Instructions to use Ralriki/multilingual-e5-large-instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ralriki/multilingual-e5-large-instruct-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Ralriki/multilingual-e5-large-instruct-GGUF",
	filename="multilingual-e5-large-instruct-F16.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 Ralriki/multilingual-e5-large-instruct-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Ralriki/multilingual-e5-large-instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Ralriki/multilingual-e5-large-instruct-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 Ralriki/multilingual-e5-large-instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Ralriki/multilingual-e5-large-instruct-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 Ralriki/multilingual-e5-large-instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Ralriki/multilingual-e5-large-instruct-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 Ralriki/multilingual-e5-large-instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Ralriki/multilingual-e5-large-instruct-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Ralriki/multilingual-e5-large-instruct-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use Ralriki/multilingual-e5-large-instruct-GGUF with Ollama:
```
ollama run hf.co/Ralriki/multilingual-e5-large-instruct-GGUF:Q4_K_M
```

Unsloth Studio

How to use Ralriki/multilingual-e5-large-instruct-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 Ralriki/multilingual-e5-large-instruct-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 Ralriki/multilingual-e5-large-instruct-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Ralriki/multilingual-e5-large-instruct-GGUF to start chatting

Docker Model Runner
How to use Ralriki/multilingual-e5-large-instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/Ralriki/multilingual-e5-large-instruct-GGUF:Q4_K_M
```

Lemonade

How to use Ralriki/multilingual-e5-large-instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Ralriki/multilingual-e5-large-instruct-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.multilingual-e5-large-instruct-GGUF-Q4_K_M

List all available models

lemonade list

The multilingual-e5 family is one of the best options for multilingual embedding models.

This is the GGUF version of https://huggingface.co/intfloat/multilingual-e5-large-instruct. Check out their prompt recommendations for different tasks!

It is supported since the XLMRoberta addition in llama.cpp was merged on 6th August 2024. https://github.com/ggerganov/llama.cpp/pull/8658

Currently q4_k_m, q6_k, q8_0 and f16 versions are available. I would recommend q6_k or q8_0. In general you barely have any performance loss going to 8-bit quantization from base models, while there usually is a small but noticable dropoff occuring somewhere between q6-q4. At some point the dropoff gets pretty massive going towards ~q3 or lower.

Downloads last month: 33,670

GGUF

Model size

0.6B params

Architecture

bert

Hardware compatibility

4-bit

6-bit

8-bit

16-bit

Inference Providers NEW

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