Instructions to use moondream/moondream-next with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use moondream/moondream-next with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="moondream/moondream-next", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("moondream/moondream-next", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use moondream/moondream-next with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "moondream/moondream-next" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "moondream/moondream-next", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/moondream/moondream-next
- SGLang
How to use moondream/moondream-next 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 "moondream/moondream-next" \ --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": "moondream/moondream-next", "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 "moondream/moondream-next" \ --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": "moondream/moondream-next", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use moondream/moondream-next with Docker Model Runner:
docker model run hf.co/moondream/moondream-next
Download summary_fixed.json from moondream/moondream-next: direct link, hf CLI and curl.
- Browser
- Download file 2.97 kB
-
https://huggingface.co/moondream/moondream-next/resolve/main/summary_fixed.json
- Command line
-
hf download hf://moondream/moondream-next/summary_fixed.json
-
curl -L -o summary_fixed.json https://huggingface.co/moondream/moondream-next/resolve/main/summary_fixed.json
2.97 kB
| { | |
| "after": { | |
| "dtype_counts": { | |
| "torch.bfloat16": 742, | |
| "torch.bool": 48, | |
| "torch.float32": 40, | |
| "torch.float8_e4m3fn": 40 | |
| }, | |
| "expert_count": 40, | |
| "expert_dtype_counts": { | |
| "torch.float8_e4m3fn": 40 | |
| }, | |
| "keys": 870, | |
| "scale_count": 40, | |
| "scale_dtype_counts": { | |
| "torch.float32": 40 | |
| } | |
| }, | |
| "before": { | |
| "dtype_counts": { | |
| "torch.bfloat16": 622, | |
| "torch.bool": 48, | |
| "torch.float32": 160, | |
| "torch.float8_e4m3fn": 40 | |
| }, | |
| "expert_count": 40, | |
| "expert_dtype_counts": { | |
| "torch.float8_e4m3fn": 40 | |
| }, | |
| "keys": 870, | |
| "scale_count": 40, | |
| "scale_dtype_counts": { | |
| "torch.float32": 40 | |
| } | |
| }, | |
| "converted_nonexpert_float_tensors": 120, | |
| "default": { | |
| "dtype_counts": { | |
| "torch.bfloat16": 742, | |
| "torch.bool": 48, | |
| "torch.float32": 40, | |
| "torch.float8_e4m3fn": 40 | |
| }, | |
| "expert_count": 40, | |
| "expert_dtype_counts": { | |
| "torch.float8_e4m3fn": 40 | |
| }, | |
| "keys": 870, | |
| "scale_count": 40, | |
| "scale_dtype_counts": { | |
| "torch.float32": 40 | |
| } | |
| }, | |
| "default_counts": { | |
| "dtype_counts": { | |
| "torch.bfloat16": 742, | |
| "torch.bool": 48, | |
| "torch.float32": 40, | |
| "torch.float8_e4m3fn": 40 | |
| }, | |
| "expert_count": 40, | |
| "expert_dtype_counts": { | |
| "torch.float8_e4m3fn": 40 | |
| }, | |
| "keys": 870, | |
| "scale_count": 40, | |
| "scale_dtype_counts": { | |
| "torch.float32": 40 | |
| } | |
| }, | |
| "default_size": 10505451019, | |
| "default_zip_layout": { | |
| "entries": 876, | |
| "payload_size": 10505277740 | |
| }, | |
| "final_counts": { | |
| "dtype_counts": { | |
| "torch.bfloat16": 742, | |
| "torch.bool": 48, | |
| "torch.float32": 40, | |
| "torch.float8_e4m3fn": 40 | |
| }, | |
| "expert_count": 40, | |
| "expert_dtype_counts": { | |
| "torch.float8_e4m3fn": 40 | |
| }, | |
| "keys": 870, | |
| "scale_count": 40, | |
| "scale_dtype_counts": { | |
| "torch.float32": 40 | |
| } | |
| }, | |
| "final_output": "/workspace/runs/mdnext-fp8-repair/model_fp8.pt", | |
| "final_sha256": "e1acbd3f5eb8a1e74c7500b8a85051483de0406fa847eae35d53ce4032bb6ac7", | |
| "final_size": 10505451019, | |
| "final_size_delta_vs_default": 0, | |
| "final_zip_layout": { | |
| "entries": 876, | |
| "payload_size": 10505277740 | |
| }, | |
| "output_sha256": "dc627b35f59dd6a1c5d38e28df0f228c257ea151c2822a48667b127896e83f2e", | |
| "output_size": 10505451251, | |
| "resaved_output": "/workspace/runs/mdnext-fp8-repair/model_fp8.pt", | |
| "resaved_output_size": 10505446139, | |
| "resaved_sha256": "790875f0726f64f4e76bf6cb7ad7d996b16ce13818cc806981f9a9cd26647aff", | |
| "resaved_size_delta_vs_default": -4880, | |
| "saved": { | |
| "dtype_counts": { | |
| "torch.bfloat16": 742, | |
| "torch.bool": 48, | |
| "torch.float32": 40, | |
| "torch.float8_e4m3fn": 40 | |
| }, | |
| "expert_count": 40, | |
| "expert_dtype_counts": { | |
| "torch.float8_e4m3fn": 40 | |
| }, | |
| "keys": 870, | |
| "scale_count": 40, | |
| "scale_dtype_counts": { | |
| "torch.float32": 40 | |
| } | |
| }, | |
| "size_delta_vs_default": 232 | |
| } | |