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

Libraries

How to use vngrs/VBART-Medium-Base with Transformers:

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

pipe = pipeline("text-generation", model="vngrs/VBART-Medium-Base")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use vngrs/VBART-Medium-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "vngrs/VBART-Medium-Base"
# 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-Medium-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/vngrs/VBART-Medium-Base

SGLang

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

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

meliksahturker commited on Mar 23, 2024

Commit

1342f46

verified ·

1 Parent(s): 2829d03

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -2

README.md CHANGED Viewed

@@ -17,13 +17,12 @@ VBART is the first sequence-to-sequence LLM pre-trained on Turkish corpora from
 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 pre-trained TensorFlow and Safetensors weights of VBARTMedium-Base.
 - **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)
 ## Training Details

 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 pre-trained TensorFlow and Safetensors weights of VBART-Medium-Base.
 - **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
 - **Paper:** [arXiv](https://arxiv.org/abs/2403.01308)
 ## Training Details