Text Generation
Transformers
TensorBoard
Safetensors
English
gpt2
Generated from Trainer
text-generation-inference
Instructions to use codewithdark/Lumina with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use codewithdark/Lumina with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="codewithdark/Lumina")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("codewithdark/Lumina") model = AutoModelForCausalLM.from_pretrained("codewithdark/Lumina", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use codewithdark/Lumina with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "codewithdark/Lumina" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "codewithdark/Lumina", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/codewithdark/Lumina
- SGLang
How to use codewithdark/Lumina 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 "codewithdark/Lumina" \ --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": "codewithdark/Lumina", "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 "codewithdark/Lumina" \ --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": "codewithdark/Lumina", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use codewithdark/Lumina with Docker Model Runner:
docker model run hf.co/codewithdark/Lumina
- Xet hash:
- 2f0225892bc36c607585728c3926360f1870d95e60f97c9e5e1eca166b3e58e7
- Size of remote file:
- 5.18 kB
- SHA256:
- 4ed76c9becd87f185459d48644ac5114ab4a9289936e6dc29d8a7f1de5764c23
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.