lrec-main.1213},
    note = {\url{https://arxiv.org/abs/2404.01657}}
}

References

@article{gemma-2-2024,
    title = {Gemma 2},
    url = {https://www.kaggle.com/models/google/gemma-2},
    publisher = {Kaggle},
    author = {Gemma Team},
    year = {2024}
}

@article{huang2023chat,
    title = {Chat Vector: A Simple Approach to Equip LLMs with Instruction Following and Model Alignment in New Languages},
    author = {Huang, Shih-Cheng and Li, Pin-Zu and Hsu, Yu-Chi and Chen, Kuang-Ming and Lin, Yu Tung and Hsiao, Shih-Kai and Tzong-Han Tsai, Richard and Lee, Hung-yi},
    year = {2023},
    url = {https://arxiv.org/abs/2310.04799}
}

@article{hong2024orpo,
  title = {ORPO: Monolithic Preference Optimization without Reference Model},
  author = {Hong, Jiwoo and Lee, Noah and Thorne, James},
  year = {2024},
  url = {https://arxiv.org/abs/2403.07691}
}