Instructions to use llava-hf/vip-llava-7b-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use llava-hf/vip-llava-7b-hf with Transformers:

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

pipe = pipeline("image-text-to-text", model="llava-hf/vip-llava-7b-hf")
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 AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("llava-hf/vip-llava-7b-hf")
model = AutoModelForImageTextToText.from_pretrained("llava-hf/vip-llava-7b-hf")
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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use llava-hf/vip-llava-7b-hf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "llava-hf/vip-llava-7b-hf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "llava-hf/vip-llava-7b-hf",
		"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/llava-hf/vip-llava-7b-hf

SGLang

How to use llava-hf/vip-llava-7b-hf 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 "llava-hf/vip-llava-7b-hf" \
    --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": "llava-hf/vip-llava-7b-hf",
		"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 "llava-hf/vip-llava-7b-hf" \
        --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": "llava-hf/vip-llava-7b-hf",
		"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 llava-hf/vip-llava-7b-hf with Docker Model Runner:
```
docker model run hf.co/llava-hf/vip-llava-7b-hf
```

RuntimeError: Error(s) in loading state_dict for LlavaForConditionalGeneration

by floschne - opened Feb 5, 2024

Discussion

floschne

Feb 5, 2024

Hi,

I am getting the folloing error when trying to load the model:

  File "/home/aiscuser/lmmm/./scripts/eval/eval_xgqa.py", line 64, in load_model
    LlavaForConditionalGeneration.from_pretrained(
  File "/home/aiscuser/miniforge3/envs/lmmm/lib/python3.10/site-packages/transformers/modeling_utils.py", line 3852, in from_pretrained
    ) = cls._load_pretrained_model(
  File "/home/aiscuser/miniforge3/envs/lmmm/lib/python3.10/site-packages/transformers/modeling_utils.py", line 4337, in _load_pretrained_model
    raise RuntimeError(f"Error(s) in loading state_dict for {model.__class__.__name__}:\n\t{error_msg}")
RuntimeError: Error(s) in loading state_dict for LlavaForConditionalGeneration:
        size mismatch for multi_modal_projector.linear_1.weight: copying a param with shape torch.Size([4096, 5120]) from checkpoint, the shape in current model is torch.Size([4096, 1024]).
        You may consider adding `ignore_mismatched_sizes=True` in the model `from_pretrained` method.

nielsr

Llava Hugging Face org Feb 5, 2024

Hi,

You need to use the VipLlavaForConditionalGeneration class to load the weights, not LlavaForConditionalGeneration.

floschne

Feb 5, 2024

Oh, thanks! I totally overlooked this...

floschne changed discussion status to closed Feb 5, 2024

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment