Instructions to use menglc/SliMM-DeepStackE-Qwen2VL-2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use menglc/SliMM-DeepStackE-Qwen2VL-2B with Transformers:

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

pipe = pipeline("image-text-to-text", model="menglc/SliMM-DeepStackE-Qwen2VL-2B")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForSeq2SeqLM

processor = AutoProcessor.from_pretrained("menglc/SliMM-DeepStackE-Qwen2VL-2B")
model = AutoModelForSeq2SeqLM.from_pretrained("menglc/SliMM-DeepStackE-Qwen2VL-2B", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use menglc/SliMM-DeepStackE-Qwen2VL-2B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "menglc/SliMM-DeepStackE-Qwen2VL-2B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "menglc/SliMM-DeepStackE-Qwen2VL-2B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/menglc/SliMM-DeepStackE-Qwen2VL-2B

SGLang

How to use menglc/SliMM-DeepStackE-Qwen2VL-2B 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 "menglc/SliMM-DeepStackE-Qwen2VL-2B" \
    --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": "menglc/SliMM-DeepStackE-Qwen2VL-2B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "menglc/SliMM-DeepStackE-Qwen2VL-2B" \
        --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": "menglc/SliMM-DeepStackE-Qwen2VL-2B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use menglc/SliMM-DeepStackE-Qwen2VL-2B with Docker Model Runner:
```
docker model run hf.co/menglc/SliMM-DeepStackE-Qwen2VL-2B
```

menglc commited on Dec 13, 2024

Commit

b2a7ef6

verified ·

1 Parent(s): 5eba8a1

Update README.md

Browse files

Files changed (1) hide show

README.md +8 -1

README.md CHANGED Viewed

@@ -91,9 +91,16 @@ print(output_text)
 |----------------------------------------------------------|------------|----------------|-------------|-------------|
 |Qwen2VL-2B (official evaluation)                          |41.1        | 73.5           |74.7         |90.1         |
 |Qwen2VL-2B (our evaluation, 1024 max vistokens to LLM)    |39.4        | 75.6           |70.7         |90.4         |
-|SliMM-DeepStackE-Qwen2VL-0.5B (320 max vistokens to LLM)  |40.7        | 74.5           |74.7         |85.4         |
 |SliMM-DeepStackE-Qwen2VL-0.5B (400 max vistokens to LLM)  |41.2        | 76.8           |74.9         |88.0         |
 ## 🔗 Citation
 If you find our work helpful, please consider citing our paper :paperclip: and starring our repo :star2: :

 |----------------------------------------------------------|------------|----------------|-------------|-------------|
 |Qwen2VL-2B (official evaluation)                          |41.1        | 73.5           |74.7         |90.1         |
 |Qwen2VL-2B (our evaluation, 1024 max vistokens to LLM)    |39.4        | 75.6           |70.7         |90.4         |
+|SliMM-DeepStackE-Qwen2VL-0.5B (256 max vistokens to LLM)  |40.7        | 74.5           |74.7         |85.4         |
 |SliMM-DeepStackE-Qwen2VL-0.5B (400 max vistokens to LLM)  |41.2        | 76.8           |74.9         |88.0         |
+<p align="left">
+    <img src="https://cdn-uploads.huggingface.co/production/uploads/64d852a4bab152b2470bf96e/dtVzPkcIp40oH8sg7MG_u.png" alt="Trade-off between N Vistokens for LLM and Acc" style="width:500px;" >  <br>
+</p>
 ## 🔗 Citation
 If you find our work helpful, please consider citing our paper :paperclip: and starring our repo :star2: :