Instructions to use MU-NLPC/CzeGPT-2_summarizer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MU-NLPC/CzeGPT-2_summarizer with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="MU-NLPC/CzeGPT-2_summarizer")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MU-NLPC/CzeGPT-2_summarizer")
model = AutoModelForCausalLM.from_pretrained("MU-NLPC/CzeGPT-2_summarizer", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MU-NLPC/CzeGPT-2_summarizer 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_summarizer"
# 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_summarizer",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/MU-NLPC/CzeGPT-2_summarizer

SGLang

How to use MU-NLPC/CzeGPT-2_summarizer 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_summarizer" \
    --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_summarizer",
		"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_summarizer" \
        --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_summarizer",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use MU-NLPC/CzeGPT-2_summarizer with Docker Model Runner:
```
docker model run hf.co/MU-NLPC/CzeGPT-2_summarizer
```

hajekad commited on Apr 4, 2022

Commit

8bee35f

1 Parent(s): b922fa0

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -7,7 +7,7 @@ datasets:
 ---
 # CzeGPT-2_summarizer
-CzeGPT-2_summarizer is a Czech summarizer built upon the <a href="https://huggingface.co/MU-NLPC/CzeGPT-2">CzeGPT-2</a> model. The model has the same architectural dimensions as the GPT-2 small (12 layers, 12 heads, 1024 tokens on input/output, and embedding vectors with 768 dimensions) resulting in 124M trainable parameters. It was fine-tuned and evaluated on the <a href="https://aclanthology.org/L18-1551.pdf">SumeCzech</a> summarization dataset containing about 1M Czech news articles.
 The model is trained to generate the summary as long as you let it (or it runs out of sequence length). This leaves a space for developers to set their own constraints.
 ## Tokenizer

 ---
 # CzeGPT-2_summarizer
+CzeGPT-2 summarizer is a Czech summarizer built upon the <a href="https://huggingface.co/MU-NLPC/CzeGPT-2">CzeGPT-2</a> model. The model has the same architectural dimensions as the GPT-2 small (12 layers, 12 heads, 1024 tokens on input/output, and embedding vectors with 768 dimensions) resulting in 124M trainable parameters. It was fine-tuned and evaluated on the <a href="https://aclanthology.org/L18-1551.pdf">SumeCzech</a> summarization dataset containing about 1M Czech news articles.
 The model is trained to generate the summary as long as you let it (or it runs out of sequence length). This leaves a space for developers to set their own constraints.
 ## Tokenizer