Instructions to use quantumaikr/max-0.1b-v0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use quantumaikr/max-0.1b-v0 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="quantumaikr/max-0.1b-v0")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("quantumaikr/max-0.1b-v0") model = AutoModelForCausalLM.from_pretrained("quantumaikr/max-0.1b-v0", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use quantumaikr/max-0.1b-v0 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 quantumaikr/max-0.1b-v0:Q4_K_M # Run inference directly in the terminal: llama cli -hf quantumaikr/max-0.1b-v0:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf quantumaikr/max-0.1b-v0:Q4_K_M # Run inference directly in the terminal: llama cli -hf quantumaikr/max-0.1b-v0:Q4_K_M
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 quantumaikr/max-0.1b-v0:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf quantumaikr/max-0.1b-v0:Q4_K_M
Use Docker
docker model run hf.co/quantumaikr/max-0.1b-v0:Q4_K_M
- Llama new
- LM Studio
- Jan
- vLLM
How to use quantumaikr/max-0.1b-v0 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "quantumaikr/max-0.1b-v0" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "quantumaikr/max-0.1b-v0", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/quantumaikr/max-0.1b-v0:Q4_K_M
- SGLang
How to use quantumaikr/max-0.1b-v0 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 "quantumaikr/max-0.1b-v0" \ --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": "quantumaikr/max-0.1b-v0", "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 "quantumaikr/max-0.1b-v0" \ --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": "quantumaikr/max-0.1b-v0", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Ollama
How to use quantumaikr/max-0.1b-v0 with Ollama:
ollama run hf.co/quantumaikr/max-0.1b-v0:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use quantumaikr/max-0.1b-v0 with Docker Model Runner:
docker model run hf.co/quantumaikr/max-0.1b-v0:Q4_K_M
- Lemonade
How to use quantumaikr/max-0.1b-v0 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull quantumaikr/max-0.1b-v0:Q4_K_M
Run and chat with the model
lemonade run user.max-0.1b-v0-Q4_K_M
List all available models
lemonade list
- Atomic Chat
max-0.1b v0
Newer version: quantumaikr/max-0.1b-v1 continues this model to 10.0B training tokens (better validation loss and public Korean task scores). / ํ์ ๋ชจ๋ธ: max-0.1b-v1(ํ์ต 100์ต ํ ํฐ).
A small Korean-first base language model (109.5M parameters) for industrial small functions such as document classification, request routing, field extraction and form filling. This is an early base model (not instruction-tuned). It is intended as a starting point for task fine-tuning and for research, not for direct end-user use.
ํ๊ตญ์ด ์ค์ฌ์ ์ํ ๊ธฐ์ด ์ธ์ด๋ชจ๋ธ(1.095์ต ๋งค๊ฐ๋ณ์)์ ๋๋ค. ๋ฌธ์ ๋ถ๋ฅ, ์์ฒญ ๋ถ๊ธฐ, ํญ๋ชฉ ์ถ์ถ, ์์ ์์ฑ ๊ฐ์ ์ฐ์ ์ฉ ์์ ๊ธฐ๋ฅ์ ์ถ๋ฐ์ ์ผ๋ก ์ฐ๊ธฐ ์ํ ์ด๊ธฐ ๊ธฐ์ด ๋ชจ๋ธ์ด๋ฉฐ, ์ง์ ๋ฐ๋ฅด๊ธฐ ๋ฏธ์ธ์กฐ์ ์ ๋จ๊ณ์ ๋๋ค.
Files
| File | Use |
|---|---|
model.safetensors, config.json, tokenizer.json |
Transformers (Qwen3ForCausalLM-compatible layout) |
gguf/max01b-v0-f16.gguf (221 MB) |
llama.cpp, full precision |
gguf/max01b-v0-q8_0.gguf (118 MB) |
llama.cpp, 8-bit |
gguf/max01b-v0-q4_k_m.gguf (73 MB) |
llama.cpp, 4-bit, runs on ordinary CPUs |
Context length: 1,024 tokens. Vocabulary: 32,000 (Korean-optimized, digits split). Input text should be Unicode NFC-normalized.
from transformers import AutoModelForCausalLM, PreTrainedTokenizerFast
tok = PreTrainedTokenizerFast.from_pretrained("quantumaikr/max-0.1b-v0")
model = AutoModelForCausalLM.from_pretrained("quantumaikr/max-0.1b-v0")
llama-cli -m max01b-v0-q4_k_m.gguf -p "์ค๋ ํ์์์ ๋
ผ์๋ ์๊ฑด์" -n 64
Evaluation (base model, held-out sets)
Validation (bits per byte, lower is better): Korean web 0.90 ยท Korean documents 0.83 ยท English 1.03.
| Task (0-shot, n=300) | Accuracy | Chance |
|---|---|---|
| ARC-Easy | 0.43 | 0.25 |
| PIQA | 0.60 | 0.50 |
| HellaSwag | 0.29 | 0.25 |
| KoBEST COPA | 0.56 | 0.50 |
| KoBEST HellaSwag | 0.32 (norm 0.41) | 0.25 |
| KoBEST BoolQ | 0.49 | 0.50 |
Few-shot industrial tasks (n=40 each, before fine-tuning): document-type classification 0.63 (calibrated), complaint classification 0.45, request routing 0.28, JSON output parse rate 0.48โ0.58. Field extraction and number-faithful summarization are not usable without fine-tuning.
Limitations
- Trained on 2.8B tokens only: factual knowledge is weak and the model repeats itself.
- It may invent numbers and facts. Do not use its output without verification.
- Base model: it continues text; it does not follow instructions reliably.
- Personal identifiers in the training text were masked, but small models can still reproduce fragments of web text.
Training data and attribution
All training data is publicly released under the Open Data Commons Attribution License (ODC-By 1.0):
- FineWeb-2 (Korean subset) โ Hugging Face, ODC-By 1.0
- FinePDFs (Korean subset) โ Hugging Face, ODC-By 1.0
- FineWeb-Edu โ Hugging Face, ODC-By 1.0
- FineMath โ Hugging Face, ODC-By 1.0
These datasets are derived from Common Crawl and are also subject to the Common Crawl Terms of Use.
License
Apache License 2.0.
- Downloads last month
- 173