Instructions to use VisGym/visgym_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use VisGym/visgym_model with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="VisGym/visgym_model")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("VisGym/visgym_model", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use VisGym/visgym_model with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "VisGym/visgym_model" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "VisGym/visgym_model", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/VisGym/visgym_model
- SGLang
How to use VisGym/visgym_model 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 "VisGym/visgym_model" \ --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": "VisGym/visgym_model", "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 "VisGym/visgym_model" \ --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": "VisGym/visgym_model", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use VisGym/visgym_model with Docker Model Runner:
docker model run hf.co/VisGym/visgym_model
Ctrl+K
- colorization
- counting
- fetch_pick_place
- fetch_reach
- jigsaw
- matchstick_equation
- matchstick_rotation
- maze_2d
- maze_3d
- mental_rotation_2d
- mental_rotation_3d_cube
- mental_rotation_3d_objaverse
- mixed
- mixed_freeze_language
- mixed_freeze_vision
- mixed_qwen3vl
- patch_reassembly
- refdot
- sliding_block
- video_unshuffle
- zoom_in_puzzle
- 2.91 kB
- 1.85 kB