Instructions to use utter-project/EuroLLM-9B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use utter-project/EuroLLM-9B-Instruct with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="utter-project/EuroLLM-9B-Instruct") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("utter-project/EuroLLM-9B-Instruct") model = AutoModelForCausalLM.from_pretrained("utter-project/EuroLLM-9B-Instruct") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use utter-project/EuroLLM-9B-Instruct with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "utter-project/EuroLLM-9B-Instruct" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "utter-project/EuroLLM-9B-Instruct", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/utter-project/EuroLLM-9B-Instruct
- SGLang
How to use utter-project/EuroLLM-9B-Instruct 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 "utter-project/EuroLLM-9B-Instruct" \ --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": "utter-project/EuroLLM-9B-Instruct", "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 "utter-project/EuroLLM-9B-Instruct" \ --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": "utter-project/EuroLLM-9B-Instruct", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use utter-project/EuroLLM-9B-Instruct with Docker Model Runner:
docker model run hf.co/utter-project/EuroLLM-9B-Instruct
Disable "gated access", it is Apache 2
It would be much easier to use this if "gated access" were disabled. After all, the model is Apache 2, so anybody may download it and upload a copy to an ungated repository (in fact, I have been considering exactly that); and this will mess up your download statistics.
It would be much easier to use this if "gated access" were disabled. After all, the model is Apache 2, so anybody may download it and upload a copy to an ungated repository (in fact, I have been considering exactly that); and this will mess up your download statistics.
EU regulations that no one seems to understand including their well regarded makers. People play safe.
When using docker with huggingface cli logged in, and I have been granted access, i still see the gated access permission error
It would be much easier to use this if "gated access" were disabled. After all, the model is Apache 2, so anybody may download it and upload a copy to an ungated repository (in fact, I have been considering exactly that); and this will mess up your download statistics.
EU regulations that no one seems to understand including their well regarded makers. People play safe.
Gated access often requires users to provide personal information, such as an email address, to gain access to certain content or services. This process enables the collection of users' data, which can be used for various purposes, such as tracking downloads, analyzing user behavior, or marketing. When it comes to compliance with GDPR, organizations must ensure that they handle personal data transparently, obtain clear consent for data collection and processing, and allow users to access, modify, or delete their data.
Implications for privacy under GDPR include ensuring data minimization, where only necessary data is collected, and ensuring that users are fully informed about how their data will be used. Organizations must also implement appropriate security measures to protect personal data from breaches.
I see no compliance to GDPR.