Instructions to use TFMC/Japanese-Starling-ChatV-7B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TFMC/Japanese-Starling-ChatV-7B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="TFMC/Japanese-Starling-ChatV-7B-GGUF",
	filename="japanese-starling-chatv-7b.Q4_K_M.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use TFMC/Japanese-Starling-ChatV-7B-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 TFMC/Japanese-Starling-ChatV-7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf TFMC/Japanese-Starling-ChatV-7B-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 TFMC/Japanese-Starling-ChatV-7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf TFMC/Japanese-Starling-ChatV-7B-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 TFMC/Japanese-Starling-ChatV-7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf TFMC/Japanese-Starling-ChatV-7B-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 TFMC/Japanese-Starling-ChatV-7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf TFMC/Japanese-Starling-ChatV-7B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/TFMC/Japanese-Starling-ChatV-7B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use TFMC/Japanese-Starling-ChatV-7B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TFMC/Japanese-Starling-ChatV-7B-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TFMC/Japanese-Starling-ChatV-7B-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TFMC/Japanese-Starling-ChatV-7B-GGUF:Q4_K_M

Ollama
How to use TFMC/Japanese-Starling-ChatV-7B-GGUF with Ollama:
```
ollama run hf.co/TFMC/Japanese-Starling-ChatV-7B-GGUF:Q4_K_M
```

Unsloth Studio

How to use TFMC/Japanese-Starling-ChatV-7B-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 TFMC/Japanese-Starling-ChatV-7B-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 TFMC/Japanese-Starling-ChatV-7B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for TFMC/Japanese-Starling-ChatV-7B-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use TFMC/Japanese-Starling-ChatV-7B-GGUF with Docker Model Runner:
```
docker model run hf.co/TFMC/Japanese-Starling-ChatV-7B-GGUF:Q4_K_M
```

Lemonade

How to use TFMC/Japanese-Starling-ChatV-7B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull TFMC/Japanese-Starling-ChatV-7B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Japanese-Starling-ChatV-7B-GGUF-Q4_K_M

List all available models

lemonade list

Japanese-Starling-ChatV-7B-GGUF

GGUF conversion of "Japanese-Starling-ChatV-7B"

"Japanese-Starling-ChatV-7B" is a Japanese chat model built on top of "chatntq-ja-7b-v1.0", originally based on Mistral-7B-v0.1. I applied the chat vector acquired by subtracting the weights of Mistral-7B-v0.1 from the weights of "Starling-LM-7B-beta" to this model.

このモデルはchatntq-ja-7b-v1.0をベースにした7Bパラメータの日本語チャットモデルです。高性能の英語モデルであるStarling-LM-7B-betaの重みからMistral-7B-v0.1の重みを差し引くことで得たchat vectorを適用しています（ブログ記事）。

Performance

Model (Q8_0 quant)	c4ai-command-r-v01-GGUF	JA-Starling-ChatV-7B-GGUF (This model)	ChatNTQ-JA-7b-v1.0-GGUF	RakutenAI-7B-chat-gguf	ELYZA-japanese-Llama-2-7b-instruct-gguf
Parameters	35B	7B(Mistral)	7B(Mistral)	7B(Mistral)	7B(Llama-2)
ELYZAtasks100 average score	3.42	3.42	3.06	2.82	2.46

Scores on "ELYZA-tasks-100" benchmark for the instruction-tuned Japanese models evaluated by GPT-4-0125-preview. Please note that this is a simplified evaluation using the Q8 quantized models.

このスコアはinstruction-tuningを行った日本語モデルのベンチマーク「ELYZA-tasks-100」を使い、GPT-4-0125-previewにより評価させたものです。Q8量子化モデルを用いた簡易的な評価であることにご留意ください。

Prompt Template

[INST] <<SYS>>\nあなたは役に立つアシスタントです。\n<</SYS>>\n\n{prompt} [/INST]

Downloads last month: 119

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

4-bit

5-bit

6-bit

8-bit

16-bit