Instructions to use vikhyatk/moondream1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use vikhyatk/moondream1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="vikhyatk/moondream1", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("vikhyatk/moondream1", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use vikhyatk/moondream1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "vikhyatk/moondream1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "vikhyatk/moondream1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/vikhyatk/moondream1
- SGLang
How to use vikhyatk/moondream1 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 "vikhyatk/moondream1" \ --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": "vikhyatk/moondream1", "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 "vikhyatk/moondream1" \ --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": "vikhyatk/moondream1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use vikhyatk/moondream1 with Docker Model Runner:
docker model run hf.co/vikhyatk/moondream1
PhiForCasualLM Issue
#16 opened 8 months ago
by
kXborg
proposed patch for the Tensor size mismatch error
#15 opened over 1 year ago
by
claverAI
Error while downloading the model
1
#14 opened about 2 years ago
by
shishimanu
Troubleshooting Tensor Dimension Mismatch
1
#13 opened about 2 years ago
by
dankoyy
Error in downloading file
1
#12 opened about 2 years ago
by
PoyBoi
Batched inference?
#11 opened over 2 years ago
by
snimu
What's the minimum system requirement's to run it locally?
2
#10 opened over 2 years ago
by
Tarunasnani
Fine tuning moondream1
👍 2
#9 opened over 2 years ago
by
Inje
add pipeline
9
#6 opened over 2 years ago
by
not-lain
I'd like to see a GGUF version of this
❤️ 5
3
#5 opened over 2 years ago
by
iplayfast
Could you use phi 2 for your next model?
#4 opened over 2 years ago
by
distantquant
How much did it cost in Compute?
🤝 1
2
#3 opened over 2 years ago
by
iter8
Quants
7
#1 opened over 2 years ago
by
CyberTimon