Instructions to use LumiOpen/Viking-33B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use LumiOpen/Viking-33B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="LumiOpen/Viking-33B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("LumiOpen/Viking-33B") model = AutoModelForCausalLM.from_pretrained("LumiOpen/Viking-33B") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use LumiOpen/Viking-33B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "LumiOpen/Viking-33B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "LumiOpen/Viking-33B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/LumiOpen/Viking-33B
- SGLang
How to use LumiOpen/Viking-33B 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 "LumiOpen/Viking-33B" \ --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": "LumiOpen/Viking-33B", "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 "LumiOpen/Viking-33B" \ --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": "LumiOpen/Viking-33B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use LumiOpen/Viking-33B with Docker Model Runner:
docker model run hf.co/LumiOpen/Viking-33B
UserWarning: `pad_token_id` should be positive but got -1.
I get this warning when using Viking-33B :
UserWarning: pad_token_id should be positive but got -1. This will cause errors when batch generating, if there is padding. Please set pad_token_id explicitly by model.generation_config.pad_token_id=PAD_TOKEN_ID to avoid errors in generation, and ensure your input_ids input does not have negative values.
Should i do something about this?
transformers version is: 4.42.4
code:
model = AutoModelForCausalLM.from_pretrained(
MODEL_PATH,
device_map='auto'
)
tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH, device_map='auto')
encoded = tokenizer("Kuka on Suomen presidentti? Vastaus: ", return_tensors='pt').to(model.device)
pred = model.generate(**encoded, max_new_tokens=512)
output= tokenizer.decode(pred[0])