Instructions to use yuchenxie/Arlow-Vision-Encoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use yuchenxie/Arlow-Vision-Encoder with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="yuchenxie/Arlow-Vision-Encoder")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("yuchenxie/Arlow-Vision-Encoder", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use yuchenxie/Arlow-Vision-Encoder with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "yuchenxie/Arlow-Vision-Encoder" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "yuchenxie/Arlow-Vision-Encoder", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/yuchenxie/Arlow-Vision-Encoder
- SGLang
How to use yuchenxie/Arlow-Vision-Encoder 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 "yuchenxie/Arlow-Vision-Encoder" \ --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": "yuchenxie/Arlow-Vision-Encoder", "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 "yuchenxie/Arlow-Vision-Encoder" \ --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": "yuchenxie/Arlow-Vision-Encoder", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use yuchenxie/Arlow-Vision-Encoder with Docker Model Runner:
docker model run hf.co/yuchenxie/Arlow-Vision-Encoder
| { | |
| "_last_selected_frame_indices": [], | |
| "do_convert_rgb": true, | |
| "do_normalize": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "do_sample_frames": true, | |
| "image_mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "max_frames": 96, | |
| "max_volume": 786432, | |
| "merge_size": 2, | |
| "min_frames": 4, | |
| "motion_threshold": 0.1, | |
| "patch_size": 14, | |
| "resample": 3, | |
| "rescale_factor": 0.00392156862745098, | |
| "return_metadata": false, | |
| "sample_strategy": "uniform", | |
| "size": { | |
| "longest_edge": 786432, | |
| "shortest_edge": 131072 | |
| }, | |
| "temporal_patch_size": 2, | |
| "video_processor_type": "ArlowVideoProcessor" | |
| } | |