Text Generation
Transformers
PyTorch
Safetensors
English
t5
text2text-generation
Generated from Trainer
text-generation-inference
Instructions to use Isotonic/bullet-points-generator with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Isotonic/bullet-points-generator with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Isotonic/bullet-points-generator")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Isotonic/bullet-points-generator") model = AutoModelForSeq2SeqLM.from_pretrained("Isotonic/bullet-points-generator") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Isotonic/bullet-points-generator with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Isotonic/bullet-points-generator" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Isotonic/bullet-points-generator", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Isotonic/bullet-points-generator
- SGLang
How to use Isotonic/bullet-points-generator 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 "Isotonic/bullet-points-generator" \ --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": "Isotonic/bullet-points-generator", "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 "Isotonic/bullet-points-generator" \ --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": "Isotonic/bullet-points-generator", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Isotonic/bullet-points-generator with Docker Model Runner:
docker model run hf.co/Isotonic/bullet-points-generator
| tags: | |
| - generated_from_trainer | |
| model-index: | |
| - name: bullet-points-generator | |
| results: [] | |
| language: | |
| - en | |
| widget: | |
| - text: "'The fake charges put forth in their sham indictment are an outrageous criminalization of political speech,' the former president said. 'They’re trying to make it illegal to question the results of a bad election. It was a very bad election,' said Trump, who refuses to accept he lost the 2020 election and regularly promotes election conspiracy theories." | |
| - text: "Donald Trump’s campaign released a new video Friday attacking the prosecutors who have brought cases against or are investigating the former president one day after Trump was arrested and arraigned for a third time. The video attacks federal special prosecutor Jack Smith, New York Attorney General Letitia James, Manhattan District Attorney Alvin Bragg and Fulton County District Attorney Fani Willis and dubs the group the 'Fraud Squad.' 'Meet the cast of unscrupulous accomplices he’s assembled to get Trump,' the narrator says in the video." | |
| pipeline_tag: text2text-generation | |
| <!-- This model card has been generated automatically according to the information the Trainer had access to. You | |
| should probably proofread and complete it, then remove this comment. --> | |
| # bullet-points-generator | |
| This model was trained from scratch on an unknown dataset. | |
| Dataset contains 35k rows of 2 columns `source_text` and `target_text`. | |
| ## Model description | |
| More information needed | |
| ## Intended uses & limitations | |
| More information needed | |
| ## Training and evaluation data | |
| More information needed | |
| ## Training procedure | |
| ### Training hyperparameters | |
| The following hyperparameters were used during training: | |
| - learning_rate: 5e-05 | |
| - train_batch_size: 32 | |
| - eval_batch_size: 32 | |
| - seed: 42 | |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 | |
| - lr_scheduler_type: linear | |
| - num_epochs: 3.0 | |
| ### Framework versions | |
| - Transformers 4.32.0.dev0 | |
| - Pytorch 2.0.1+cu117 | |
| - Datasets 2.13.1 | |
| - Tokenizers 0.13.3 |