base_model:
- INSAIT-Institute/BgGPT-Gemma-2-2.6B-IT-v1.0
language:
- bg
license: cc-by-4.0
tags:
- function_calling
- MCP
- tool_use
pipeline_tag: text-generation
library_name: transformers
Tucan-2.6B-v1.0-LoRA
Bulgarian Language Models for Function Calling 🇧🇬
This model is presented in the paper Teaching a Language Model to Speak the Language of Tools. Paper: https://arxiv.org/abs/2506.23394 Code: https://github.com/llm-bg/Tucan-Eval
Overview 🚀
External tool integration through function-calling is essential for practical language model applications, yet most multilingual models lack reliable tool-use capabilities in non-English languages. Even state-of-the-art multilingual models struggle with determining when to use tools and generating the structured outputs required for function calls, often exhibiting language confusion when prompted in lower-resource languages. This work presents a methodology for adapting existing language models to enable robust tool use in any target language, using Bulgarian as a case study. The approach involves continued training of the BgGPT model series (2.6B, 9B, 27B parameters) on a novel bilingual dataset of 10,035 function-calling examples designed to support standardized protocols like MCP (Model Context Protocol). The research introduces TUCAN (Tool-Using Capable Assistant Navigator), which achieves up to 28.75% improvement in function-calling accuracy over base models while preserving core language understanding, as verified on established Bulgarian benchmarks. Beyond accuracy gains, TUCAN models demonstrate production-ready response formatting with clean, parsable function calls, contrasting with the verbose and inconsistent outputs of base models. The models, evaluation framework, and dataset are released to enable replication for other languages. This work demonstrates a practical approach for extending tool-augmented capabilities beyond English-centric systems.
TUCAN (Tool-Using Capable Assistant Navigator) is a series of open-source Bulgarian language models fine-tuned specifically for function calling and tool use.
These models can interact with external tools, APIs, and databases, making them appropriate for building AI agents and Model Context Protocol (MCP) applications.
Built on top of BgGPT models from INSAIT Institute, these models have been enhanced with function-calling capabilities.
Motivation 🎯
Although BgGPT models demonstrate strong Bulgarian language comprehension, they face challenges in maintaining the precise formatting necessary for consistent function calling. Despite implementing detailed system prompts, their performance in this specific task remains suboptimal.
This project addresses that gap by fine-tuning BgGPT, providing the Bulgarian AI community with proper tool-use capabilities in their native language.
Models and variants 📦
Available in three sizes with full models, LoRA adapters, and quantized GGUF variants:
| Model Size | Full Model | LoRA Adapter | GGUF (Quantized) |
|---|---|---|---|
| 2.6B | Tucan-2.6B-v1.0 | LoRA 📍 | GGUF |
| 9B | Tucan-9B-v1.0 | LoRA | GGUF |
| 27B | Tucan-27B-v1.0 | LoRA | GGUF |
GGUF variants include: q4_k_m, q5_k_m, q6_k, q8_0, q4_0 quantizations
Usage 🛠️
Quick Start ⚡
pip install -U "transformers[torch]" accelerate bitsandbytes
Prompt format ⚙️
Critical: Use this format for function calling for the best results.
📋 Required System Prompt Template
<bos><start_of_turn>user
Ти си полезен AI асистент, който предоставя полезни и точни отговори.
Имаш достъп и можеш да извикаш една или повече функции, за да помогнеш с потребителското запитване. Използвай ги, само ако е необходимо и подходящо.
Когато използваш функция, форматирай извикването ѝ в блок ```tool_call``` на отделен ред, a след това ще получиш резултат от изпълнението в блок ```toll_response```.
## Шаблон за извикване:
```tool_call
{"name": <function-name>, "arguments": <args-json-object>}```
## Налични функции:
[your function definitions here]
## Потребителска заявка :
[your query in Bulgarian]<end_of_turn>
<start_of_turn>model
Note 📝
The model only generates the tool_call blocks with function names and parameters - it doesn't actually execute the functions. Your client application must parse these generated calls, execute the actual functions (API calls, database queries, etc.), and provide the results back to the model in tool_response blocks for the conversation to continue the interperation of the results. A full demo is comming soon.
Python example 🐍
💻 Complete Working Example
import torch
import json
from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig
# Load model
model_name = "s-emanuilov/Tucan-2.6B-v1.0"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype=torch.bfloat16,
device_map="auto",
attn_implementation="eager" # Required for Gemma models
)
# Create prompt with system template
def create_prompt(functions, user_query):
system_prompt = """Ти си полезен AI асистент, който предоставя полезни и точни отговори.
Имаш достъп и можеш да извикаш една или повече функции, за да помогнеш с потребителското запитване. Използвай ги, само ако е необходимо и подходящо.
Когато използваш функция, форматирай извикването ѝ в блок ```tool_call``` на отделен ред, a след това ще получиш резултат от изпълнението в блок ```toll_response```.
## Шаблон за извикване:
```tool_call
{{"name": <function-name>, "arguments": <args-json-object>}}```
"""
functions_text = json.dumps(functions, ensure_ascii=False, indent=2)
full_prompt = f"{system_prompt}
## Налични функции:
{functions_text}
## Потребителска заявка:
{user_query}"
chat = [{"role": "user", "content": full_prompt}]
return tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)
# Example usage
functions = [{
"name": "create_calendar_event",
"description": "Creates a new event in Google Calendar.",
"parameters": {
"type": "object",
"properties": {
"title": {"type": "string"},
"date": {"type": "string"},
"start_time": {"type": "string"},
"end_time": {"type": "string"}
},
"required": ["title", "date", "start_time", "end_time"]
}
}]
query = "Създай събитие 'Годишен преглед' за 8-ми юни 2025 от 14:00 до 14:30."
# Generate response
prompt = create_prompt(functions, query)
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(
**inputs,
max_new_tokens=1024,
temperature=0.1,
top_k=25,
top_p=1.0,
repetition_penalty=1.1,
do_sample=True,
eos_token_id=[tokenizer.eos_token_id, tokenizer.convert_tokens_to_ids("<end_of_turn>")],
pad_token_id=tokenizer.eos_token_id
)
result = tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True)
print(result)
Performance & Dataset 📊
📄 Full methodology, dataset details, and comprehensive evaluation results coming in the upcoming paper
Dataset: 8,000+ bilingual (Bulgarian/English) function-calling examples across 1,000+ topics, including tool calls with single/multiple arguments, optional parameters, follow-up queries, multi-tool selection, ambiguous queries requiring clarification, and conversational interactions without tool use. Data sourced from manual curation and synthetic generation (Gemini Pro 2.5/GPT-4.1/Sonnet 4).
Results: ~40% improvement in tool-use capabilities over base BgGPT models in internal benchmarks.
Questions & Contact 💬
For questions, collaboration, or feedback: Connect on LinkedIn
Acknowledgments 🙏
Built on top of BgGPT series.
License 📄
This work is licensed under CC-BY-4.0.