Instructions to use YangyiYY/SOLO-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use YangyiYY/SOLO-7B with Transformers:

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

pipe = pipeline("text-generation", model="YangyiYY/SOLO-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("YangyiYY/SOLO-7B")
model = AutoModelForCausalLM.from_pretrained("YangyiYY/SOLO-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use YangyiYY/SOLO-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "YangyiYY/SOLO-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "YangyiYY/SOLO-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/YangyiYY/SOLO-7B

SGLang

How to use YangyiYY/SOLO-7B 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 "YangyiYY/SOLO-7B" \
    --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": "YangyiYY/SOLO-7B",
		"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 "YangyiYY/SOLO-7B" \
        --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": "YangyiYY/SOLO-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use YangyiYY/SOLO-7B with Docker Model Runner:
```
docker model run hf.co/YangyiYY/SOLO-7B
```

SOLO Model Card

Model details

Model type: SOLO is a 7B large vision-language model with a single Transformer architecture for unified vision-language modeling. SOLO accepts both raw image patches (in pixels) and texts as inputs, without using a separate pre-trained vision encoder.

Model date: SOLO-7B was trained in June 2024.

Paper or resources for more information: Paper & Github

Where to send questions or comments about the model: https://github.com/Yangyi-Chen/SOLO/issues

Inference with Huggingface Please check this scripts for an example of performing inference on the model.

Downloads last month: 97

Safetensors

Model size

7B params

Tensor type

BF16

Paper for YangyiYY/SOLO-7B

A Single Transformer for Scalable Vision-Language Modeling

Paper • 2407.06438 • Published Jul 8, 2024 • 1