Instructions to use MartinNav/compliantLLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MartinNav/compliantLLM with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="MartinNav/compliantLLM", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("MartinNav/compliantLLM", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use MartinNav/compliantLLM with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "MartinNav/compliantLLM" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "MartinNav/compliantLLM", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/MartinNav/compliantLLM
- SGLang
How to use MartinNav/compliantLLM 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 "MartinNav/compliantLLM" \ --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": "MartinNav/compliantLLM", "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 "MartinNav/compliantLLM" \ --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": "MartinNav/compliantLLM", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use MartinNav/compliantLLM with Docker Model Runner:
docker model run hf.co/MartinNav/compliantLLM
| { | |
| "architectures": [ | |
| "CompliantLLMModel" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_compliant_llm.CompliantLLMConfig", | |
| "AutoModel": "modeling_compliant_llm.CompliantLLMModel" | |
| }, | |
| "d_model": 64, | |
| "dropout": 0.0, | |
| "ffn_dim": 128, | |
| "input_vocab_size": 256, | |
| "max_context": 1024, | |
| "model_type": "compliant_llm", | |
| "n_heads": 4, | |
| "n_layers": 2, | |
| "output_length": 3, | |
| "output_tokens": [ | |
| "Sorry, but that question violates GDPR.", | |
| "<|end_turn|>", | |
| "<|eos|>" | |
| ], | |
| "output_vocab_size": 3, | |
| "torch_dtype": "float32", | |
| "transformers_version": "5.14.1" | |
| } | |