Instructions to use DFveloper/AAIKR-3.1-mini-Q4_0-QAT-unquantized with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DFveloper/AAIKR-3.1-mini-Q4_0-QAT-unquantized with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="DFveloper/AAIKR-3.1-mini-Q4_0-QAT-unquantized") 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("DFveloper/AAIKR-3.1-mini-Q4_0-QAT-unquantized") model = AutoModelForMultimodalLM.from_pretrained("DFveloper/AAIKR-3.1-mini-Q4_0-QAT-unquantized", 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
- vLLM
How to use DFveloper/AAIKR-3.1-mini-Q4_0-QAT-unquantized with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "DFveloper/AAIKR-3.1-mini-Q4_0-QAT-unquantized" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "DFveloper/AAIKR-3.1-mini-Q4_0-QAT-unquantized", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/DFveloper/AAIKR-3.1-mini-Q4_0-QAT-unquantized
- SGLang
How to use DFveloper/AAIKR-3.1-mini-Q4_0-QAT-unquantized 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 "DFveloper/AAIKR-3.1-mini-Q4_0-QAT-unquantized" \ --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": "DFveloper/AAIKR-3.1-mini-Q4_0-QAT-unquantized", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'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 "DFveloper/AAIKR-3.1-mini-Q4_0-QAT-unquantized" \ --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": "DFveloper/AAIKR-3.1-mini-Q4_0-QAT-unquantized", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }' - Unsloth Desktop
- Docker Model Runner
How to use DFveloper/AAIKR-3.1-mini-Q4_0-QAT-unquantized with Docker Model Runner:
docker model run hf.co/DFveloper/AAIKR-3.1-mini-Q4_0-QAT-unquantized
AAIKR 3.1 mini
๐ ์๊ฐ
AAIKR 3.1 mini๋ ์ต์ ํ๋ ๋์์ธ์ผ๋ก ์ค๊ณ๋ ์ด๊ฒฝ๋ LLM์ ๋๋ค. ๋ฐฉ๋ํ ์์ ์ง์์ ํจ์จ์ ์ผ๋ก ์์ถํ์ฌ ์ถ๋ก ์๋๋ ๋์ด๊ณ ๋ชจ๋ธ ํฌ๊ธฐ๋ ์ต์ํํ์ต๋๋ค.
์ด ๋ชจ๋ธ์ ๋น ๋ฅด๊ณ , ๊ฐ๋ฒผ์ฐ๋ฉฐ, ๋ค์ํ ์์ง๋์ด๋ง ํ๊ฒฝ์์ ๋ฐฐํฌํ ์ ์๋๋ก ์ ์๋์์ต๋๋ค. ๋จ์ํ ์ฑ๋ด๋ถํฐ ๊ณ ์ฑ๋ฅ ์ถ๋ก ์์ ๊น์ง, AAIKR 3.1 mini๋ ๋น ๋ฅด๊ณ ํจ์จ์ ์ธ ์์ ํํธ๋๊ฐ ๋ ๊ฒ์ ๋๋ค.
โจ ์ฃผ์ ํน์ง
- โก ๋น ๋ฅธ ์ถ๋ก ์๋: 2B ํ๋ผ๋ฏธํฐ์์๋ ๋ถ๊ตฌํ๊ณ gemma 4์ ๊ณ ํจ์จ ์ํคํ ์ฒ๋ฅผ ํ์ฌํ์ฌ ๋น ๋ฅธ ์๋๋ฅผ ์๋ํฉ๋๋ค.
- ๐ ๏ธ ๊ฒฝ๋ํ: ๋ฉ๋ชจ๋ฆฌ ์ฌ์ฉ๋์ด ์ ์ด ๋ค์ํ ํ๊ฒฝ์์ ์ํํ๊ฒ ์๋ํฉ๋๋ค.
- ๐ง ๋ฐ์ด๋ ๋ฒ์ฉ์ฑ: ๋ ผ๋ฆฌ์ ์ถ๋ก , ์ฝ๋ ์์ฑ, ์ผ๋ฐ ์ง์ ๊ฒ์ ๋ฑ ๋ค์ํ ์์ ์ ์ง์ํฉ๋๋ค.
๐ ๊ธฐ์ ์คํ
| ํญ๋ชฉ | ๋ด์ฉ |
|---|---|
| ํ๋ผ๋ฏธํฐ ์ | 2B |
| ํน์ง | ํ๊ตญ์ด ์ถ๋ก ๊ฐํ |
| ๊ถ์ฅ ์ฌ์ฉ ์ฌ๋ก | ์ค์๊ฐ QA ์์คํ , ๊ฒฝ๋ ์ฝ๋ ์์ฑ ๋์ฐ๋ฏธ, ๋น ๋ฅธ ๋ฌธ์ ์์ฝ, ์ฃ์ง ๋๋ฐ์ด์ค ๋ฐฐํฌ |
โ๏ธ ๊ฐ๋ฐ ๊ด๋ จ ์ฐธ๊ณ ์ฌํญ
AAIKR 3.1 mini๋ ์ด๊ธฐ ๋ฒ์ ์ผ๋ก, ์ถ๋ก ๊ณผ์ ์์์ ๋ฏธ์ธํ ํธํฅ์ด ์กด์ฌํ ์ ์์ต๋๋ค. ์ค์ํ ๊ฒฐ์ ์ ํญ์ ์ ๋ขฐํ ์ ์๋ ์ถ์ฒ๋ฅผ ํตํด ๊ฒ์ฆํ์๊ธฐ ๋ฐ๋๋๋ค. ๋ํ, ๊ทน๋๋ก ๊ธด ๋ํ์์๋ ๊ธฐ์ต ์ค์๋์ด ๋ฐ์ํ ์ ์์ผ๋ฏ๋ก ๋ช ์์ ์ธ Context Re-tuning์ด ํ์ํฉ๋๋ค.
์ด ๋ชจ๋ธ์ AAIKR ๋ชจ๋ธ๊ตฐ ์ค ์ฑ๋ฅ์ ๋นํด ๊ฐ์ฅ ๋น ๋ฅด๊ฒ ์์ฉํ์ ๊ทผ์ ํ๊ณ ์๋ ๋ชจ๋ธ์ ๋๋ค. ์ฌ์ฉ์ ์ปค๋ฎค๋ํฐ์์ ๋ฐ๊ฒฌ๋๋ ๋ฒ๊ทธ๋ ๊ฐ์ ์ ์ ๋ํด์๋ ํ๋ ฅํ์ฌ ์ ๋ฐ์ดํธํ ์ ์์ต๋๋ค.
๊ฐ๋ฐ: LOOP์ AI ์ฐ๊ตฌ ํ ๋ฒ์ : 3.1-rc2 ๋ผ์ด์ ์ค: Apache-2.0
- Downloads last month
- 17