Instructions to use quantumaikr/max-0.1b-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use quantumaikr/max-0.1b-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="quantumaikr/max-0.1b-v1")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("quantumaikr/max-0.1b-v1") model = AutoModelForCausalLM.from_pretrained("quantumaikr/max-0.1b-v1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use quantumaikr/max-0.1b-v1 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-v1:F16 # Run inference directly in the terminal: llama cli -hf quantumaikr/max-0.1b-v1:F16
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-v1:F16 # Run inference directly in the terminal: llama cli -hf quantumaikr/max-0.1b-v1: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 quantumaikr/max-0.1b-v1:F16 # Run inference directly in the terminal: ./build/bin/llama cli -hf quantumaikr/max-0.1b-v1:F16
Use Docker
docker model run hf.co/quantumaikr/max-0.1b-v1:F16
- Llama new
- LM Studio
- Jan
- vLLM
How to use quantumaikr/max-0.1b-v1 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-v1" # 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-v1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/quantumaikr/max-0.1b-v1:F16
- SGLang
How to use quantumaikr/max-0.1b-v1 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-v1" \ --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-v1", "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-v1" \ --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-v1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Ollama
How to use quantumaikr/max-0.1b-v1 with Ollama:
ollama run hf.co/quantumaikr/max-0.1b-v1:F16
- Unsloth Desktop
- Docker Model Runner
How to use quantumaikr/max-0.1b-v1 with Docker Model Runner:
docker model run hf.co/quantumaikr/max-0.1b-v1:F16
- Lemonade
How to use quantumaikr/max-0.1b-v1 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull quantumaikr/max-0.1b-v1:F16
Run and chat with the model
lemonade run user.max-0.1b-v1-F16
List all available models
lemonade list
- Atomic Chat
max-0.1b v1
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. v1 continues v0 from its pre-decay checkpoint for 7.6B more tokens (10.0B in total). This is a base model (not instruction-tuned): a starting point for task fine-tuning and 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 ์ฐ๋ ๊ธฐ์ด ๋ชจ๋ธ์ ๋๋ค. ์ง์ ๋ฐ๋ฅด๊ธฐ ๋ฏธ์ธ์กฐ์ ์ ํ์ง ์์์ต๋๋ค. v0์ ๊ฐ์ ์ ์ ์ฅ๋ถ์์ ์ด์ด์ ํ์ตํ๊ณ , ๋์ ํ์ต๋์ 100์ต ํ ํฐ์ ๋๋ค.
Files
| File | Use |
|---|---|
model.safetensors, config.json, tokenizer.json |
Transformers (Qwen3ForCausalLM-compatible layout) |
gguf/max01b-v1-f16.gguf (221 MB) |
llama.cpp, full precision (greedy output identical to Transformers on 5/5 test prompts) |
gguf/max01b-v1-q4_k_m.gguf (73 MB) |
llama.cpp, 4-bit, runs on ordinary CPUs (perplexity about 8% higher than f16) |
Context length: 1,024 tokens. Vocabulary: 32,000 (Korean-optimized, digits split; same tokenizer as v0). Input text should be Unicode NFC-normalized (NFD Korean inflates the token count about 10x).
llama-completion -m max01b-v1-q4_k_m.gguf -p "์ค๋ ํ์์์ ๋
ผ์๋ ์๊ฑด์" -n 64 -no-cnv
from transformers import AutoModelForCausalLM, PreTrainedTokenizerFast
tok = PreTrainedTokenizerFast.from_pretrained("quantumaikr/max-0.1b-v1")
model = AutoModelForCausalLM.from_pretrained("quantumaikr/max-0.1b-v1")
Training
- Architecture as v0: 12 layers, width 768, SwiGLU 2048, RoPE, QK-norm, tied embeddings (Qwen3-compatible names).
- Continued from v0
stable_pre_decay(2.40B tokens) for 7.60B tokens on 2 GPUs (DDP); last 20% linear learning-rate decay. - Optimizer: Muon (hidden matrices) + AdamW (embeddings, scalars). Batch 524,288 tokens, context 1,024.
- Data (all ODC-By 1.0): FineWeb-2 Korean, FinePDFs Korean, FineWeb-Edu (incl. score โฅ 4 subset), FineMath-4plus. Mix: Korean web 40% / Korean documents 20% / English educational 33% / math 7% (decay phase: 33 / 25 / 32 / 10). Cleaning: NFC, script-ratio and length filters, exact deduplication, regex replacement of e-mail, phone, account and resident-registration-number patterns. No code data, no B/C-grade corpora, no model-generated text.
Evaluation
Validation loss (held-out, same files as v0; lower is better):
| set | v0 (2.8B tokens) | v1 (10.0B) |
|---|---|---|
| Korean web | 3.199 | 3.055 (0.903 bpb) |
| English | 2.961 | 2.851 (1.020 bpb) |
| Korean documents (PDF) | 2.341 | 2.208 (0.791 bpb) |
| Math | 2.185 | 2.020 (0.936 bpb) |
Fine-tuned on public, human-written Korean tasks (train split, 2 epochs; LR chosen on dev; test mean ยฑ std over 3 seeds):
| task | v0 | v1 | KLUE-RoBERTa-base (ref.) |
|---|---|---|---|
| KLUE-YNAT (macro F1) | 84.4 ยฑ 0.3 | 85.1 ยฑ 0.0 | 86.4 |
| KLUE-NLI (acc) | 70.4 ยฑ 0.6 | 73.8 ยฑ 1.0 | 85.1 |
| KLUE-NER (entity F1) | 81.1 ยฑ 0.3 | 82.5 ยฑ 0.4 | 87.4 |
| NSMC (acc) | 86.4 | 87.1 ยฑ 0.1 | 88.4 |
| MASSIVE ko intent (acc) | 86.4 ยฑ 0.2 | 86.1 ยฑ 0.4 | 86.5 |
| MASSIVE ko slot (F1) | 74.6 ยฑ 0.1 | 74.9 ยฑ 0.3 | 74.6 |
| 3i4K (acc) | 89.6 ยฑ 0.0 | 89.5 ยฑ 0.3 | 90.0 |
The decoder is generative (answers are generated text scored by the same scorer for every model); the encoder reference uses classification/tagging heads on the same splits.
Limitations
- Small base model: limited world knowledge and reasoning; it can produce fluent but wrong text. Fine-tune before use.
- Personal-information patterns were replaced with regular expressions; names and other free-form personal data may remain in the training text. Do not use the model to extract personal data.
- Korean and English only; context 1,024 tokens.
License
Apache-2.0 for the model weights. Training data: FineWeb-2, FinePDFs, FineWeb-Edu and FineMath (Hugging Face), ODC-By 1.0; please keep the attribution when redistributing derived datasets.
- Downloads last month
- 125