Instructions to use RUCAIBox/mvp-summarization with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use RUCAIBox/mvp-summarization with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="RUCAIBox/mvp-summarization")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("RUCAIBox/mvp-summarization", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use RUCAIBox/mvp-summarization with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "RUCAIBox/mvp-summarization" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "RUCAIBox/mvp-summarization", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/RUCAIBox/mvp-summarization
- SGLang
How to use RUCAIBox/mvp-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 "RUCAIBox/mvp-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": "RUCAIBox/mvp-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 "RUCAIBox/mvp-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": "RUCAIBox/mvp-summarization", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use RUCAIBox/mvp-summarization with Docker Model Runner:
docker model run hf.co/RUCAIBox/mvp-summarization
Commit ·
8b0bfb6
1
Parent(s): e82063b
Update README
Browse files
README.md
CHANGED
|
@@ -5,6 +5,7 @@ language:
|
|
| 5 |
tags:
|
| 6 |
- text-generation
|
| 7 |
- text2text-generation
|
|
|
|
| 8 |
pipeline_tag: text2text-generation
|
| 9 |
widget:
|
| 10 |
- text: "Summarize: You may want to stick it to your boss and leave your job, but don't do it if these are your reasons."
|
|
@@ -14,7 +15,7 @@ widget:
|
|
| 14 |
---
|
| 15 |
|
| 16 |
# MVP-summarization
|
| 17 |
-
The MVP-summarization model was proposed in [**MVP: Multi-task Supervised Pre-training for Natural Language Generation**](https://
|
| 18 |
|
| 19 |
The detailed information and instructions can be found [https://github.com/RUCAIBox/MVP](https://github.com/RUCAIBox/MVP).
|
| 20 |
|
|
@@ -39,4 +40,36 @@ MVP-summarization is specially designed for summarization tasks, such as new sum
|
|
| 39 |
["Don't do it if these are your reasons"]
|
| 40 |
```
|
| 41 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 42 |
## Citation
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
tags:
|
| 6 |
- text-generation
|
| 7 |
- text2text-generation
|
| 8 |
+
- summarization
|
| 9 |
pipeline_tag: text2text-generation
|
| 10 |
widget:
|
| 11 |
- text: "Summarize: You may want to stick it to your boss and leave your job, but don't do it if these are your reasons."
|
|
|
|
| 15 |
---
|
| 16 |
|
| 17 |
# MVP-summarization
|
| 18 |
+
The MVP-summarization model was proposed in [**MVP: Multi-task Supervised Pre-training for Natural Language Generation**](https://arxiv.org/abs/2206.12131) by Tianyi Tang, Junyi Li, Wayne Xin Zhao and Ji-Rong Wen.
|
| 19 |
|
| 20 |
The detailed information and instructions can be found [https://github.com/RUCAIBox/MVP](https://github.com/RUCAIBox/MVP).
|
| 21 |
|
|
|
|
| 40 |
["Don't do it if these are your reasons"]
|
| 41 |
```
|
| 42 |
|
| 43 |
+
## Related Models
|
| 44 |
+
**MVP**: [https://huggingface.co/RUCAIBox/mvp](https://huggingface.co/RUCAIBox/mvp).
|
| 45 |
+
|
| 46 |
+
**Prompt-based models**:
|
| 47 |
+
|
| 48 |
+
- MVP-multi-task: [https://huggingface.co/RUCAIBox/mvp-multi-task](https://huggingface.co/RUCAIBox/mvp-multi-task).
|
| 49 |
+
- MVP-summarization: [https://huggingface.co/RUCAIBox/mvp-summarization](https://huggingface.co/RUCAIBox/mvp-summarization).
|
| 50 |
+
- MVP-open-dialog: [https://huggingface.co/RUCAIBox/mvp-open-dialog](https://huggingface.co/RUCAIBox/mvp-open-dialog).
|
| 51 |
+
- MVP-data-to-text: [https://huggingface.co/RUCAIBox/mvp-data-to-text](https://huggingface.co/RUCAIBox/mvp-data-to-text).
|
| 52 |
+
- MVP-story: [https://huggingface.co/RUCAIBox/mvp-story](https://huggingface.co/RUCAIBox/mvp-story).
|
| 53 |
+
- MVP-question-answering: [https://huggingface.co/RUCAIBox/mvp-question-answering](https://huggingface.co/RUCAIBox/mvp-question-answering).
|
| 54 |
+
- MVP-question-generation: [https://huggingface.co/RUCAIBox/mvp-question-generation](https://huggingface.co/RUCAIBox/mvp-question-generation).
|
| 55 |
+
- MVP-task-dialog: [https://huggingface.co/RUCAIBox/mvp-task-dialog](https://huggingface.co/RUCAIBox/mvp-task-dialog).
|
| 56 |
+
|
| 57 |
+
**Multi-task models**:
|
| 58 |
+
- MTL-summarization: [https://huggingface.co/RUCAIBox/mtl-summarization](https://huggingface.co/RUCAIBox/mtl-summarization).
|
| 59 |
+
- MTL-open-dialog: [https://huggingface.co/RUCAIBox/mtl-open-dialog](https://huggingface.co/RUCAIBox/mtl-open-dialog).
|
| 60 |
+
- MTL-data-to-text: [https://huggingface.co/RUCAIBox/mtl-data-to-text](https://huggingface.co/RUCAIBox/mtl-data-to-text).
|
| 61 |
+
- MTL-story: [https://huggingface.co/RUCAIBox/mtl-story](https://huggingface.co/RUCAIBox/mtl-story).
|
| 62 |
+
- MTL-question-answering: [https://huggingface.co/RUCAIBox/mtl-question-answering](https://huggingface.co/RUCAIBox/mtl-question-answering).
|
| 63 |
+
- MTL-question-generation: [https://huggingface.co/RUCAIBox/mtl-question-generation](https://huggingface.co/RUCAIBox/mtl-question-generation).
|
| 64 |
+
- MTL-task-dialog: [https://huggingface.co/RUCAIBox/mtl-task-dialog](https://huggingface.co/RUCAIBox/mtl-task-dialog).
|
| 65 |
+
|
| 66 |
## Citation
|
| 67 |
+
```bibtex
|
| 68 |
+
@article{tang2022mvp,
|
| 69 |
+
title={MVP: Multi-task Supervised Pre-training for Natural Language Generation},
|
| 70 |
+
author={Tang, Tianyi and Li, Junyi and Zhao, Wayne Xin and Wen, Ji-Rong},
|
| 71 |
+
journal={arXiv preprint arXiv:2206.12131},
|
| 72 |
+
year={2022},
|
| 73 |
+
url={https://arxiv.org/abs/2206.12131},
|
| 74 |
+
}
|
| 75 |
+
```
|