Instructions to use gigant/graph_t5_230612 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use gigant/graph_t5_230612 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="gigant/graph_t5_230612")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("gigant/graph_t5_230612") model = AutoModelForSeq2SeqLM.from_pretrained("gigant/graph_t5_230612", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use gigant/graph_t5_230612 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "gigant/graph_t5_230612" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "gigant/graph_t5_230612", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/gigant/graph_t5_230612
- SGLang
How to use gigant/graph_t5_230612 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 "gigant/graph_t5_230612" \ --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": "gigant/graph_t5_230612", "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 "gigant/graph_t5_230612" \ --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": "gigant/graph_t5_230612", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use gigant/graph_t5_230612 with Docker Model Runner:
docker model run hf.co/gigant/graph_t5_230612
Commit History
-
Saving weights and logs of epoch 5
4673089 -
Saving weights and logs of epoch 4
5188ba4 -
Saving weights and logs of epoch 3
2afe8e9 -
Saving weights and logs of epoch 2
b80c98b -
Saving weights and logs of epoch 1
9a8d483 -
Saving weights and logs of epoch 0
50d51b3 -
Saving weights and logs of epoch 5
b58d823 -
Saving weights and logs of epoch 4
ffb11dc -
Saving weights and logs of epoch 3
8753401 -
Saving weights and logs of epoch 2
d7f2fb5 -
Saving weights and logs of epoch 1
f9afe6e -
Saving weights and logs of epoch 0
607a480
-
Saving weights and logs of epoch 3
c4b03ac -
Saving weights and logs of epoch 2
c384a81 -
Saving weights and logs of epoch 1
bfd8361 -
Saving weights and logs of epoch 0
acd5857 -
Saving weights and logs of epoch 4
2a26e80 -
Saving weights and logs of epoch 3
1f96486 -
Saving weights and logs of epoch 2
dc31864 -
Saving weights and logs of epoch 1
5e7e7b4 -
Saving weights and logs of epoch 0
aee19a5 -
Saving weights and logs of epoch 0
f7071ca -
Saving weights and logs of epoch 5
a67d5dd -
Saving weights and logs of epoch 4
b663aa8 -
Saving weights and logs of epoch 3
2d9da0d -
Saving weights and logs of epoch 2
e01feb5 -
Saving weights and logs of epoch 1
5677079 -
Saving weights and logs of epoch 0
2e6904e -
Saving weights and logs of epoch 5
fe13c38 -
Saving weights and logs of epoch 4
1877503 -
Saving weights and logs of epoch 3
1db83de -
Saving weights and logs of epoch 2
b6cd6aa -
Saving weights and logs of epoch 1
f0401cd -
Saving weights and logs of epoch 0
b9f50a4