Instructions to use baidu/ERNIE-4.5-VL-28B-A3B-PT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use baidu/ERNIE-4.5-VL-28B-A3B-PT 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-PT", 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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForMultimodalLM
model = AutoModelForMultimodalLM.from_pretrained("baidu/ERNIE-4.5-VL-28B-A3B-PT", trust_remote_code=True, device_map="auto")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use baidu/ERNIE-4.5-VL-28B-A3B-PT 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-PT"
# 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-PT",
		"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-PT

SGLang

How to use baidu/ERNIE-4.5-VL-28B-A3B-PT 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-PT" \
    --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-PT",
		"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-PT" \
        --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-PT",
		"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-PT with Docker Model Runner:
```
docker model run hf.co/baidu/ERNIE-4.5-VL-28B-A3B-PT
```

SFLY5 commited on Jul 18, 2025

Commit

00a4006

verified ·

1 Parent(s): 71fbd01

Update modeling_ernie_45t_vl.py

Browse files

Files changed (1) hide show

modeling_ernie_45t_vl.py +5 -1

modeling_ernie_45t_vl.py CHANGED Viewed

@@ -1634,7 +1634,11 @@ class MOELayer(nn.Module):
         S, H = x.shape
         E = gate_logits.shape[1]
         device = x.device
-        topk_prob, topk_idx = torch.topk(gate_logits, k, dim=-1)  # [S, k]
         combine_weights = topk_prob  # [S, k]
         expert_id = topk_idx  # [S, k]
         y = x.new_zeros((E, capacity, H))  # [E, C, H]

         S, H = x.shape
         E = gate_logits.shape[1]
         device = x.device
+        if self.use_correction_bias:
+            _, topk_idx = torch.topk(gate_logits + self.moe_statics.e_score_correction_bias[0].detach().to(gate_logits.device), k, dim=-1)
+            topk_prob = torch.gather(gate_logits, dim=1, index=topk_idx) #  [Seq, k]
+        else:
+            topk_prob, topk_idx = torch.topk(gate_logits, k, dim=-1)  # [S, k]
         combine_weights = topk_prob  # [S, k]
         expert_id = topk_idx  # [S, k]
         y = x.new_zeros((E, capacity, H))  # [E, C, H]