Instructions to use apple/FastVLM-1.5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use apple/FastVLM-1.5B with Transformers:

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

pipe = pipeline("text-generation", model="apple/FastVLM-1.5B", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("apple/FastVLM-1.5B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use apple/FastVLM-1.5B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "apple/FastVLM-1.5B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "apple/FastVLM-1.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/apple/FastVLM-1.5B

SGLang

How to use apple/FastVLM-1.5B 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 "apple/FastVLM-1.5B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "apple/FastVLM-1.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "apple/FastVLM-1.5B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "apple/FastVLM-1.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use apple/FastVLM-1.5B with Docker Model Runner:
```
docker model run hf.co/apple/FastVLM-1.5B
```

FastVLM-1.5B / processor_config.json

JettChenT

Add custom processor for easier inference and mlx-vlm compatibility

ea79a1f 4 months ago

raw

history blame

1.09 kB

	{
	"chat_template": "{%- if messages is string -%}\n {{- messages -}}\n{%- else -%}\n {%- for message in messages -%}\n {%- if loop.first and messages[0]['role'] != 'system' -%}\n {{- '<\|im_start\|>system\\nYou are a helpful assistant.<\|im_end\|>\\n' -}}\n {%- endif -%}\n {{- '<\|im_start\|>' + message['role'] + '\\n' -}}\n {%- if message['content'] is string -%}\n {{- message['content'] -}}\n {%- elif message['content'] is iterable -%}\n {%- for item in message['content'] -%}\n {%- if item['type'] == 'image' -%}\n {{- '<image>\\n' -}}\n {%- elif item['type'] == 'text' -%}\n {{- item['text'] -}}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{- raise_exception(\"Invalid content type\") -}}\n {%- endif -%}\n {{- '<\|im_end\|>' + '\\n' -}}\n {%- endfor -%}\n {%- if add_generation_prompt -%}\n {{- '<\|im_start\|>assistant\\n' -}}\n {%- endif -%}\n{%- endif -%}\n"
	}