Instructions to use Rostlab/prot_t5_xl_bfd with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Rostlab/prot_t5_xl_bfd with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Rostlab/prot_t5_xl_bfd")# Load model directly from transformers import AutoTokenizer, AutoModelWithLMHead tokenizer = AutoTokenizer.from_pretrained("Rostlab/prot_t5_xl_bfd") model = AutoModelWithLMHead.from_pretrained("Rostlab/prot_t5_xl_bfd") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Rostlab/prot_t5_xl_bfd with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Rostlab/prot_t5_xl_bfd" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Rostlab/prot_t5_xl_bfd", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Rostlab/prot_t5_xl_bfd
- SGLang
How to use Rostlab/prot_t5_xl_bfd 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 "Rostlab/prot_t5_xl_bfd" \ --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": "Rostlab/prot_t5_xl_bfd", "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 "Rostlab/prot_t5_xl_bfd" \ --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": "Rostlab/prot_t5_xl_bfd", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Rostlab/prot_t5_xl_bfd with Docker Model Runner:
docker model run hf.co/Rostlab/prot_t5_xl_bfd
CLS token?
#3
by pipparichter - opened
Hello! It seems as though the T5 model does not have a CLS token (based on this post https://discuss.huggingface.co/t/t5-sequence-classification/2664). I just wanted to confirm if this was true for this model, or if I have just missed something?
Thank you!