Instructions to use tbilisi-ai-lab/kona2-12B-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tbilisi-ai-lab/kona2-12B-Base with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="tbilisi-ai-lab/kona2-12B-Base")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tbilisi-ai-lab/kona2-12B-Base")
model = AutoModelForCausalLM.from_pretrained("tbilisi-ai-lab/kona2-12B-Base")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use tbilisi-ai-lab/kona2-12B-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tbilisi-ai-lab/kona2-12B-Base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tbilisi-ai-lab/kona2-12B-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tbilisi-ai-lab/kona2-12B-Base

SGLang

How to use tbilisi-ai-lab/kona2-12B-Base with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "tbilisi-ai-lab/kona2-12B-Base" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tbilisi-ai-lab/kona2-12B-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "tbilisi-ai-lab/kona2-12B-Base" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tbilisi-ai-lab/kona2-12B-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tbilisi-ai-lab/kona2-12B-Base with Docker Model Runner:
```
docker model run hf.co/tbilisi-ai-lab/kona2-12B-Base
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Kona2-12B-Base

Kona2-12B-Base is a 12-billion parameter base language model optimized for Georgian language understanding and generation. It is built by continue-pretraining Mistral-Nemo-Base-2407 on approximately 30 billion tokens of Georgian/English data with expanded Georgian vocabulary.

Model Summary

Property	Value
Parameters	12B
Architecture	Mistral (Transformer)
Context Length	8K tokens
Vocabulary	Extended (~20K Georgian tokens)
Languages	Georgian (ka), English (en), other (limited)
Training Tokens	~30B
Training	Continue pre-training (embeddings + high-rank LoRA)
Base Model	mistralai/Mistral-Nemo-Base-2407

Intended Uses

Primary Use Cases

Base model for Georgian language fine-tuning
Georgian text generation and completion
Multilingual text understanding (KA/EN primary, others limited)
Foundation for instruction-tuned models
Translation capabilities (enhanced in fine-tuned versions)

Training

Training Data (~30B Tokens)

Open source corpora
Web content (custom crawlers/scrapers)
Translated texts

Vocabulary Expansion

Added ~20K Georgian tokens to improve tokenization efficiency:

Tokenizer fertility: 1.9 tokens/word on Georgian text
New embeddings initialized as mean of subtoken embeddings

Training Procedure

Method: Continue pre-training
Embeddings: Full training (unfrozen)
LoRA: High-rank adaptation on transformer layers
Training Context: 8K tokens
Precision: BF16
Infrastructure: NVIDIA H100 GPUs

Usage

Installation

pip install transformers torch accelerate

Basic Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "tbilisi-ai-lab/kona2-12B-Base",
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("tbilisi-ai-lab/kona2-12B-Base")

# Text completion
text = "საქართველო არის"
inputs = tokenizer(text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=100)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Related Models

Model	Description
kona2-12B-Instruct	Instruction-tuned version (SFT)
kona2-12B	Preference-aligned version (DPO)
kona2-small-3.8B	Smaller 3.8B model

Limitations

Training data cutoff: 2024

Training Pipeline

Mistral-Nemo-Base-2407
    │
    ├── Expand Vocabulary (+20K Georgian tokens)
    │   └── Initialize with token average
    │
    └── Continue Pre-training (~30B tokens)
        └── Full embeddings training + high-rank LoRA
            │
            └── kona2-12B-Base ← YOU ARE HERE
                │
                └── SFT (~2.8M examples)
                    │
                    └── kona2-12B-Instruct
                        │
                        └── DPO (387K pairs)
                            │
                            └── kona2-12B

Technical Specifications

Precision: BF16/FP16 supported
Minimum VRAM: 24GB (with quantization)

Citation

@misc{tbilisi2025kona2base,
  title        = {Kona2-12B-Base: A Georgian Language Model},
  author       = {Tbilisi AI Lab Team},
  year         = {2025},
  publisher    = {Hugging Face},
  howpublished = {\url{https://huggingface.co/tbilisi-ai-lab/kona2-12B-Base}}
}