Instructions to use MU-NLPC/CzeGPT-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MU-NLPC/CzeGPT-2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="MU-NLPC/CzeGPT-2")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("MU-NLPC/CzeGPT-2") model = AutoModelForCausalLM.from_pretrained("MU-NLPC/CzeGPT-2") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use MU-NLPC/CzeGPT-2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "MU-NLPC/CzeGPT-2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "MU-NLPC/CzeGPT-2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/MU-NLPC/CzeGPT-2
- SGLang
How to use MU-NLPC/CzeGPT-2 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 "MU-NLPC/CzeGPT-2" \ --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": "MU-NLPC/CzeGPT-2", "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 "MU-NLPC/CzeGPT-2" \ --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": "MU-NLPC/CzeGPT-2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use MU-NLPC/CzeGPT-2 with Docker Model Runner:
docker model run hf.co/MU-NLPC/CzeGPT-2
Update README.md
Browse files
README.md
CHANGED
|
@@ -21,6 +21,10 @@ The model's perplexity on a 250 MB random slice of csTenTen17 dataset is **42.12
|
|
| 21 |
The repository includes a simple Jupyter Notebook that can help with the first steps when using the model.
|
| 22 |
|
| 23 |
## How to cite
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
@article{hajek_horak2024,
|
| 25 |
author = "Adam Hájek and Aleš Horák",
|
| 26 |
title = "CzeGPT-2 -- Training New Model for Czech Generative Text Processing Evaluated with the Summarization Task",
|
|
|
|
| 21 |
The repository includes a simple Jupyter Notebook that can help with the first steps when using the model.
|
| 22 |
|
| 23 |
## How to cite
|
| 24 |
+
Hájek A. and Horák A. *CzeGPT-2 – Training New Model for Czech Generative Text Processing Evaluated with the Summarization Task*.
|
| 25 |
+
IEEE Access, vol. 12, 34570–34581, Elsevier, 2024. https://doi.org/10.1109/ACCESS.2024.3371689
|
| 26 |
+
|
| 27 |
+
|
| 28 |
@article{hajek_horak2024,
|
| 29 |
author = "Adam Hájek and Aleš Horák",
|
| 30 |
title = "CzeGPT-2 -- Training New Model for Czech Generative Text Processing Evaluated with the Summarization Task",
|