Instructions to use llamaindex/vdr-2b-multi-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use llamaindex/vdr-2b-multi-v1 with sentence-transformers:

from sentence_transformers import SentenceTransformer

model = SentenceTransformer("llamaindex/vdr-2b-multi-v1")

sentences = [
    "The weather is lovely today.",
    "It's so sunny outside!",
    "He drove to the stadium."
]
embeddings = model.encode(sentences)

similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Transformers

How to use llamaindex/vdr-2b-multi-v1 with Transformers:

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

pipe = pipeline("image-text-to-text", model="llamaindex/vdr-2b-multi-v1")
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, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("llamaindex/vdr-2b-multi-v1")
model = AutoModelForMultimodalLM.from_pretrained("llamaindex/vdr-2b-multi-v1", 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 llamaindex/vdr-2b-multi-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "llamaindex/vdr-2b-multi-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "llamaindex/vdr-2b-multi-v1",
		"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/llamaindex/vdr-2b-multi-v1

SGLang

How to use llamaindex/vdr-2b-multi-v1 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 "llamaindex/vdr-2b-multi-v1" \
    --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": "llamaindex/vdr-2b-multi-v1",
		"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 "llamaindex/vdr-2b-multi-v1" \
        --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": "llamaindex/vdr-2b-multi-v1",
		"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 llamaindex/vdr-2b-multi-v1 with Docker Model Runner:
```
docker model run hf.co/llamaindex/vdr-2b-multi-v1
```

cheesyFishes commited on Jan 9, 2025

Commit

c43084e

verified ·

1 Parent(s): 0da786d

cpu default, fix args

Browse files

Files changed (1) hide show

custom_st.py +8 -19

custom_st.py CHANGED Viewed

@@ -24,8 +24,10 @@ class Transformer(nn.Module):
         max_seq_length: Optional[int] = None,
         model_args: Optional[Dict[str, Any]] = None,
         processor_args: Optional[Dict[str, Any]] = None,
         cache_dir: Optional[str] = None,
-        device: str = 'cuda:0',
         backend: Literal['torch', 'onnx', 'openvino'] = 'torch',
         **kwargs,
     ) -> None:
@@ -54,24 +56,11 @@ class Transformer(nn.Module):
         })
         # Initialize model
-        try:
-            self.model = Qwen2VLForConditionalGeneration.from_pretrained(
-                model_name_or_path,
-                attn_implementation="flash_attention_2",
-                torch_dtype=torch.bfloat16,
-                device_map=device,
-                cache_dir=cache_dir,
-                **model_kwargs
-            ).eval()
-        except (ImportError, ValueError) as e:
-            print(f"Flash attention not available, falling back to default attention: {e}")
-            self.model = Qwen2VLForConditionalGeneration.from_pretrained(
-                model_name_or_path,
-                torch_dtype=torch.bfloat16,
-                device_map=device,
-                cache_dir=cache_dir,
-                **model_kwargs
-            ).eval()
         # Initialize processor
         self.processor = AutoProcessor.from_pretrained(

         max_seq_length: Optional[int] = None,
         model_args: Optional[Dict[str, Any]] = None,
         processor_args: Optional[Dict[str, Any]] = None,
+        tokenizer_args: Optional[Dict[str, Any]] = None,
+        config_args: Optional[Dict[str, Any]] = None,
         cache_dir: Optional[str] = None,
+        device: str = 'cpu',
         backend: Literal['torch', 'onnx', 'openvino'] = 'torch',
         **kwargs,
     ) -> None:
         })
         # Initialize model
+        self.model = Qwen2VLForConditionalGeneration.from_pretrained(
+            model_name_or_path,
+            cache_dir=cache_dir,
+            **model_kwargs
+        ).eval()
         # Initialize processor
         self.processor = AutoProcessor.from_pretrained(