Instructions to use baidu/ERNIE-4.5-VL-28B-A3B-Thinking with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use baidu/ERNIE-4.5-VL-28B-A3B-Thinking with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="baidu/ERNIE-4.5-VL-28B-A3B-Thinking", trust_remote_code=True) 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)# Load model directly from transformers import AutoModelForMultimodalLM model = AutoModelForMultimodalLM.from_pretrained("baidu/ERNIE-4.5-VL-28B-A3B-Thinking", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use baidu/ERNIE-4.5-VL-28B-A3B-Thinking with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "baidu/ERNIE-4.5-VL-28B-A3B-Thinking" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "baidu/ERNIE-4.5-VL-28B-A3B-Thinking", "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/baidu/ERNIE-4.5-VL-28B-A3B-Thinking
- SGLang
How to use baidu/ERNIE-4.5-VL-28B-A3B-Thinking 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 "baidu/ERNIE-4.5-VL-28B-A3B-Thinking" \ --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": "baidu/ERNIE-4.5-VL-28B-A3B-Thinking", "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 "baidu/ERNIE-4.5-VL-28B-A3B-Thinking" \ --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": "baidu/ERNIE-4.5-VL-28B-A3B-Thinking", "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 baidu/ERNIE-4.5-VL-28B-A3B-Thinking with Docker Model Runner:
docker model run hf.co/baidu/ERNIE-4.5-VL-28B-A3B-Thinking
I don't understand how this broken model became popular.
demo no work and no GPU
demo no work and no GPU
what's your query?
demo no work and no GPU
what's your query?
I just tested it, but Space still doesn't have a GPU and isn't working properly.
Please add GPU support to Space.
demo no work and no GPU
what's your query?
this https://huggingface.co/spaces/baidu/ERNIE-4.5-VL-28B-A3B-Thinking
demo no work and no GPU
what's your query?
I tested it again, and it seems to be a bug, not a GPU issue.
It answers questions correctly when no image is added.
But it freezes when an image is added.
demo no work and no GPU
what's your query?
I tested it again, and it seems to be a bug, not a GPU issue.
It answers questions correctly when no image is added.
But it freezes when an image is added.
Zero issues here using space https://huggingface.co/spaces/baidu/ERNIE-4.5-VL-28B-A3B-Thinking:
Took it about 60 seconds but it did respond.
demo no work and no GPU
what's your query?
I tested it again, and it seems to be a bug, not a GPU issue.
It answers questions correctly when no image is added.
But it freezes when an image is added.
Zero issues here using space https://huggingface.co/spaces/baidu/ERNIE-4.5-VL-28B-A3B-Thinking:
Took it about 60 seconds but it did respond.
Okay, I see.
Could you make it output its thought process? So that people won't think it's stuck.