Instructions to use petkopetkov/SmolLM2-135M-bg with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use petkopetkov/SmolLM2-135M-bg with Transformers:

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

pipe = pipeline("text-generation", model="petkopetkov/SmolLM2-135M-bg")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("petkopetkov/SmolLM2-135M-bg")
model = AutoModelForCausalLM.from_pretrained("petkopetkov/SmolLM2-135M-bg")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use petkopetkov/SmolLM2-135M-bg with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "petkopetkov/SmolLM2-135M-bg"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "petkopetkov/SmolLM2-135M-bg",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/petkopetkov/SmolLM2-135M-bg

SGLang

How to use petkopetkov/SmolLM2-135M-bg 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 "petkopetkov/SmolLM2-135M-bg" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "petkopetkov/SmolLM2-135M-bg",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "petkopetkov/SmolLM2-135M-bg" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "petkopetkov/SmolLM2-135M-bg",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio new

How to use petkopetkov/SmolLM2-135M-bg 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 petkopetkov/SmolLM2-135M-bg 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 petkopetkov/SmolLM2-135M-bg to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for petkopetkov/SmolLM2-135M-bg to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="petkopetkov/SmolLM2-135M-bg",
    max_seq_length=2048,
)

Docker Model Runner
How to use petkopetkov/SmolLM2-135M-bg with Docker Model Runner:
```
docker model run hf.co/petkopetkov/SmolLM2-135M-bg
```

SmolLM2-135M-Bulgarian

Developed by: petkopetkov
License: apache-2.0
Finetuned from model : unsloth/SmolLM2-135M

SmolLM2-135M finetuned on datasets translated to Bulgarian language:

MMLU: multiple-choice questions from various branches of knowledge
Winogrande challenge: testing world knowledge and understanding
Hellaswag: testing sentence completion
ARC Easy/Challenge: testing logical reasoning
GSM-8k: solving multiple-choice questions in high-school mathematics
MathQA: math word problems

Usage

First, install the Transformers library with:

pip install -U transformers

Run with the `pipeline` API

import torch
from transformers import pipeline

pipe = pipeline(
    "text-generation",
    model="petkopetkov/SmolLM2-135M-bg",
    torch_dtype=torch.bfloat16, 
    device_map="auto"
)

prompt = "Колко е 2 + 2?"

print(pipe(prompt)[0]['generated_text'])

Downloads last month: -

Safetensors

Model size

0.1B params

Tensor type

BF16

Model tree for petkopetkov/SmolLM2-135M-bg

Base model

HuggingFaceTB/SmolLM2-135M

Finetuned

unsloth/SmolLM2-135M

Finetuned

(21)

this model

Datasets used to train petkopetkov/SmolLM2-135M-bg

Collection including petkopetkov/SmolLM2-135M-bg

Bulgarian LLMs

Collection

23 items • Updated Nov 18, 2025 • 1