Instructions to use Impulse2000/multilingual-e5-large-instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Impulse2000/multilingual-e5-large-instruct-GGUF with sentence-transformers:

from sentence_transformers import SentenceTransformer

model = SentenceTransformer("Impulse2000/multilingual-e5-large-instruct-GGUF")

sentences = [
    "The weather is lovely today.",
    "It's so sunny outside!",
    "He drove to the stadium."
]
embeddings = model.encode(sentences)

similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Transformers

How to use Impulse2000/multilingual-e5-large-instruct-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("feature-extraction", model="Impulse2000/multilingual-e5-large-instruct-GGUF")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Impulse2000/multilingual-e5-large-instruct-GGUF", dtype="auto")

llama-cpp-python

How to use Impulse2000/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="Impulse2000/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 Impulse2000/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 Impulse2000/multilingual-e5-large-instruct-GGUF:F16
# Run inference directly in the terminal:
llama-cli -hf Impulse2000/multilingual-e5-large-instruct-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Impulse2000/multilingual-e5-large-instruct-GGUF:F16
# Run inference directly in the terminal:
llama-cli -hf Impulse2000/multilingual-e5-large-instruct-GGUF:F16

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 Impulse2000/multilingual-e5-large-instruct-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf Impulse2000/multilingual-e5-large-instruct-GGUF:F16

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 Impulse2000/multilingual-e5-large-instruct-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Impulse2000/multilingual-e5-large-instruct-GGUF:F16

Use Docker

docker model run hf.co/Impulse2000/multilingual-e5-large-instruct-GGUF:F16

LM Studio
Jan
Ollama
How to use Impulse2000/multilingual-e5-large-instruct-GGUF with Ollama:
```
ollama run hf.co/Impulse2000/multilingual-e5-large-instruct-GGUF:F16
```

Unsloth Studio new

How to use Impulse2000/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 Impulse2000/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 Impulse2000/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 Impulse2000/multilingual-e5-large-instruct-GGUF to start chatting

Docker Model Runner
How to use Impulse2000/multilingual-e5-large-instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/Impulse2000/multilingual-e5-large-instruct-GGUF:F16
```

Lemonade

How to use Impulse2000/multilingual-e5-large-instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Impulse2000/multilingual-e5-large-instruct-GGUF:F16

Run and chat with the model

lemonade run user.multilingual-e5-large-instruct-GGUF-F16

List all available models

lemonade list

Impulse2000/multilingual-e5-large-instruct-GGUF

This model was converted to GGUF format from intfloat/multilingual-e5-large-instruct using llama.cpp via its 'convert_hf_to_gguf.py' script. Refer to the original model card for more details on the model.

Downloads last month: 6

GGUF

Model size

0.6B params

Architecture

bert

Hardware compatibility

8-bit

16-bit

Model tree for Impulse2000/multilingual-e5-large-instruct-GGUF

Base model

intfloat/multilingual-e5-large-instruct

Quantized

(24)

this model

Evaluation results

accuracy on MTEB AmazonCounterfactualClassification (en)
test set self-reported

76.239
ap on MTEB AmazonCounterfactualClassification (en)
test set self-reported

39.074
f1 on MTEB AmazonCounterfactualClassification (en)
test set self-reported

70.048
accuracy on MTEB AmazonCounterfactualClassification (de)
test set self-reported

66.713
ap on MTEB AmazonCounterfactualClassification (de)
test set self-reported

79.015
f1 on MTEB AmazonCounterfactualClassification (de)
test set self-reported

64.820
accuracy on MTEB AmazonCounterfactualClassification (en-ext)
test set self-reported

73.853
ap on MTEB AmazonCounterfactualClassification (en-ext)
test set self-reported

22.448
f1 on MTEB AmazonCounterfactualClassification (en-ext)
test set self-reported

61.016
accuracy on MTEB AmazonCounterfactualClassification (ja)
test set self-reported

76.049
ap on MTEB AmazonCounterfactualClassification (ja)
test set self-reported

23.450
f1 on MTEB AmazonCounterfactualClassification (ja)
test set self-reported

62.572
accuracy on MTEB AmazonPolarityClassification
test set self-reported

96.287
ap on MTEB AmazonPolarityClassification
test set self-reported

94.845
f1 on MTEB AmazonPolarityClassification
test set self-reported

96.287
accuracy on MTEB AmazonReviewsClassification (en)
test set self-reported

56.716