Image-Text-to-Text
Transformers
Safetensors
multimodal
benchmark
vision-language
agentic-ai
business-ideation
qwen2-vl
Instructions to use hchoi256/mba with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use hchoi256/mba with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="hchoi256/mba")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("hchoi256/mba", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use hchoi256/mba with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "hchoi256/mba" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "hchoi256/mba", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/hchoi256/mba
- SGLang
How to use hchoi256/mba 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 "hchoi256/mba" \ --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": "hchoi256/mba", "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 "hchoi256/mba" \ --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": "hchoi256/mba", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use hchoi256/mba with Docker Model Runner:
docker model run hf.co/hchoi256/mba
Add pipeline tag, library name, and project page link
#1
by nielsr HF Staff - opened
This PR adds the correct pipeline_tag and library_name metadata to improve model discoverability and usage, and adds a link to the project page in the model card content.
Thanks for the PR! I’ve incorporated the suggested metadata and project page link directly into the model card on main. Appreciate the contribution!
hchoi256 changed pull request status to closed