Instructions to use umiyuki/Japanese-WizardLM2-ChatV-7B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use umiyuki/Japanese-WizardLM2-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 umiyuki/Japanese-WizardLM2-ChatV-7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf umiyuki/Japanese-WizardLM2-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 umiyuki/Japanese-WizardLM2-ChatV-7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf umiyuki/Japanese-WizardLM2-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 umiyuki/Japanese-WizardLM2-ChatV-7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf umiyuki/Japanese-WizardLM2-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 umiyuki/Japanese-WizardLM2-ChatV-7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf umiyuki/Japanese-WizardLM2-ChatV-7B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/umiyuki/Japanese-WizardLM2-ChatV-7B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use umiyuki/Japanese-WizardLM2-ChatV-7B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "umiyuki/Japanese-WizardLM2-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": "umiyuki/Japanese-WizardLM2-ChatV-7B-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/umiyuki/Japanese-WizardLM2-ChatV-7B-GGUF:Q4_K_M

Ollama
How to use umiyuki/Japanese-WizardLM2-ChatV-7B-GGUF with Ollama:
```
ollama run hf.co/umiyuki/Japanese-WizardLM2-ChatV-7B-GGUF:Q4_K_M
```

Unsloth Studio

How to use umiyuki/Japanese-WizardLM2-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 umiyuki/Japanese-WizardLM2-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 umiyuki/Japanese-WizardLM2-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 umiyuki/Japanese-WizardLM2-ChatV-7B-GGUF to start chatting

Docker Model Runner
How to use umiyuki/Japanese-WizardLM2-ChatV-7B-GGUF with Docker Model Runner:
```
docker model run hf.co/umiyuki/Japanese-WizardLM2-ChatV-7B-GGUF:Q4_K_M
```

Lemonade

How to use umiyuki/Japanese-WizardLM2-ChatV-7B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull umiyuki/Japanese-WizardLM2-ChatV-7B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Japanese-WizardLM2-ChatV-7B-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

Japanese-WizardLM2-ChatV-7B-GGUF

GGUF conversion of "Japanese-WizardLM2-ChatV-7B"

This model, Japanese-WizardLM2-ChatV-7B, is based on "chatntq-ja-7b-v1.0 ", and was created by subtracting "Mistral-7B-v0.1" from "WizardLM-2-7b" ChatVector was added by a factor of 1.0. We aimed to add the high performance of WizardLM-2 to the Japanese language capability of ChatNTQ.

このモデル、Japanese-WizardLM2-ChatV-7Bは、”chatntq-ja-7b-v1.0”をベースに、"WizardLM-2-7b"から"Mistral-7B-v0.1"を差し引いて作ったChatVectorを1.0倍で足しました。 ChatNTQの日本語能力にWizardLM-2の性能の高さが加わる事を狙いました。

Performance

Model	c4ai-command-r-plus(Cohere API)	JA-Starling-ChatV-7B-GGUF(fp16)	JA-WizardLM2-ChatV-7B-GGUF (This model)(fp16)	ChatNTQ-JA-7b-v1.0-GGUF(Q8_0)
Parameters	104B	7B(Mistral)	7B(Mistral)	7B(Mistral)
ELYZAtasks100 average score	4.04	3.77	3.40	2.74

This score was evaluated by Cohere API command-r-plus using the "ELYZA-tasks-100", a Japanese model with instruction-tuning.

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、Cohere APIのcommand-r-plusにより評価させたものです。

Prompt Template

Llama-2-Chat

[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: 175

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit