Instructions to use Ti-Ma/TiMaGPT2-2020 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Ti-Ma/TiMaGPT2-2020 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Ti-Ma/TiMaGPT2-2020")# Load model directly from transformers import AutoTokenizer, AutoModelWithLMHead tokenizer = AutoTokenizer.from_pretrained("Ti-Ma/TiMaGPT2-2020") model = AutoModelWithLMHead.from_pretrained("Ti-Ma/TiMaGPT2-2020") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Ti-Ma/TiMaGPT2-2020 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Ti-Ma/TiMaGPT2-2020" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Ti-Ma/TiMaGPT2-2020", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Ti-Ma/TiMaGPT2-2020
- SGLang
How to use Ti-Ma/TiMaGPT2-2020 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 "Ti-Ma/TiMaGPT2-2020" \ --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": "Ti-Ma/TiMaGPT2-2020", "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 "Ti-Ma/TiMaGPT2-2020" \ --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": "Ti-Ma/TiMaGPT2-2020", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Ti-Ma/TiMaGPT2-2020 with Docker Model Runner:
docker model run hf.co/Ti-Ma/TiMaGPT2-2020
The following model is trained on entirely historical data up to the cutoff date "31-12-2020". The training data comes from the WMT News dataset (https://data.statmt.org/news-crawl/en/) and Wikipedia. The exact training dataset for this model is available on Huggingface at the following location: "TiMa/TiMaGPT2-2020".
Please refer to and cite the following paper when using this model in any downstream applications:
@inproceedings{drinkall-tima-2024, title = "Time Machine GPT", author = "Drinkall, Felix and Zohren, Stefan and Pierrehumbert, Janet", booktitle = "Findings of the Association for Computational Linguistics: NAACL 2024", month = june, year = "2024", publisher = "Association for Computational Linguistics" }
- Downloads last month
- 1