Instructions to use yanolja/YanoljaNEXT-Rosetta-27B-2511-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yanolja/YanoljaNEXT-Rosetta-27B-2511-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="yanolja/YanoljaNEXT-Rosetta-27B-2511-GGUF",
	filename="BF16/YanoljaNEXT-Rosetta-27B-2511-bf16.gguf",
)

llm.create_chat_completion(
	messages = "\"Меня зовут Вольфганг и я живу в Берлине\""
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use yanolja/YanoljaNEXT-Rosetta-27B-2511-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf yanolja/YanoljaNEXT-Rosetta-27B-2511-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf yanolja/YanoljaNEXT-Rosetta-27B-2511-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 yanolja/YanoljaNEXT-Rosetta-27B-2511-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf yanolja/YanoljaNEXT-Rosetta-27B-2511-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 yanolja/YanoljaNEXT-Rosetta-27B-2511-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf yanolja/YanoljaNEXT-Rosetta-27B-2511-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 yanolja/YanoljaNEXT-Rosetta-27B-2511-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf yanolja/YanoljaNEXT-Rosetta-27B-2511-GGUF:Q4_K_M

Use Docker

docker model run hf.co/yanolja/YanoljaNEXT-Rosetta-27B-2511-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use yanolja/YanoljaNEXT-Rosetta-27B-2511-GGUF with Ollama:
```
ollama run hf.co/yanolja/YanoljaNEXT-Rosetta-27B-2511-GGUF:Q4_K_M
```

Unsloth Studio

How to use yanolja/YanoljaNEXT-Rosetta-27B-2511-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 yanolja/YanoljaNEXT-Rosetta-27B-2511-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 yanolja/YanoljaNEXT-Rosetta-27B-2511-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for yanolja/YanoljaNEXT-Rosetta-27B-2511-GGUF to start chatting

Docker Model Runner
How to use yanolja/YanoljaNEXT-Rosetta-27B-2511-GGUF with Docker Model Runner:
```
docker model run hf.co/yanolja/YanoljaNEXT-Rosetta-27B-2511-GGUF:Q4_K_M
```

Lemonade

How to use yanolja/YanoljaNEXT-Rosetta-27B-2511-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull yanolja/YanoljaNEXT-Rosetta-27B-2511-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.YanoljaNEXT-Rosetta-27B-2511-GGUF-Q4_K_M

List all available models

lemonade list

YanoljaNEXT-Rosetta-27B-2511

This model is a fine-tuned version of google/gemma-3-27b-pt. As it is intended solely for text generation, we have extracted and utilized only the Gemma3ForCausalLM component from the original architecture.

Unlike our previous EEVE models, this model does not feature an expanded tokenizer.

Model Name: yanolja/YanoljaNEXT-Rosetta-27B-2511
Base Model: google/gemma-3-27b-pt

GGUF files

This folder contains ready-to-run GGUF files for llama.cpp.

Quantized variants (choose one based on your device and quality needs):
- K-family: Q2_K, Q2_K_S, Q3_K_{S,M}, Q4_K_{S,M}, Q5_K_{S,M}, Q6_K, Q8_0
- IQ-family: IQ1_{S,M}, IQ2_{XXS,XS,S,M}, IQ3_{XXS,XS,S,M}, IQ4_{XS,NL}
_IMX variants are produced with an activation matrix (imatrix.gguf) and often offer better quality at the same size. Some lower-precision types may be IMX-only.

Model Description

This model is a 27-billion parameter, decoder-only language model built on the Gemma3 architecture and fine-tuned by Yanolja NEXT. It is specifically designed to translate structured data (JSON, YAML, XML formats) while preserving the original data structure.

The model was trained on a multilingual dataset covering the following languages equally:

Arabic
Bulgarian
Chinese
Czech
Danish
Dutch
English
Finnish
French
German
Greek
Gujarati
Hebrew
Hindi
Hungarian
Indonesian
Italian
Japanese
Korean
Persian
Polish
Portuguese
Romanian
Russian
Slovak
Spanish
Swedish
Tagalog
Thai
Turkish
Ukrainian
Vietnamese

While optimized for these languages, it may also perform effectively on other languages supported by the base Gemma3 model.

How to use

Use a recent build of llama.cpp that supports Gemma 3 models. Pick any GGUF file from this folder (a quantized variant is recommended for most users).

# Example: use a Q5_K_M quantized file (adjust the path/model to your choice)
MODEL="path/to/YanoljaNEXT-Rosetta-27B-2511-q5_k_m.gguf"

# Build a formatted prompt using the included chat template roles
# (see release/YanoljaNEXT-Rosetta-27B-2511/chat_template.jinja)
read -r -d '' PROMPT <<'EOT'
<start_of_turn>instruction
Translate the user's text to Korean. Keep the JSON structure and keys.
Context: Simple introduction about a tech company.
Tone: Informative and helpful
Glossary:
- Yanolja NEXT -> 야놀자넥스트
- travel industry -> 여행 산업
Provide the final translation immediately without any other text.
<end_of_turn>
<start_of_turn>source
{"company_name": "Yanolja NEXT", "description": "Yanolja NEXT is a company that provides cutting-edge technology for the global travel industry."}
<end_of_turn>
<start_of_turn>translation\n
EOT

# Run llama.cpp (adjust -n/-c/--temp as needed)
llama-cli -m "$MODEL" -p "$PROMPT" -n 64 -c 4096 --temp 0.7 -no-cnv

REST server

MODEL="path/to/YanoljaNEXT-Rosetta-27B-2511-q5_k_m.gguf"
llama-server -m "$MODEL" -c 4096 --host 0.0.0.0 --port 8080

LM Studio / other GUIs

Import any of the .gguf files into your GUI of choice (LM Studio, KoboldCPP, text-generation-webui) and select chat mode. The embedded template in the GGUF will be used automatically by recent tools.

The model outputs the final translation in the same structured format as the input (JSON, YAML, XML) when appropriate, or plain text for simple translations.

Training Procedure

Training Data

The translation datasets were synthesized using fineweb corpora.

The model was fine-tuned on synthetic multilingual translation data to optimize performance across the supported language pairs.

Performance

Translation Quality Benchmarks

The following CHrF++ scores (WMT24++) demonstrate the model's competitive performance compared to other state-of-the-art translation models on English to Korean translation:

Model	CHrF++ Score (WMT24++)
yanolja/YanoljaNEXT-Rosetta-12B-2510	37.36
yanolja/YanoljaNEXT-Rosetta-27B-2511	37.21
openai/gpt-4o	36.08
google/gemini-2.5-flash	35.25
tencent/Hunyuan-MT-7B	34.76
yanolja/YanoljaNEXT-Rosetta-12B	34.75
yanolja/YanoljaNEXT-Rosetta-20B	33.87
AIDC-AI/Marco-MT-Algharb	33.40
openai/gpt-oss-120b	31.51
ByteDance-Seed/Seed-X-PPO-7B	30.48
google/gemma-3-27b-it	30.05
google/gemma-3-12b-it	29.31

YanoljaNEXT-Rosetta-27B-2511 achieves strong translation quality while maintaining efficient inference for its parameter size. Scores for the other language pairs can be found in the WMT24++ Evaluation Results.

Intended Uses & Limitations

This model is intended for translating structured data (JSON, YAML, XML formats) while preserving the original structure. It is particularly well-suited for tasks such as localizing product catalogs, translating hotel reviews, or handling any other structured content that requires accurate translation.

Limitations

The model is primarily optimized for processing structured data (JSON, YAML, XML). Its performance on unstructured text or other data formats may vary. In some cases, the model may produce invalid structured outputs, repetitive output, or inaccurate translations.

License

This model is released under the Gemma license, inherited from its base architecture. Please consult the official Gemma license terms for detailed usage guidelines.

Acknowledgments

This work was supported by the Korea Creative Content Agency (KOCCA) grant, funded by the Ministry of Culture, Sports and Tourism (MCST) in 2025 (Project Name: Cultivating Masters and Doctoral Experts to Lead Digital-Tech Tourism, Project Number: RS-2024-00442006, Contribution Rate: 100%).

Citation

If you use this model, please consider citing:

@misc{yanolja2025yanoljanextrosetta27b,
  author = {Yanolja NEXT Co., Ltd.},
  title = {YanoljaNEXT-Rosetta-27B-2511},
  year = {2025},
  publisher = {Hugging Face},
  journal = {Hugging Face repository},
  howpublished = {\\url{https://huggingface.co/yanolja/YanoljaNEXT-Rosetta-27B-2511}}
}

References

This work utilizes several models and datasets. We would like to acknowledge the original authors for their valuable contributions to the field.

@misc{gemma3,
  author = {Google},
  title = {Gemma 3},
  year = {2024},
  publisher = {Google DeepMind},
  howpublished = {\\url{https://deepmind.google/models/gemma/gemma-3/}}
}

@misc{penedo2025fineweb2pipelinescale,
  title = {FineWeb2: One Pipeline to Scale Them All -- Adapting Pre-Training Data Processing to Every Language}, 
  author = {Guilherme Penedo and Hynek Kydlíček and Vinko Sabolčec and Bettina Messmer and Negar Foroutan and Amir Hossein Kargaran and Colin Raffel and Martin Jaggi and Leandro Von Werra and Thomas Wolf},
  year = {2025},
  eprint = {2506.20920},
  archivePrefix = {arXiv},
  primaryClass = {cs.CL},
  url = {https://arxiv.org/abs/2506.20920},
}

@misc{lozhkov2024fineweb-edu,
  author = {Lozhkov, Anton and Ben Allal, Loubna and von Werra, Leandro and Wolf, Thomas},
  title = {FineWeb-Edu: the Finest Collection of Educational Content},
  year = 2024,
  url = {https://huggingface.co/datasets/HuggingFaceFW/fineweb-edu},
  doi = {10.57967/hf/2497},
  publisher={Hugging Face}
}