Instructions to use keizer69/moondream-flowmind with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries
PEFT
How to use keizer69/moondream-flowmind with PEFT:
```
Base model is not found.
```

How to use keizer69/moondream-flowmind with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="keizer69/moondream-flowmind", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("keizer69/moondream-flowmind", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use keizer69/moondream-flowmind with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "keizer69/moondream-flowmind"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "keizer69/moondream-flowmind",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/keizer69/moondream-flowmind

SGLang

How to use keizer69/moondream-flowmind 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 "keizer69/moondream-flowmind" \
    --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": "keizer69/moondream-flowmind",
		"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 "keizer69/moondream-flowmind" \
        --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": "keizer69/moondream-flowmind",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use keizer69/moondream-flowmind with Docker Model Runner:
```
docker model run hf.co/keizer69/moondream-flowmind
```

moondream-flowmind

File size: 799 Bytes

9a2b6bf

{
  "architectures": [
    "Moondream"
  ],
  "auto_map": {
    "AutoConfig": "configuration_moondream.MoondreamConfig",
    "AutoModelForCausalLM": "moondream.Moondream"
  },
  "dtype": "float16",
  "model_type": "moondream1",
  "text_config": {
    "attention_dropout": 0.0,
    "embd_pdrop": 0.0,
    "hidden_act": "gelu_new",
    "hidden_size": 2048,
    "initializer_range": 0.02,
    "intermediate_size": 8192,
    "layer_norm_eps": 1e-05,
    "max_position_embeddings": 2048,
    "model_type": "phi",
    "num_attention_heads": 32,
    "num_hidden_layers": 24,
    "num_key_value_heads": 32,
    "partial_rotary_factor": 0.5,
    "resid_pdrop": 0.0,
    "rope_scaling": null,
    "rope_theta": 10000.0,
    "use_cache": true,
    "vocab_size": 51200
  },
  "transformers_version": "4.57.6"
}