Instructions to use grapevine-AI/sarashina2-70b-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use grapevine-AI/sarashina2-70b-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="grapevine-AI/sarashina2-70b-gguf",
	filename="sarashina2-70B-BF16-00001-of-00003.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use grapevine-AI/sarashina2-70b-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/sarashina2-70b-gguf:BF16
# Run inference directly in the terminal:
llama-cli -hf grapevine-AI/sarashina2-70b-gguf:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf grapevine-AI/sarashina2-70b-gguf:BF16
# Run inference directly in the terminal:
llama-cli -hf grapevine-AI/sarashina2-70b-gguf:BF16

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/sarashina2-70b-gguf:BF16
# Run inference directly in the terminal:
./llama-cli -hf grapevine-AI/sarashina2-70b-gguf:BF16

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/sarashina2-70b-gguf:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf grapevine-AI/sarashina2-70b-gguf:BF16

Use Docker

docker model run hf.co/grapevine-AI/sarashina2-70b-gguf:BF16

LM Studio
Jan
Ollama
How to use grapevine-AI/sarashina2-70b-gguf with Ollama:
```
ollama run hf.co/grapevine-AI/sarashina2-70b-gguf:BF16
```

Unsloth Studio

How to use grapevine-AI/sarashina2-70b-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/sarashina2-70b-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/sarashina2-70b-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/sarashina2-70b-gguf to start chatting

Docker Model Runner
How to use grapevine-AI/sarashina2-70b-gguf with Docker Model Runner:
```
docker model run hf.co/grapevine-AI/sarashina2-70b-gguf:BF16
```

Lemonade

How to use grapevine-AI/sarashina2-70b-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull grapevine-AI/sarashina2-70b-gguf:BF16

Run and chat with the model

lemonade run user.sarashina2-70b-gguf-BF16

List all available models

lemonade list

What is this?

SB Intuitionsによる日本語特化の言語モデルsarashina2-70bをGGUFフォーマットに変換したものです。
なお、Instruction Tuningが施されていないピュアな状態の言語モデルですのでご注意ください。

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、計算リソースの関係上imatrixの算出においてはQ8_0量子化モデルを使用しました。

Environment

Windows版llama.cpp-b3621およびllama.cpp-b3472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

MIT License

Developer

SB Intuitions

Downloads last month: 34

GGUF

Model size

70B params

Architecture

llama

Hardware compatibility

4-bit

16-bit

Inference Providers NEW

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