Instructions to use Veol-CZ/czech-semantic-embeddings-c with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Veol-CZ/czech-semantic-embeddings-c with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Veol-CZ/czech-semantic-embeddings-c",
	filename="Seznam__dist-mpnet-paracrawl-cs-en.f16.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 Veol-CZ/czech-semantic-embeddings-c 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 Veol-CZ/czech-semantic-embeddings-c:F16
# Run inference directly in the terminal:
llama cli -hf Veol-CZ/czech-semantic-embeddings-c:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Veol-CZ/czech-semantic-embeddings-c:F16
# Run inference directly in the terminal:
llama cli -hf Veol-CZ/czech-semantic-embeddings-c: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 Veol-CZ/czech-semantic-embeddings-c:F16
# Run inference directly in the terminal:
./llama-cli -hf Veol-CZ/czech-semantic-embeddings-c: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 Veol-CZ/czech-semantic-embeddings-c:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Veol-CZ/czech-semantic-embeddings-c:F16

Use Docker

docker model run hf.co/Veol-CZ/czech-semantic-embeddings-c:F16

LM Studio
Jan
Ollama
How to use Veol-CZ/czech-semantic-embeddings-c with Ollama:
```
ollama run hf.co/Veol-CZ/czech-semantic-embeddings-c:F16
```

Unsloth Studio

How to use Veol-CZ/czech-semantic-embeddings-c 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 Veol-CZ/czech-semantic-embeddings-c 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 Veol-CZ/czech-semantic-embeddings-c to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Veol-CZ/czech-semantic-embeddings-c to start chatting

Atomic Chat new
Docker Model Runner
How to use Veol-CZ/czech-semantic-embeddings-c with Docker Model Runner:
```
docker model run hf.co/Veol-CZ/czech-semantic-embeddings-c:F16
```

Lemonade

How to use Veol-CZ/czech-semantic-embeddings-c with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Veol-CZ/czech-semantic-embeddings-c:F16

Run and chat with the model

lemonade run user.czech-semantic-embeddings-c-F16

List all available models

lemonade list

Czech Semantic Embeddings (GGUF)

GGUF conversions of Czech semantic embedding models from Seznam, prepared for llama.cpp embedding inference.

Included Models

Seznam__retromae-small-cs.f16.gguf
Seznam__retromae-small-cs.q8_0.gguf
Seznam__dist-mpnet-paracrawl-cs-en.f16.gguf
Seznam__dist-mpnet-paracrawl-cs-en.q8_0.gguf
Seznam__simcse-retromae-small-cs.f16.gguf
Seznam__simcse-retromae-small-cs.q8_0.gguf
Seznam__simcse-dist-mpnet-paracrawl-cs-en.f16.gguf
Seznam__simcse-dist-mpnet-paracrawl-cs-en.q8_0.gguf

Upstream Sources

Citation

If you use these models, please cite the original Seznam paper:

Bednar et al., 2024, Some Like It Small: Czech Semantic Embedding Models for Industry Applications
https://arxiv.org/abs/2311.13921

@inproceedings{bednavr2024some,
  title={Some Like It Small: Czech Semantic Embedding Models for Industry Applications},
  author={Bedn{\'a}{\v{r}}, Ji{\v{r}}{\'\i} and N{\'a}plava, Jakub and Baran{\v{c}}{\'\i}kov{\'a}, Petra and Lisick{\`y}, Ond{\v{r}}ej},
  booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
  volume={38},
  number={21},
  pages={22734--22742},
  year={2024}
}

Usage (llama.cpp)

Run embedding server:

llama-server -m Seznam__retromae-small-cs.q8_0.gguf --embedding --pooling cls

OpenAI-compatible embeddings endpoint:

curl http://127.0.0.1:8080/v1/embeddings \
  -H "Content-Type: application/json" \
  -d '{"input":["Ahoj svete","Semantic search test"]}'

File Integrity

SHA256 checksums are in checksums.txt.

License

This repo contains converted checkpoints from upstream models. Respect original model licenses and terms:

retromae-small-cs: CC-BY-4.0
dist-mpnet-paracrawl-cs-en: CC-BY-4.0
simcse-retromae-small-cs: CC-BY-4.0
simcse-dist-mpnet-paracrawl-cs-en: CC-BY-4.0

Attribution to Seznam and original model cards is required.

Downloads last month: 13

GGUF

Model size

24.3M params

Architecture

bert

Hardware compatibility

8-bit

16-bit

Paper for Veol-CZ/czech-semantic-embeddings-c

Some Like It Small: Czech Semantic Embedding Models for Industry Applications

Paper • 2311.13921 • Published Nov 23, 2023