Instructions to use mmnga/webbigdata-ALMA-7B-Ja-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mmnga/webbigdata-ALMA-7B-Ja-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="mmnga/webbigdata-ALMA-7B-Ja-gguf",
	filename="webbigdata-ALMA-7B-Ja-q2_K.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 mmnga/webbigdata-ALMA-7B-Ja-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mmnga/webbigdata-ALMA-7B-Ja-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf mmnga/webbigdata-ALMA-7B-Ja-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 mmnga/webbigdata-ALMA-7B-Ja-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf mmnga/webbigdata-ALMA-7B-Ja-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 mmnga/webbigdata-ALMA-7B-Ja-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf mmnga/webbigdata-ALMA-7B-Ja-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 mmnga/webbigdata-ALMA-7B-Ja-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mmnga/webbigdata-ALMA-7B-Ja-gguf:Q4_K_M

Use Docker

docker model run hf.co/mmnga/webbigdata-ALMA-7B-Ja-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use mmnga/webbigdata-ALMA-7B-Ja-gguf with Ollama:
```
ollama run hf.co/mmnga/webbigdata-ALMA-7B-Ja-gguf:Q4_K_M
```

Unsloth Studio

How to use mmnga/webbigdata-ALMA-7B-Ja-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 mmnga/webbigdata-ALMA-7B-Ja-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 mmnga/webbigdata-ALMA-7B-Ja-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mmnga/webbigdata-ALMA-7B-Ja-gguf to start chatting

Docker Model Runner
How to use mmnga/webbigdata-ALMA-7B-Ja-gguf with Docker Model Runner:
```
docker model run hf.co/mmnga/webbigdata-ALMA-7B-Ja-gguf:Q4_K_M
```

Lemonade

How to use mmnga/webbigdata-ALMA-7B-Ja-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mmnga/webbigdata-ALMA-7B-Ja-gguf:Q4_K_M

Run and chat with the model

lemonade run user.webbigdata-ALMA-7B-Ja-gguf-Q4_K_M

List all available models

lemonade list

webbigdata-ALMA-7B-Ja-gguf

webbigdataさんが公開しているALMA-7B-Jaのggufフォーマット変換版です。

v1のggufの各量子化の評価がwebbigdataさんのblogで公開されています
webbigdata/１．日英・英日機械翻訳モデルALMA-7B-Ja-V2の公開

モデル一覧
mmnga/webbigdata-ALMA-7B-Ja-V2-gguf
mmnga/webbigdata-ALMA-7B-Ja-gguf

Usage

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
make -j
./main -m 'webbigdata-ALMA-7B-Ja-q4_0.gguf' -n 128 -p 'Translate this from Japanese to English:\nJapanese: 今日の夕食はピザです。\nEnglish:'

引用 Citations

@misc{xu2023paradigm,
      title={A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Models}, 
      author={Haoran Xu and Young Jin Kim and Amr Sharaf and Hany Hassan Awadalla},
      year={2023},
      eprint={2309.11674},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

Downloads last month: 99

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW

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

Paper for mmnga/webbigdata-ALMA-7B-Ja-gguf

A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Models

Paper • 2309.11674 • Published Sep 20, 2023 • 33