Image-Text-to-Text
Transformers
Safetensors
Vietnamese
English
GOT
feature-extraction
got
vision-language
ocr2.0
got_vietnamese
custom_code
Instructions to use tadkt/GOT_Vietnamese with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tadkt/GOT_Vietnamese with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="tadkt/GOT_Vietnamese", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("tadkt/GOT_Vietnamese", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use tadkt/GOT_Vietnamese with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "tadkt/GOT_Vietnamese" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "tadkt/GOT_Vietnamese", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/tadkt/GOT_Vietnamese
- SGLang
How to use tadkt/GOT_Vietnamese 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 "tadkt/GOT_Vietnamese" \ --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": "tadkt/GOT_Vietnamese", "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 "tadkt/GOT_Vietnamese" \ --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": "tadkt/GOT_Vietnamese", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use tadkt/GOT_Vietnamese with Docker Model Runner:
docker model run hf.co/tadkt/GOT_Vietnamese
Update modeling_GOT.py
#1
by htrnguyen - opened
No description provided.
Can you describe this error please?
I have a fault when used on google colab and when it is repaired, it works normally
I faced the issue: AttributeError: 'DynamicCache' object has no attribute 'get_max_length'. How can I solve it?
I faced the issue: AttributeError: 'DynamicCache' object has no attribute 'get_max_length'. How can I solve it?
You need to replace themax_cache_length = Nonein line 401 in file modeling_GOT.py is okay
tadkt changed pull request status to merged
Merged. Can you guys check if the problem is now solved. Thank guys