Instructions to use TeeA/ViMATCHA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TeeA/ViMATCHA with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="TeeA/ViMATCHA")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("TeeA/ViMATCHA") model = AutoModelForMultimodalLM.from_pretrained("TeeA/ViMATCHA") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use TeeA/ViMATCHA with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "TeeA/ViMATCHA" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "TeeA/ViMATCHA", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/TeeA/ViMATCHA
- SGLang
How to use TeeA/ViMATCHA 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 "TeeA/ViMATCHA" \ --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": "TeeA/ViMATCHA", "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 "TeeA/ViMATCHA" \ --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": "TeeA/ViMATCHA", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use TeeA/ViMATCHA with Docker Model Runner:
docker model run hf.co/TeeA/ViMATCHA
| { | |
| "_name_or_path": "google/matcha-chartqa", | |
| "architectures": [ | |
| "Pix2StructForConditionalGeneration" | |
| ], | |
| "decoder_start_token_id": 0, | |
| "eos_token_id": 1, | |
| "initializer_factor": 1.0, | |
| "initializer_range": 0.02, | |
| "is_encoder_decoder": true, | |
| "is_vqa": false, | |
| "model_type": "pix2struct", | |
| "pad_token_id": 0, | |
| "text_config": { | |
| "encoder_hidden_size": 768, | |
| "initializer_range": 0.02, | |
| "model_type": "pix2struct_text_model", | |
| "vocab_size": 9497 | |
| }, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.40.1", | |
| "vision_config": { | |
| "initializer_range": 0.02, | |
| "layer_norm_bias": false, | |
| "model_type": "pix2struct_vision_model", | |
| "num_channels": 3, | |
| "patch_size": 16, | |
| "projection_dim": 768 | |
| } | |
| } | |