Instructions to use BSC-LT/ALIA-40b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BSC-LT/ALIA-40b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="BSC-LT/ALIA-40b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("BSC-LT/ALIA-40b") model = AutoModelForCausalLM.from_pretrained("BSC-LT/ALIA-40b") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use BSC-LT/ALIA-40b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "BSC-LT/ALIA-40b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "BSC-LT/ALIA-40b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/BSC-LT/ALIA-40b
- SGLang
How to use BSC-LT/ALIA-40b 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 "BSC-LT/ALIA-40b" \ --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": "BSC-LT/ALIA-40b", "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 "BSC-LT/ALIA-40b" \ --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": "BSC-LT/ALIA-40b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use BSC-LT/ALIA-40b with Docker Model Runner:
docker model run hf.co/BSC-LT/ALIA-40b
Appreciate the model drop!
But why is it only 4k? Its 2025 man, those are rookie numbers.
Agree
We understand the demand for longer context windows and our roadmap includes multiple possible approaches to increase it. Extending the context length involves trade-offs in training efficiency, memory usage, and model performance, we are working on how to do it as efficient as possible.
If you now need a model with a longer context, consider using our instructed Salamandra-7b, it might be more suitable for you.
Hi,
The current ALIA-40B model supports up to 32K tokens, and we're actively working on extending its capabilities even further. Stay tuned for updates, we hope you enjoy using it!