Text Generation
Transformers
Safetensors
Korean
English
qwen3_5_moe
image-text-to-text
korean
conversational
Instructions to use FINAL-Bench/Darwin-36B-KR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use FINAL-Bench/Darwin-36B-KR with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="FINAL-Bench/Darwin-36B-KR") 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)# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("FINAL-Bench/Darwin-36B-KR") model = AutoModelForMultimodalLM.from_pretrained("FINAL-Bench/Darwin-36B-KR") 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=40) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use FINAL-Bench/Darwin-36B-KR with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "FINAL-Bench/Darwin-36B-KR" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "FINAL-Bench/Darwin-36B-KR", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/FINAL-Bench/Darwin-36B-KR
- SGLang
How to use FINAL-Bench/Darwin-36B-KR 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 "FINAL-Bench/Darwin-36B-KR" \ --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": "FINAL-Bench/Darwin-36B-KR", "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 "FINAL-Bench/Darwin-36B-KR" \ --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": "FINAL-Bench/Darwin-36B-KR", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use FINAL-Bench/Darwin-36B-KR with Docker Model Runner:
docker model run hf.co/FINAL-Bench/Darwin-36B-KR
Ctrl+K
- 1.57 kB
- 11.3 kB
- 219 Bytes
- 7.76 kB
- 3.69 kB
- 58 Bytes
- 202 Bytes
- 3.35 MB
- 4 GB xet
- 1.28 GB xet
- 3.36 GB xet
- 3.37 GB xet
- 3.36 GB xet
- 3.96 GB xet
- 1.1 GB xet
- 3.95 GB xet
- 1.1 GB xet
- 3.95 GB xet
- 1.1 GB xet
- 3.41 GB xet
- 1.63 GB xet
- 3.42 GB xet
- 1.63 GB xet
- 3.95 GB xet
- 1.1 GB xet
- 3.95 GB xet
- 1.1 GB xet
- 3.41 GB xet
- 1.63 GB xet
- 3.37 GB xet
- 3.36 GB xet
- 3.37 GB xet
- 3.83 GB xet
- 2.23 GB xet
- 98.4 kB
- 390 Bytes
- 12.8 MB xet
- 16.7 kB
- 385 Bytes
- 6.72 MB