Instructions to use khhuang/chartve with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use khhuang/chartve with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="khhuang/chartve")# Load model directly from transformers import AutoTokenizer, AutoModelForImageTextToText tokenizer = AutoTokenizer.from_pretrained("khhuang/chartve") model = AutoModelForImageTextToText.from_pretrained("khhuang/chartve") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use khhuang/chartve with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "khhuang/chartve" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "khhuang/chartve", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/khhuang/chartve
- SGLang
How to use khhuang/chartve 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 "khhuang/chartve" \ --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": "khhuang/chartve", "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 "khhuang/chartve" \ --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": "khhuang/chartve", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use khhuang/chartve with Docker Model Runner:
docker model run hf.co/khhuang/chartve
khuangaf commited on
Commit ·
1257a6d
1
Parent(s): 83ab152
update readme
Browse files
README.md
CHANGED
|
@@ -51,7 +51,7 @@ binary_entail_prob_positive = torch.nn.functional.softmax(outputs['logits'].sque
|
|
| 51 |
```
|
| 52 |
|
| 53 |
### Citation
|
| 54 |
-
```
|
| 55 |
@misc{huang-etal-2023-do,
|
| 56 |
title = "Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioning",
|
| 57 |
author = "Huang, Kung-Hsiang and
|
|
@@ -63,7 +63,8 @@ binary_entail_prob_positive = torch.nn.functional.softmax(outputs['logits'].sque
|
|
| 63 |
Chang, Shih-Fu and
|
| 64 |
Ji, Heng",
|
| 65 |
year={2023},
|
|
|
|
| 66 |
archivePrefix={arXiv},
|
| 67 |
primaryClass={cs.CL}
|
| 68 |
-
}
|
| 69 |
-
```
|
|
|
|
| 51 |
```
|
| 52 |
|
| 53 |
### Citation
|
| 54 |
+
```bibtex
|
| 55 |
@misc{huang-etal-2023-do,
|
| 56 |
title = "Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioning",
|
| 57 |
author = "Huang, Kung-Hsiang and
|
|
|
|
| 63 |
Chang, Shih-Fu and
|
| 64 |
Ji, Heng",
|
| 65 |
year={2023},
|
| 66 |
+
eprint={2312.10160},
|
| 67 |
archivePrefix={arXiv},
|
| 68 |
primaryClass={cs.CL}
|
| 69 |
+
}
|
| 70 |
+
```
|