Instructions to use grapevine-AI/gemma-2-9b-it-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use grapevine-AI/gemma-2-9b-it-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="grapevine-AI/gemma-2-9b-it-gguf",
	filename="gemma-2-9b-it-IQ4_XS.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use grapevine-AI/gemma-2-9b-it-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf grapevine-AI/gemma-2-9b-it-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf grapevine-AI/gemma-2-9b-it-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf grapevine-AI/gemma-2-9b-it-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf grapevine-AI/gemma-2-9b-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 grapevine-AI/gemma-2-9b-it-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf grapevine-AI/gemma-2-9b-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 grapevine-AI/gemma-2-9b-it-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf grapevine-AI/gemma-2-9b-it-gguf:Q4_K_M

Use Docker

docker model run hf.co/grapevine-AI/gemma-2-9b-it-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use grapevine-AI/gemma-2-9b-it-gguf with Ollama:
```
ollama run hf.co/grapevine-AI/gemma-2-9b-it-gguf:Q4_K_M
```

Unsloth Studio new

How to use grapevine-AI/gemma-2-9b-it-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 grapevine-AI/gemma-2-9b-it-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 grapevine-AI/gemma-2-9b-it-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for grapevine-AI/gemma-2-9b-it-gguf to start chatting

Docker Model Runner
How to use grapevine-AI/gemma-2-9b-it-gguf with Docker Model Runner:
```
docker model run hf.co/grapevine-AI/gemma-2-9b-it-gguf:Q4_K_M
```

Lemonade

How to use grapevine-AI/gemma-2-9b-it-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull grapevine-AI/gemma-2-9b-it-gguf:Q4_K_M

Run and chat with the model

lemonade run user.gemma-2-9b-it-gguf-Q4_K_M

List all available models

lemonade list

What is this?

Googleの言語モデルgemma-2-9b-itをGGUFフォーマットに変換したものです。
また、一連の作業前にllama.cppのトークナイザテスト機能(#8248)にて動作の正確性の確認を行いました。

テスト内容

python convert_hf_to_gguf_update.py <hf_token>
python convert_hf_to_gguf.py models/tokenizers/gemma-2/ --outfile models/ggml-vocab-gemma-2.gguf --vocab-only
test-tokenizer-0 models/ggml-vocab-gemma-2.gguf

imatrix dataset

日本語能力を重視し、日本語が多量に含まれるTFMC/imatrix-dataset-for-japanese-llmデータセットを使用しました。
なお、imatrixの算出においてはf32精度のモデルを使用しました。これは、本来の数値精度であるbf16でのimatrix計算に現行のCUDA版llama.cppが対応していないためです。

Chat template

<start_of_turn>user
ここにpromptを書きます<end_of_turn>
<start_of_turn>model

Quants

各クオンツと必要と想定されるVRAM容量をまとめておきます。

クオンツ	VRAM
IQ4_XS	10GB
Q4_K_M	11GB
Q5_K_M	11GB
Q6_K	12GB
Q8_0	14GB
bf16	22GB

Note

llama.cpp-b3389以降と合わせてご利用ください。
なお、このモデル特有の処理であるAttention logit soft-cappingが存在するため、現状では-fa オプションによるFlash Attentionの使用はできません。

Environment

Windows版llama.cpp-b3389および同時リリースのconvert_hf_to_gguf.pyを使用して量子化作業を実施しました。

License

gemma license

Developer

Google

Downloads last month: 16

GGUF

Model size

9B params

Architecture

gemma2

Hardware compatibility

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support