Instructions to use SZTAKI-HLT/Bert2Bert-HunSum-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SZTAKI-HLT/Bert2Bert-HunSum-2 with Transformers:

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

pipe = pipeline("text-generation", model="SZTAKI-HLT/Bert2Bert-HunSum-2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("SZTAKI-HLT/Bert2Bert-HunSum-2")
model = AutoModelForSeq2SeqLM.from_pretrained("SZTAKI-HLT/Bert2Bert-HunSum-2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use SZTAKI-HLT/Bert2Bert-HunSum-2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SZTAKI-HLT/Bert2Bert-HunSum-2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SZTAKI-HLT/Bert2Bert-HunSum-2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/SZTAKI-HLT/Bert2Bert-HunSum-2

SGLang

How to use SZTAKI-HLT/Bert2Bert-HunSum-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 "SZTAKI-HLT/Bert2Bert-HunSum-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": "SZTAKI-HLT/Bert2Bert-HunSum-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 "SZTAKI-HLT/Bert2Bert-HunSum-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": "SZTAKI-HLT/Bert2Bert-HunSum-2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use SZTAKI-HLT/Bert2Bert-HunSum-2 with Docker Model Runner:
```
docker model run hf.co/SZTAKI-HLT/Bert2Bert-HunSum-2
```

YAML Metadata Warning:The pipeline tag "text2text-generation" is not in the official list: text-classification, token-classification, table-question-answering, question-answering, zero-shot-classification, translation, summarization, feature-extraction, text-generation, fill-mask, sentence-similarity, text-to-speech, text-to-audio, automatic-speech-recognition, audio-to-audio, audio-classification, audio-text-to-text, voice-activity-detection, depth-estimation, image-classification, object-detection, image-segmentation, text-to-image, image-to-text, image-to-image, image-to-video, unconditional-image-generation, video-classification, reinforcement-learning, robotics, tabular-classification, tabular-regression, tabular-to-text, table-to-text, multiple-choice, text-ranking, text-retrieval, time-series-forecasting, text-to-video, image-text-to-text, image-text-to-image, image-text-to-video, visual-question-answering, document-question-answering, zero-shot-image-classification, graph-ml, mask-generation, zero-shot-object-detection, text-to-3d, image-to-3d, image-feature-extraction, video-text-to-text, keypoint-detection, visual-document-retrieval, any-to-any, video-to-video, other

Model Card for Bert2Bert-HunSum-2

The Bert2Bert-HunSum-2 is a Hungarian abstractive summarization model, which was trained on the SZTAKI-HLT/HunSum-2-abstractive dataset. The model is based on SZTAKI-HLT/hubert-base-cc.

Intended uses & limitations

Model type: Text Summarization
Language(s) (NLP): Hungarian
Resource(s) for more information:
- GitHub Repo

Parameters

Batch Size: 13
Learning Rate: 5e-5
Weight Decay: 0.01
Warmup Steps: 16000
Epochs: 10
no_repeat_ngram_size: 3
num_beams: 5
early_stopping: False

Results

Metric	Value
ROUGE-1	40.95
ROUGE-2	14.18
ROUGE-L	27.42

Downloads last month: 14

SZTAKI-HLT
/

Bert2Bert-HunSum-2

Model Card for Bert2Bert-HunSum-2

Intended uses & limitations

Parameters

Results

Dataset used to train SZTAKI-HLT/Bert2Bert-HunSum-2