Instructions to use dacorvo/gpt2-neuronx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dacorvo/gpt2-neuronx with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="dacorvo/gpt2-neuronx")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("dacorvo/gpt2-neuronx") model = AutoModelForCausalLM.from_pretrained("dacorvo/gpt2-neuronx", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use dacorvo/gpt2-neuronx with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "dacorvo/gpt2-neuronx" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "dacorvo/gpt2-neuronx", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/dacorvo/gpt2-neuronx
- SGLang
How to use dacorvo/gpt2-neuronx 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 "dacorvo/gpt2-neuronx" \ --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": "dacorvo/gpt2-neuronx", "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 "dacorvo/gpt2-neuronx" \ --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": "dacorvo/gpt2-neuronx", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use dacorvo/gpt2-neuronx with Docker Model Runner:
docker model run hf.co/dacorvo/gpt2-neuronx
Download compiled/neuron-program.pkl from dacorvo/gpt2-neuronx: direct link, hf CLI and curl.
- Browser
- Download file 613 kB
-
https://huggingface.co/dacorvo/gpt2-neuronx/resolve/main/compiled/neuron-program.pkl
- Command line
-
hf download hf://dacorvo/gpt2-neuronx/compiled/neuron-program.pkl
-
curl -L -o neuron-program.pkl https://huggingface.co/dacorvo/gpt2-neuronx/resolve/main/compiled/neuron-program.pkl
613 kB
- Xet hash:
- 7a46a821f636b0ccc8b2d2d35f0951e01b745997e6a2c014f41f50c2bef56bcf
- Size of remote file:
- 613 kB
- SHA256:
- 15824d6ca3481824c36309f592b74dad424f0cd9833d46a1d611aa530eca7947
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.