Instructions to use Jung/t5-large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Jung/t5-large with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Jung/t5-large")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelWithLMHead tokenizer = AutoTokenizer.from_pretrained("Jung/t5-large") model = AutoModelWithLMHead.from_pretrained("Jung/t5-large", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Jung/t5-large with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Jung/t5-large" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Jung/t5-large", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Jung/t5-large
- SGLang
How to use Jung/t5-large 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 "Jung/t5-large" \ --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": "Jung/t5-large", "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 "Jung/t5-large" \ --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": "Jung/t5-large", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Jung/t5-large with Docker Model Runner:
docker model run hf.co/Jung/t5-large
Commit History
-
upload flax model
03ad92b -
allow flax
4022401
-
Update config.json
162ec90 -
Update eval_results.txt
a1ee23b -
Update tokenizer_config.json
f637b13 -
Update spiece.model
47be61a -
Update special_tokens_map.json
ce86068 -
Update training_args.bin
3e3c322 -
Update pytorch_model.bin
e112c1f
-
Update special_tokens_map.json
a7bfa59 -
Update tokenizer_config.json
7215a86 -
Update eval_results.txt
0b4cd0b -
Update config.json
89e7c42 -
Update spiece.model
67cfee5
-
Update dataset-metadata.json
9989c20 -
Update spiece.model
82f0b90 -
Update eval_results.txt
173bb56 -
Update special_tokens_map.json
f4d274a -
Update tokenizer_config.json
750db46 -
Update config.json
5faefa1 -
Update dataset-metadata.json
9a0597b -
Update eval_results.txt
ff3f3c7 -
Update spiece.model
cc4bac8 -
Update special_tokens_map.json
5217412 -
Update tokenizer_config.json
a1c5955 -
Update config.json
a59ec7a -
Update eval_results.txt
e54836c -
Update spiece.model
8c0c539 -
Update special_tokens_map.json
f61a430 -
Update tokenizer_config.json
3522216 -
Update config.json
aa40495 -
initial commit
d5d8a0c