Instructions to use tiny-random/step3-vl with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tiny-random/step3-vl with Transformers:

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

pipe = pipeline("text-generation", model="tiny-random/step3-vl", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForSeq2SeqLM
model = AutoModelForSeq2SeqLM.from_pretrained("tiny-random/step3-vl", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tiny-random/step3-vl with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tiny-random/step3-vl"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tiny-random/step3-vl",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tiny-random/step3-vl

SGLang

How to use tiny-random/step3-vl 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 "tiny-random/step3-vl" \
    --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": "tiny-random/step3-vl",
		"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 "tiny-random/step3-vl" \
        --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": "tiny-random/step3-vl",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tiny-random/step3-vl with Docker Model Runner:
```
docker model run hf.co/tiny-random/step3-vl
```

step3-vl / special_tokens_map.json

yujiepan

Upload folder using huggingface_hub

429214e verified 6 months ago

Raw

History Blame Contribute Delete

5.6 kB

	{
	"additional_special_tokens": [
	{
	"content": "<\|im_start\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false
	},
	{
	"content": "<\|im_end\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false
	},
	{
	"content": "<\|object_ref_start\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false
	},
	{
	"content": "<\|object_ref_end\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false
	},
	{
	"content": "<\|box_start\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false
	},
	{
	"content": "<\|box_end\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false
	},
	{
	"content": "<\|quad_start\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false
	},
	{
	"content": "<\|quad_end\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false
	},
	{
	"content": "<\|vision_start\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false
	},
	{
	"content": "<\|vision_end\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false
	},
	{
	"content": "<\|vision_pad\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false
	},
	{
	"content": "<\|image_pad\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false
	},
	{
	"content": "<\|video_pad\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false
	},
	{
	"content": "<tool_calls>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false
	},
	{
	"content": "</tool_calls>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false
	},
	{
	"content": "<\|EOT\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false
	},
	{
	"content": "<\|BOT\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false
	},
	{
	"content": "<\|CALL_START\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false
	},
	{
	"content": "<\|CALL_END\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false
	},
	{
	"content": "<\|THINK_START\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false
	},
	{
	"content": "<\|THINK_END\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false
	},
	{
	"content": "<\|IMG_START\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false
	},
	{
	"content": "<\|IMG_END\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false
	},
	{
	"content": "<im_patch>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false
	},
	{
	"content": "<im_start>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false
	},
	{
	"content": "<im_end>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false
	},
	{
	"content": "<dream>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false
	},
	{
	"content": "<dream_start>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false
	},
	{
	"content": "<dream_end>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false
	},
	{
	"content": "<\|MASK_1e69f\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false
	},
	{
	"content": "<\|UNMASK_1e69f\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false
	},
	{
	"content": "<video_start>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false
	},
	{
	"content": "<video_end>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false
	},
	{
	"content": "<patch_start>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false
	},
	{
	"content": "<patch_end>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false
	},
	{
	"content": "<patch_newline>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false
	}
	],
	"eos_token": {
	"content": "<\|im_end\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false
	},
	"pad_token": {
	"content": "<\|endoftext\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false
	}
	}