Instructions to use nferruz/ProtGPT2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nferruz/ProtGPT2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="nferruz/ProtGPT2")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("nferruz/ProtGPT2") model = AutoModelForCausalLM.from_pretrained("nferruz/ProtGPT2") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use nferruz/ProtGPT2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "nferruz/ProtGPT2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "nferruz/ProtGPT2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/nferruz/ProtGPT2
- SGLang
How to use nferruz/ProtGPT2 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 "nferruz/ProtGPT2" \ --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": "nferruz/ProtGPT2", "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 "nferruz/ProtGPT2" \ --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": "nferruz/ProtGPT2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use nferruz/ProtGPT2 with Docker Model Runner:
docker model run hf.co/nferruz/ProtGPT2
How to work training and generating on GPU environment
Hello,
Thank u so much for this wonderful work, it works perfectly!!!! And I was thinking if I could work on GPU will be much more efficient.
But there are some problems with training and generating on a GPU environment that I can't figure out.
Sorry, I do not know well about working it on GPU, never tried that before. :(
Want to ask if you can help me with this problem. Thank u so much!!! :)
(GPU---RTX3050-8G)
Hi Jonathanlin,
Not sure how can I help you, if you follow the installation guidelines from huggingface, the transformer library works by default on GPUs. Then, the code in the documentation uses also the GPUs by default.
But I am distressed about which part of the code in the documentation alters to the GPUs by default. :(
I am trying to add .to('cuda') on it, but I can't found here should I check? Want to ask if you have any tips or suggestions.