Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,24 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+BF16/YanoljaNEXT-Rosetta-4B-2510-bf16.gguf filter=lfs diff=lfs merge=lfs -text
+IQ2_M_IMX/YanoljaNEXT-Rosetta-4B-2510-bf16-iq2_m.gguf filter=lfs diff=lfs merge=lfs -text
+IQ2_S_IMX/YanoljaNEXT-Rosetta-4B-2510-bf16-iq2_s.gguf filter=lfs diff=lfs merge=lfs -text
+IQ3_S/YanoljaNEXT-Rosetta-4B-2510-bf16-iq3_s.gguf filter=lfs diff=lfs merge=lfs -text
+IQ3_S_IMX/YanoljaNEXT-Rosetta-4B-2510-bf16-iq3_s.gguf filter=lfs diff=lfs merge=lfs -text
+IQ3_XS_IMX/YanoljaNEXT-Rosetta-4B-2510-bf16-iq3_xs.gguf filter=lfs diff=lfs merge=lfs -text
+IQ3_XXS_IMX/YanoljaNEXT-Rosetta-4B-2510-bf16-iq3_xxs.gguf filter=lfs diff=lfs merge=lfs -text
+IQ4_XS/YanoljaNEXT-Rosetta-4B-2510-bf16-iq4_xs.gguf filter=lfs diff=lfs merge=lfs -text
+IQ4_XS_IMX/YanoljaNEXT-Rosetta-4B-2510-bf16-iq4_xs.gguf filter=lfs diff=lfs merge=lfs -text
+Q3_K_L/YanoljaNEXT-Rosetta-4B-2510-bf16-q3_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+Q3_K_L_IMX/YanoljaNEXT-Rosetta-4B-2510-bf16-q3_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+Q3_K_S/YanoljaNEXT-Rosetta-4B-2510-bf16-q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+Q3_K_S_IMX/YanoljaNEXT-Rosetta-4B-2510-bf16-q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+Q5_K_M/YanoljaNEXT-Rosetta-4B-2510-bf16-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+Q5_K_M_IMX/YanoljaNEXT-Rosetta-4B-2510-bf16-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+Q5_K_S/YanoljaNEXT-Rosetta-4B-2510-bf16-q5_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+Q5_K_S_IMX/YanoljaNEXT-Rosetta-4B-2510-bf16-q5_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+Q6_K/YanoljaNEXT-Rosetta-4B-2510-bf16-q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+Q6_K_IMX/YanoljaNEXT-Rosetta-4B-2510-bf16-q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+Q8_0/YanoljaNEXT-Rosetta-4B-2510-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+imatrix.gguf filter=lfs diff=lfs merge=lfs -text

BF16/YanoljaNEXT-Rosetta-4B-2510-bf16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbb764230144b1821196a85153863bd6d1622186b7635863394261c5d1e3ff0d
+size 7767803424

IQ2_M_IMX/YanoljaNEXT-Rosetta-4B-2510-bf16-iq2_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2d736fa59036a99d61ce88603a71498cd02787771e60fe395a7f0f23daee28f
+size 1537982336

IQ2_S_IMX/YanoljaNEXT-Rosetta-4B-2510-bf16-iq2_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b00dd9d60cd6ce3de37f2c2b3e51e770219f73d6ae958d751f4b67e3fead4570
+size 1449344896

IQ3_S/YanoljaNEXT-Rosetta-4B-2510-bf16-iq3_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:355c8ed24471dc5cf2831d24c9129b7e6481988c6018c5bcdc485a575923d480
+size 1937363744

IQ3_S_IMX/YanoljaNEXT-Rosetta-4B-2510-bf16-iq3_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb07d75fe7ea5e76aef2e5d64091e750e8bb22bc327c7cc08b2b80734e715d8f
+size 1937364096

IQ3_XS_IMX/YanoljaNEXT-Rosetta-4B-2510-bf16-iq3_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84babc42c4df9fab82dd013d3fab7b29dfe1313f6bb4ccbc97c5a3e05fd33afa
+size 1863390336

IQ3_XXS_IMX/YanoljaNEXT-Rosetta-4B-2510-bf16-iq3_xxs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f50df4eebe06688310932b72194cd608cb15156e38bdae327c36ff36c54d6543
+size 1689452416

IQ4_XS/YanoljaNEXT-Rosetta-4B-2510-bf16-iq4_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a17126b851b4156f15a50843b9b021b326e937133e0af6b73af329e68ef7c52f
+size 2279625504

IQ4_XS_IMX/YanoljaNEXT-Rosetta-4B-2510-bf16-iq4_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30ad4723abfd3e3c7f6a841ea35ea2c40b0b16032c6daf0a72f1e22f2fa6ccdb
+size 2263241856

Q3_K_L/YanoljaNEXT-Rosetta-4B-2510-bf16-q3_k_l.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d57a282315d6038351a8366e1caca95e7fe80b9babb270ad92593ac7cbf040c5
+size 2236085024

Q3_K_L_IMX/YanoljaNEXT-Rosetta-4B-2510-bf16-q3_k_l.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe3207c95deab1ed3f61f82f4b070a1ce0b01c20f4734555c78b1b57a140e82b
+size 2236085376

Q3_K_S/YanoljaNEXT-Rosetta-4B-2510-bf16-q3_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7eec0d732e1abc65aea1505705c673548586f0db5c10ac1d77479f7ff209680
+size 1937363744

Q3_K_S_IMX/YanoljaNEXT-Rosetta-4B-2510-bf16-q3_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43bde6fead1473f8de196c881892c70006980004db2b270ed4721de9327612db
+size 1937364096

Q5_K_M/YanoljaNEXT-Rosetta-4B-2510-bf16-q5_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7ccede291346cc2554445dca82085ffcdd0af1caad0a942614dd3d12a394d49
+size 2829697824

Q5_K_M_IMX/YanoljaNEXT-Rosetta-4B-2510-bf16-q5_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:526eac30c887b237756d5ac19a2858b3cd4e27319f147a3132e339c1f813b411
+size 2829698176

Q5_K_S/YanoljaNEXT-Rosetta-4B-2510-bf16-q5_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ded15e8caf82e1540a11a830cfdb627ad90fa8a4c4887818eba4e56adcefb64a
+size 2764591904

Q5_K_S_IMX/YanoljaNEXT-Rosetta-4B-2510-bf16-q5_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:929ff041fa7e892f7e08ab3fa65b19428b993c2ae5ec85ec9e9d819cf261d4d9
+size 2764592256

Q6_K/YanoljaNEXT-Rosetta-4B-2510-bf16-q6_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:245dcd73830c8c9a42e18b6db0c892c012014ee4855306bf3df625869e9c82f5
+size 3190739744

Q6_K_IMX/YanoljaNEXT-Rosetta-4B-2510-bf16-q6_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4db88b92e2ed9e2c3308b66c851faf31fddc3e0e674c7d5cd0a0680eff76136b
+size 3190740096

Q8_0/YanoljaNEXT-Rosetta-4B-2510-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85f9be4da1b4be0214dcaf2b21c5adb5af503a749dc5a2db66511f1f179b541b
+size 4130401824

README.md

@@ -0,0 +1,242 @@
+library_name: transformers
+tags:
+  - translation
+  - llama-cpp
+license: gemma
+language:
+  - ar
+  - bg
+  - zh
+  - cs
+  - da
+  - nl
+  - en
+  - fi
+  - fr
+  - de
+  - el
+  - gu
+  - he
+  - hi
+  - hu
+  - id
+  - it
+  - ja
+  - ko
+  - fa
+  - pl
+  - pt
+  - ro
+  - ru
+  - sk
+  - es
+  - sv
+  - tl
+  - th
+  - tr
+  - uk
+  - vi
+base_model: yanolja/YanoljaNEXT-Rosetta-12B-2510
+---
+
+# YanoljaNEXT-Rosetta-4B-2510
+
+<p style="text-align: center; margin: 0 auto 64px">
+  <img src="next_rosetta.png" style="width: 1096px">
+</p>
+
+This model is a fine-tuned version of [`google/gemma-3-4b-pt`](https://huggingface.co/google/gemma-3-4b-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-4B-2510`
+- **Base Model:** `google/gemma-3-4b-pt`
+
+## GGUF files
+
+This folder contains ready-to-run GGUF files for llama.cpp.
+
+- `BF16/YanoljaNEXT-Rosetta-4B-2510-bf16.gguf`: full-precision reference model
+- Quantized variants (choose one based on your device and quality needs):
+  - K-family: `Q3_K_{S,L}`, `Q5_K_{S,M}`, `Q6_K`, `Q8_0`
+  - IQ-family: `IQ2_{S,M}`, `IQ3_{XXS,XS,S}`, `IQ4_{XS}`
+- For many types there are matching `_IMX` folders. Files there were produced with an activation matrix (`imatrix.gguf`) and usually offer better quality at the same size. In this release, `IQ2_{S,M}` and `IQ3_{XXS,XS}` are IMX-only.
+
+## Model Description
+
+This model is a 4-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 format) 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).
+
+```bash
+# Example: use a Q5_K_M quantized file (adjust the path/model to your choice)
+MODEL="path/to/YanoljaNEXT-Rosetta-4B-2510-q5_k_m.gguf"
+
+# Build a formatted prompt using the included chat template roles
+# (see release/YanoljaNEXT-Rosetta-4B-2510/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
+```
+
+The model is optimized to output structured JSON for translations when appropriate.
+
+### REST server
+
+```bash
+MODEL="path/to/YanoljaNEXT-Rosetta-4B-2510-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.
+
+## Training Procedure
+
+### Training Data
+The translation datasets were synthesized using fineweb corpora.
+- [FineWeb Edu](https://huggingface.co/datasets/HuggingFaceFW/fineweb-edu)
+- [FineWeb2](https://huggingface.co/datasets/HuggingFaceFW/fineweb-2)
+
+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++) |
+|------------------------------------|--------------|
+| google/gemini-2.5-flash-lite       | 35.23 |
+| **yanolja/YanoljaNEXT-Rosetta-4B-2510** | **35.09**    |
+| yanolja/YanoljaNEXT-Rosetta-12B    | 34.75 |
+| yanolja/YanoljaNEXT-Rosetta-20B    | 33.87        |
+| google/gemini-2.0-flash-001        | 33.81        |
+| openai/gpt-oss-120b                | 31.51        |
+| **yanolja/YanoljaNEXT-Rosetta-4B** | **31.31**    |
+| openai/gpt-4.1-nano                | 31.15        |
+| Qwen/Qwen3-235B-A22B-Instruct-2507-FP8 | 31.02    |
+| openai/gpt-oss-20b                 |        30.56 |
+| google/gemma-3-27b-it              |        30.05 |
+| google/gemma-3-4b-pt               |        27.53 |
+
+YanoljaNEXT-Rosetta-4B-2510 achieves competitive translation quality while maintaining the efficiency of a 4B parameter model.
+Scores for the other language pairs can be found in the [WMT24++ Evaluation Results](wmt24pp_12b.md).
+
+## Intended Uses & Limitations
+
+This model is intended for translating structured data (JSON format) 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 JSON data.
+Its performance on unstructured text or other data formats may vary.
+In some cases, the model may produce invalid JSON, repetitive output, or inaccurate translations.
+
+### License
+This model is released under the Gemma license, inherited from its base model, [`google/gemma-3-4b-pt`](https://huggingface.co/google/gemma-3-4b-pt). Please consult the official [Gemma license terms](https://ai.google.dev/gemma/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{yanolja2025yanoljanextrosetta,
+  author = {Yanolja NEXT Co., Ltd.},
+  title = {YanoljaNEXT-Rosetta-4B-2510},
+  year = {2025},
+  publisher = {Hugging Face},
+  journal = {Hugging Face repository},
+  howpublished = {\\url{https://huggingface.co/yanolja/YanoljaNEXT-Rosetta-4B-2510}}
+}
+```
+
+## 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}
+}
+```

imatrix.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76e37ef58e1293da48ffb46003dad667d76e7159e1c750f8cb5b6e07f6611970
+size 3448672