🚀 Zlatorog-12B-Instruct-Beta
This model is a fine - tuned version of zidsi/MistralNemoCPT6 on a custom mix of SFT datasets, designed for high - quality instruction following, reasoning, and tool - augmented generation tasks.
📚 Documentation
Model Description
This model is based on Mistral Nemo 12B and has gone through multiple refinement stages, including Continual Pretraining (CPT) and Supervised Fine - Tuning (SFT) with an instruction - tuned objective. It is optimized for both language understanding and function - calling scenarios, aiming at high - quality instruction following, reasoning, and tool - augmented generation tasks.
Intended Uses & Limitations
Use this model for research, exploration, and have fun with Slovenian LLM :)
Training and Evaluation Data
The results on standard Slovenian benchmarks are not ideal but it sometimes gives impressive responses to "real - world" prompts. It has a reduced hallucination rate on "Who is ...?" prompts. Up to 16k ctx should work fine, and for longer contexts, more training data is needed to improve at the CPT Long stage.
Tool Usage
This model supports tool - augmented generation, enabling it to invoke external tools via structured function calls based on user prompts. The tool usage follows a special tokenized format, with tool availability declared at the beginning of the prompt and a corresponding tool call generated in the model's output.
Example
Input (Prompt):
<s>[AVAILABLE_TOOLS][{"type": "function", "function": {"name": "poisci_novice", "description": "Orodje poišče današnje novice glede na iskalni niz - ključne besede v besedilu.", "parameters": {"type": "object", "properties": {"iskalni_niz": {"type": "string", "description": "Iskalni niz za iskanje novic."}}, "required": ["iskalni_niz"]}}}][/AVAILABLE_TOOLS][INST]Naredi seznam današnjih novic o velikih jezikovnih modelih.[/INST]
Model Output:
[TOOL_CALLS][{"name": "poisci_novice", "arguments": {"iskalni_niz": "veliki jezikovni modeli"}}]
How It Works
- [AVAILABLE_TOOLS]: Declares the tools the model can call, formatted as JSON.
- [INST]...[/INST]: Wraps the user instruction or prompt.
- [TOOL_CALLS]: The model responds with structured tool calls matching the declared API.
This format is suitable for integration into multi - tool agents or custom orchestration pipelines where the model determines and delegates external functions.
Tool Call Schema
Tool definitions follow the [OpenAI function calling specification](https://platform.openai.com/docs/guides/gpt/function - calling), using a JSON Schema
to define parameters and their constraints.
License
This model is released under the Creative Commons Attribution - NonCommercial - NoDerivatives 4.0 International (CC BY - NC - ND 4.0) license.
- Attribution: You must give attribution to the original author.
- NonCommercial: Only non - commercial use is permitted. Commercial use is not allowed under this license.
- NoDerivatives: You may not share adaptations of the model.
For commercial use, custom development, or to request extended rights, please send an email to info <at> zid.si.
More details on the license: [https://creativecommons.org/licenses/by - nc - nd/4.0/](https://creativecommons.org/licenses/by - nc - nd/4.0/)
Support Future Research
The developer is currently seeking funding to continue research and development on this model and related projects. If you're interested in supporting or collaborating, please get in touch.
📄 Citation
If you use Zlatorog - 12B - Instruct - Beta in your research or applications, please cite it as follows:
BibTeX
@misc{zlatorog12b2025,
title = {Zlatorog-12B-Instruct-Beta: A Slovenian Instruction-Tuned Large Language Model},
author = {Tomaž Savodnik, Zavod za informacijsko družbo (zID)},
year = {2025},
howpublished = {\url{https://huggingface.co/zID4si/Zlatorog-12B-Instruct-Beta}},
note = {Version Beta}
}
APA
Savodnik, T., Zavod za informacijsko družbo (zID). (2025). Zlatorog - 12B - Instruct - Beta: A Slovenian Instruction - Tuned Large Language Model [Computer software]. Hugging Face. [https://huggingface.co/zID4si/Zlatorog - 12B - Instruct - Beta](https://huggingface.co/zID4si/Zlatorog - 12B - Instruct - Beta)
📦 Information Table
Property |
Details |
Library Name |
transformers |
License |
Creative Commons Attribution - NonCommercial - NoDerivatives 4.0 International (CC BY - NC - ND 4.0) |
Base Model |
zidsi/MistralNemoCPT6 |
Tags |
full, generated_from_trainer |
Language |
sl, en |
Pipeline Tag |
text - generation |
Extra Gated Heading |
Acknowledge license to accept the repository |
Extra Gated Description |
Our team may take few days to process your request |
Extra Gated Button Content |
Acknowledge license |
Extra Gated Prompt |
You agree to not use the model to conduct experiments that cause harm to human subjects. |
Extra Gated Fields |
Company (text), Country (country), Specific date (date_picker), I want to use this model for (select: Research, Education, Other), I agree to use this model for non - commercial use ONLY (checkbox) |