Instructions to use EleutherAI/pile-t5-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use EleutherAI/pile-t5-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="EleutherAI/pile-t5-base")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("EleutherAI/pile-t5-base") model = AutoModelForSeq2SeqLM.from_pretrained("EleutherAI/pile-t5-base") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use EleutherAI/pile-t5-base with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "EleutherAI/pile-t5-base" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "EleutherAI/pile-t5-base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/EleutherAI/pile-t5-base
- SGLang
How to use EleutherAI/pile-t5-base 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 "EleutherAI/pile-t5-base" \ --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": "EleutherAI/pile-t5-base", "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 "EleutherAI/pile-t5-base" \ --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": "EleutherAI/pile-t5-base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use EleutherAI/pile-t5-base with Docker Model Runner:
docker model run hf.co/EleutherAI/pile-t5-base
No pad token
#2
by BartekSadlej - opened
Hi, what should I add as a padding token? I can see that the tokenizer doesn't have pad token.
You can use the bos token. Any token should be fine really so long as you mask them so that they don't interfere with the backpropagation signal.