Instructions to use RusMiniLM/RusNanoMath-800M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use RusMiniLM/RusNanoMath-800M with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="RusMiniLM/RusNanoMath-800M") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("RusMiniLM/RusNanoMath-800M") model = AutoModelForMultimodalLM.from_pretrained("RusMiniLM/RusNanoMath-800M", device_map="auto") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] inputs = processor.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=256) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use RusMiniLM/RusNanoMath-800M with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf RusMiniLM/RusNanoMath-800M:F16 # Run inference directly in the terminal: llama cli -hf RusMiniLM/RusNanoMath-800M:F16
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf RusMiniLM/RusNanoMath-800M:F16 # Run inference directly in the terminal: llama cli -hf RusMiniLM/RusNanoMath-800M:F16
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf RusMiniLM/RusNanoMath-800M:F16 # Run inference directly in the terminal: ./build/bin/llama cli -hf RusMiniLM/RusNanoMath-800M:F16
Use Docker
docker model run hf.co/RusMiniLM/RusNanoMath-800M:F16
- Llama new
- LM Studio
- Jan
- vLLM
How to use RusMiniLM/RusNanoMath-800M with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "RusMiniLM/RusNanoMath-800M" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "RusMiniLM/RusNanoMath-800M", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/RusMiniLM/RusNanoMath-800M:F16
- SGLang
How to use RusMiniLM/RusNanoMath-800M 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 "RusMiniLM/RusNanoMath-800M" \ --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": "RusMiniLM/RusNanoMath-800M", "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 "RusMiniLM/RusNanoMath-800M" \ --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": "RusMiniLM/RusNanoMath-800M", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Ollama
How to use RusMiniLM/RusNanoMath-800M with Ollama:
ollama run hf.co/RusMiniLM/RusNanoMath-800M:F16
- Unsloth Desktop
- Docker Model Runner
How to use RusMiniLM/RusNanoMath-800M with Docker Model Runner:
docker model run hf.co/RusMiniLM/RusNanoMath-800M:F16
- Lemonade
How to use RusMiniLM/RusNanoMath-800M with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull RusMiniLM/RusNanoMath-800M:F16
Run and chat with the model
lemonade run user.RusNanoMath-800M-F16
List all available models
lemonade list
- Atomic Chat
Download README.md from RusMiniLM/RusNanoMath-800M: direct link, hf CLI and curl.
- Browser
- Download file 6.85 kB
-
https://huggingface.co/RusMiniLM/RusNanoMath-800M/resolve/main/README.md
- Command line
-
hf download hf://RusMiniLM/RusNanoMath-800M/README.md
-
curl -L -o README.md https://huggingface.co/RusMiniLM/RusNanoMath-800M/resolve/main/README.md
language:
- ru
- en
license: apache-2.0
tags:
- math
- reasoning
- linear-attention
- sub-1b
- qwen3.5
- cot
- olympiad
- sft
- simpo
pipeline_tag: text-generation
library_name: transformers
metrics:
- accuracy
model-index:
- name: RusNanoMath-800M
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: MATH-500
type: HuggingFaceH4/MATH-500
metrics:
- type: accuracy
value: 36.2
name: MATH-500 Accuracy
- type: accuracy
value: 52.42
name: MATH-500 Algebra Accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: GSM8K
type: openai/gsm8k
metrics:
- type: accuracy
value: 52
name: GSM8K Accuracy
RusNanoMath-800M
English Overview
RusNanoMath-800M is an open-weights 800M parameter bilingual (Russian / English) mathematical reasoning model. Built on a hybrid Linear Attention architecture (Qwen3.5 with Gated Delta Rule layers) and aligned via targeted multi-stage SFT and SimPO (Simple Preference Optimization), it demonstrates very strong reasoning performance across competitive mathematics benchmarks, particularly in symbolic algebra.
Benchmark Visual Leaderboards
1. MATH-500 Overall Leaderboard
2. Dedicated Algebra Breakdown (MATH-500: Algebra)
3. GSM8K Leaderboard
Highlights
- Symbolic Algebra (MATH-500 Algebra): In the 124 algebra competition problems, RusNanoMath-800M achieves 52.4%, closely approaching Llama-3.1-8B (53.8%) and surpassing models with 1.5B–3B parameters (Qwen2.5-1.5B at 49.5%, Llama-3.2-3B at 48.0%, Gemma-2-2B at 41.2%).
- General Competition Math (MATH-500 Overall): Across all 500 problems, RusNanoMath-800M reaches 36.2%, outperforming sub-1B to 2B models (Gemma-2-2B at 35.0%, SmolLM2-1.7B at 21.5%, Llama-3.2-1B at 14.0%).
- Grade School Arithmetic (GSM8K): Achieves 52.0%, handling multi-step reasoning chains and arithmetic problems.
Quickstart & Inference
import torch
from transformers import AutoModelForImageTextToText, AutoTokenizer
MODEL_ID = "itismax0/RusNanoML-800M"
tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
model = AutoModelForImageTextToText.from_pretrained(
MODEL_ID,
torch_dtype=torch.bfloat16,
device_map="auto"
)
model.eval()
messages = [
{
"role": "user",
"content": "Найдите все действительные корни уравнения x^4 - 5x^2 + 4 = 0. Ответ запишите в \\boxed{}."
}
]
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
outputs = model.generate(
**inputs,
max_new_tokens=1024,
do_sample=False,
pad_token_id=tokenizer.eos_token_id
)
response = tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True)
print(response)
Run with llama.cpp / Ollama (GGUF, full precision)
A full-precision F16 GGUF (RusNanoML-800M-F16.gguf) is included in this repo — no quantization loss.
# llama.cpp
llama-cli -hf itismax0/RusNanoML-800M:RusNanoML-800M-F16.gguf --temp 0 -p "Найдите все действительные корни уравнения x^4 - 5x^2 + 4 = 0."
Ollama (import the GGUF locally):
echo "FROM RusNanoML-800M-F16.gguf
PARAMETER temperature 0
TEMPLATE \"{{ .Prompt }}\"" > Modelfile
ollama create rusnanoml-800m -f Modelfile
ollama run rusnanoml-800m "Найдите все действительные корни уравнения x^4 - 5x^2 + 4 = 0."
Note: the model uses the Qwen3.5 hybrid linear-attention architecture. llama.cpp builds from
master(>= b12413) support it; older builds will refuse to load the file.
Обзор на русском
RusNanoMath-800M — открытая двуязычная (русский и английский) модель на 800 млн параметров для решения математических и логических задач. Архитектура построена на базе Qwen3.5 с гибридным линейным вниманием (Gated Delta Rule), что обеспечивает константную сложность памяти состояния O(1) при генерации. Обучение включает этапы целевого SFT на цепочках рассуждений (CoT) и выравнивание методом предпочтений SimPO (Simple Preference Optimization).
Графики сравнения с открытыми моделями
1. Общий зачёт: MATH-500
2. Раздел алгебры: MATH-500 (Algebra)
3. Арифметика и текстовые задачи: GSM8K
Основные показатели
- Алгебра (MATH-500 Algebra): В блоке из 124 задач по алгебре RusNanoMath-800M показывает 52.4% (65 решённых задач из 124). Модель вплотную приближается к показателям Llama-3.1-8B (53.8%) и превосходит модели большего размера: Qwen2.5-1.5B (49.5%), Llama-3.2-3B (48.0%) и Gemma-2-2B (41.2%).
- Общий зачёт MATH-500: По всему набору из 500 олимпиадных задач модель набирает 36.2% (181 решённая задача), опережая Gemma-2-2B (35.0%), Mistral-7B-Instruct (28.4%), SmolLM2-1.7B (21.5%) и Llama-3.2-1B (14.0%).
- GSM8K: На тесте многошаговой арифметики модель показывает 52.0% (260 решённых задач из 500).
Архитектура и параметры
- Параметры: 800 млн (0.8B)
- Внимание: Гибридное линейное внимание (Gated Delta Rule) со сложностью памяти состояния O(1)
- Требования к видеопамяти: около 1.6 ГБ в формате BF16 (работает на потребительских GPU с 4 ГБ VRAM)
- Контекст: до 32 768 токенов
- Лицензия: Apache 2.0


