Instructions to use vngrs/VBART-Large-Summarization with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vngrs/VBART-Large-Summarization with Transformers:

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

pipe = pipeline("text-generation", model="vngrs/VBART-Large-Summarization")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("vngrs/VBART-Large-Summarization")
model = AutoModelForSeq2SeqLM.from_pretrained("vngrs/VBART-Large-Summarization", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use vngrs/VBART-Large-Summarization with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/vngrs/VBART-Large-Summarization

SGLang

How to use vngrs/VBART-Large-Summarization 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 "vngrs/VBART-Large-Summarization" \
    --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": "vngrs/VBART-Large-Summarization",
		"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 "vngrs/VBART-Large-Summarization" \
        --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": "vngrs/VBART-Large-Summarization",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use vngrs/VBART-Large-Summarization with Docker Model Runner:
```
docker model run hf.co/vngrs/VBART-Large-Summarization
```

VBART-Large-Summarization / README.md

meliksahturker

Update README.md

3589e3d verified over 2 years ago

preview code

Raw History Blame Contribute Delete

4.19 kB

	---
	language:
	- tr
	inference:
	parameters:
	max_new_tokens: 32
	arXiv: 2403.01308
	library_name: transformers
	pipeline_tag: text2text-generation
	license: cc-by-nc-sa-4.0
	datasets:
	- vngrs-ai/vngrs-web-corpus
	---
	# VBART Model Card

	## Model Description

	VBART is the first sequence-to-sequence LLM pre-trained on Turkish corpora from scratch on a large scale. It was pre-trained by VNGRS in February 2023.
	The model is capable of conditional text generation tasks such as text summarization, paraphrasing, and title generation when fine-tuned.
	It outperforms its multilingual counterparts, albeit being much smaller than other implementations.

	This repository contains fine-tuned TensorFlow and Safetensors weights of VBART for text summarization task.

	- Developed by: [VNGRS-AI](https://vngrs.com/ai/)
	- Model type: Transformer encoder-decoder based on mBART architecture
	- Language(s) (NLP): Turkish
	- License: CC BY-NC-SA 4.0
	- Finetuned from: VBART-Large
	- Paper: [arXiv](https://arxiv.org/abs/2403.01308)
	## How to Get Started with the Model
	```python
	from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

	tokenizer = AutoTokenizer.from_pretrained("vngrs-ai/VBART-Large-Summarization",
	model_input_names=['input_ids', 'attention_mask'])
	# Uncomment the device_map kwarg and delete the closing bracket to use model for inference on GPU
	model = AutoModelForSeq2SeqLM.from_pretrained("vngrs-ai/VBART-Large-Summarization")#, device_map="auto")

	input_text="..."

	token_input = tokenizer(input_text, return_tensors="pt")#.to('cuda')
	outputs = model.generate(**token_input)
	print(tokenizer.decode(outputs[0]))
	```

	## Training Details
	### Training Data
	The base model is pre-trained on [vngrs-web-corpus](https://huggingface.co/datasets/vngrs-ai/vngrs-web-corpus). It is curated by cleaning and filtering Turkish parts of [OSCAR-2201](https://huggingface.co/datasets/oscar-corpus/OSCAR-2201) and [mC4](https://huggingface.co/datasets/mc4) datasets. These datasets consist of documents of unstructured web crawl data. More information about the dataset can be found on their respective pages. Data is filtered using a set of heuristics and certain rules, explained in the appendix of our [paper](https://arxiv.org/abs/2403.01308).

	The fine-tuning dataset is the Turkish sections of [MLSum](https://huggingface.co/datasets/mlsum), [TRNews](https://huggingface.co/datasets/batubayk/TR-News), [XLSum](https://huggingface.co/datasets/csebuetnlp/xlsum) and [Wikilingua](https://huggingface.co/datasets/wiki_lingua) datasets.

	### Limitations
	This model is fine-tuned for paraphrasing tasks. It is not intended to be used in any other case and can not be fine-tuned to any other task with full performance of the base model. It is also not guaranteed that this model will work without specified prompts.

	### Training Procedure
	Pre-trained for 30 days and for a total of 708B tokens. Finetuned for 30 epoch.
	#### Hardware
	- GPUs: 8 x Nvidia A100-80 GB
	#### Software
	- TensorFlow
	#### Hyperparameters
	##### Pretraining
	- Training regime: fp16 mixed precision
	- Training objective: Sentence permutation and span masking (using mask lengths sampled from Poisson distribution λ=3.5, masking 30% of tokens)
	- Optimizer : Adam optimizer (β1 = 0.9, β2 = 0.98, Ɛ = 1e-6)
	- Scheduler: Custom scheduler from the original Transformers paper (20,000 warm-up steps)
	- Dropout: 0.1 (dropped to 0.05 and then to 0 in the last 165k and 205k steps, respectively)
	- Initial Learning rate: 5e-6
	- Training tokens: 708B

	##### Fine-tuning
	- Training regime: fp16 mixed precision
	- Optimizer : Adam optimizer (β1 = 0.9, β2 = 0.98, Ɛ = 1e-6)
	- Scheduler: Linear decay scheduler
	- Dropout: 0.1
	- Learning rate: 1e-5
	- Fine-tune epochs: 20

	#### Metrics
	![image/png](https://cdn-uploads.huggingface.co/production/uploads/62f8b3c84588fe31f435a92b/RY1gfk_XVhMeWKI1-GuCi.png)

	## Citation
	```
	@article{turker2024vbart,
	title={VBART: The Turkish LLM},
	author={Turker, Meliksah and Ari, Erdi and Han, Aydin},
	journal={arXiv preprint arXiv:2403.01308},
	year={2024}
	}
	```