Image-Text-to-Text
Transformers
TensorBoard
Safetensors
vision-encoder-decoder
Generated from Trainer
Instructions to use Sans1807/working with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Sans1807/working with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="Sans1807/working")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("Sans1807/working") model = AutoModelForMultimodalLM.from_pretrained("Sans1807/working", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Sans1807/working with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Sans1807/working" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Sans1807/working", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Sans1807/working
- SGLang
How to use Sans1807/working 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 "Sans1807/working" \ --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": "Sans1807/working", "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 "Sans1807/working" \ --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": "Sans1807/working", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Sans1807/working with Docker Model Runner:
docker model run hf.co/Sans1807/working
Download Dataset-plat-nomor-TrOCR-4100.zip from Sans1807/working: direct link, hf CLI and curl.
- Browser
- Download file 182 MB
-
https://huggingface.co/Sans1807/working/resolve/main/Dataset-plat-nomor-TrOCR-4100.zip
- Command line
-
hf download hf://Sans1807/working/Dataset-plat-nomor-TrOCR-4100.zip
-
curl -L -o Dataset-plat-nomor-TrOCR-4100.zip https://huggingface.co/Sans1807/working/resolve/main/Dataset-plat-nomor-TrOCR-4100.zip
182 MB
- Xet hash:
- f38c304494f586e6a7ecffaf6fcdccb24541ddb4f5b51d850b77fb17eda24f3b
- Size of remote file:
- 182 MB
- SHA256:
- 5f8b19221eb59c927d4875359ed397c4f81c884cc3b7958569decf51b3095f7a
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.