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)

# 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

hmellor HF Staff commited on Mar 27

Commit

c1628a7

1 Parent(s): 11b3064

Update configuration_ernie4_5_vl.py (#13)

Browse files

- Update configuration_ernie4_5_vl.py (f3fad3f0e4a3658a1847f5d46b6d409e591ba79c)

Co-authored-by: Harry Mellor <hmellor@users.noreply.huggingface.co>

Files changed (1) hide show

configuration_ernie4_5_vl.py +2 -3

configuration_ernie4_5_vl.py CHANGED Viewed

@@ -429,14 +429,12 @@ class Ernie4_5_MoEConfig(Ernie4_5_Config):
         Note:
             When use_recompute_moe is True, recompute_granularity will be changed to full_attn.
         """
         if use_recompute_moe:
             logger.warning(
                 "set `use_recompute_moe`=True, disabling `recompute_granularity=full`, change to full_attn."
             )
             if kwargs["recompute"] and kwargs["recompute_granularity"] == "full":
                 kwargs["recompute_granularity"] = "full_attn"
-        super().__init__(**kwargs)
         self.moe_num_experts = moe_num_experts
         self.use_recompute_moe = use_recompute_moe
@@ -476,6 +474,7 @@ class Ernie4_5_MoEConfig(Ernie4_5_Config):
         )
         self.moe_use_hard_gate = moe_use_hard_gate
         self.moe_dense_experts_token_type_id = moe_dense_experts_token_type_id
     @property
     def multimodel_experts(self) -> bool:
@@ -581,7 +580,6 @@ class Ernie4_5_VLMoEConfig(Ernie4_5_MoEConfig):
         tensor_parallel_degree=1,
         **kwargs,
     ):
-        super().__init__(**kwargs)
         if isinstance(vision_config, dict):
             self.vision_config = DFNRopeVisionTransformerConfig(**vision_config)
         else:
@@ -612,6 +610,7 @@ class Ernie4_5_VLMoEConfig(Ernie4_5_MoEConfig):
         self.moe_layer_feed_fake_token = moe_layer_feed_fake_token
         self.tensor_parallel_degree = tensor_parallel_degree
     @property
     def multimodel_experts(self) -> bool:

         Note:
             When use_recompute_moe is True, recompute_granularity will be changed to full_attn.
         """
         if use_recompute_moe:
             logger.warning(
                 "set `use_recompute_moe`=True, disabling `recompute_granularity=full`, change to full_attn."
             )
             if kwargs["recompute"] and kwargs["recompute_granularity"] == "full":
                 kwargs["recompute_granularity"] = "full_attn"
         self.moe_num_experts = moe_num_experts
         self.use_recompute_moe = use_recompute_moe
         )
         self.moe_use_hard_gate = moe_use_hard_gate
         self.moe_dense_experts_token_type_id = moe_dense_experts_token_type_id
+        super().__init__(**kwargs)
     @property
     def multimodel_experts(self) -> bool:
         tensor_parallel_degree=1,
         **kwargs,
     ):
         if isinstance(vision_config, dict):
             self.vision_config = DFNRopeVisionTransformerConfig(**vision_config)
         else:
         self.moe_layer_feed_fake_token = moe_layer_feed_fake_token
         self.tensor_parallel_degree = tensor_parallel_degree
+        super().__init__(**kwargs)
     @property
     def multimodel_experts(self) -> bool: