Instructions to use WaveMatrix/PaddleOCR-VL-1.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use WaveMatrix/PaddleOCR-VL-1.5 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="WaveMatrix/PaddleOCR-VL-1.5")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("WaveMatrix/PaddleOCR-VL-1.5", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use WaveMatrix/PaddleOCR-VL-1.5 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "WaveMatrix/PaddleOCR-VL-1.5" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "WaveMatrix/PaddleOCR-VL-1.5", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/WaveMatrix/PaddleOCR-VL-1.5
- SGLang
How to use WaveMatrix/PaddleOCR-VL-1.5 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 "WaveMatrix/PaddleOCR-VL-1.5" \ --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": "WaveMatrix/PaddleOCR-VL-1.5", "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 "WaveMatrix/PaddleOCR-VL-1.5" \ --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": "WaveMatrix/PaddleOCR-VL-1.5", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use WaveMatrix/PaddleOCR-VL-1.5 with Docker Model Runner:
docker model run hf.co/WaveMatrix/PaddleOCR-VL-1.5
Download config.json from WaveMatrix/PaddleOCR-VL-1.5: direct link, hf CLI and curl.
- Browser
- Download file 958 Bytes
-
https://huggingface.co/WaveMatrix/PaddleOCR-VL-1.5/resolve/main/config.json
- Command line
-
hf download hf://WaveMatrix/PaddleOCR-VL-1.5/config.json
-
curl -L -o config.json https://huggingface.co/WaveMatrix/PaddleOCR-VL-1.5/resolve/main/config.json
958 Bytes
| { | |
| "system_prompt": "You are PaddleOCR-VL, a helpful OCR assistant.", | |
| "model_name": "WaveMatrix/PaddleOCR-VL-1.5", | |
| "url_tokenizer_model": "paddleocr_vl_tokenizer.txt", | |
| "tokenizer_type": "PaddleOCRVL", | |
| "post_config_path": "post_config.json", | |
| "template_filename_axmodel": "paddleocr_vl_p128_l%d_together.axmodel", | |
| "axmodel_num": 18, | |
| "filename_post_axmodel": "paddleocr_vl_post.axmodel", | |
| "filename_tokens_embed": "model.embed_tokens.weight.bfloat16.bin", | |
| "tokens_embed_num": 103424, | |
| "tokens_embed_size": 1024, | |
| "use_mmap_load_embed": true, | |
| "vlm_type": "PaddleOCRVL", | |
| "filename_image_encoder_axmodel": "vit_576x768.axmodel", | |
| "vision_patch_size": 14, | |
| "vision_temporal_patch_size": 1, | |
| "vision_spatial_merge_size": 2, | |
| "vision_fps": 1, | |
| "vision_tokens_per_second": 2, | |
| "vision_cache_dir": "vision_cache", | |
| "server_max_output_tokens": 1152, | |
| "server_forced_prompt_text": "OCR:", | |
| "use_mmap_load_layer": true, | |
| "devices": [0] | |
| } | |