Instructions to use lmms-lab/LongVA-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lmms-lab/LongVA-7B with Transformers:

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

pipe = pipeline("text-generation", model="lmms-lab/LongVA-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("lmms-lab/LongVA-7B")
model = AutoModelForCausalLM.from_pretrained("lmms-lab/LongVA-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use lmms-lab/LongVA-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lmms-lab/LongVA-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lmms-lab/LongVA-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/lmms-lab/LongVA-7B

SGLang

How to use lmms-lab/LongVA-7B 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 "lmms-lab/LongVA-7B" \
    --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": "lmms-lab/LongVA-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "lmms-lab/LongVA-7B" \
        --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": "lmms-lab/LongVA-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use lmms-lab/LongVA-7B with Docker Model Runner:
```
docker model run hf.co/lmms-lab/LongVA-7B
```

TypeError: unsupported operand type(s) for //: 'int' and 'NoneType' while calling the processor

by dutta18 - opened Jan 26

Discussion

dutta18

Jan 26

TypeError Traceback (most recent call last)
Cell In[3], line 17
15 image_file = "http://images.cocodataset.org/val2017/000000039769.jpg"
16 raw_image = Image.open(requests.get(image_file, stream=True).raw)
---> 17 inputs = processor(images=raw_image, text=prompt, return_tensors='pt').to(0, torch.float16)
19 output = model.generate(**inputs, max_new_tokens=200, do_sample=False)
20 print(processor.decode(output[0][2:], skip_special_tokens=True))

File ~/miniconda3/envs/stable_env/lib/python3.9/site-packages/transformers/models/llava/processing_llava.py:156, in LlavaProcessor.call(self, images, text, audio, videos, **kwargs)
154 pixel_values = image_inputs["pixel_values"]
155 height, width = get_image_size(to_numpy_array(pixel_values[0]))
--> 156 num_image_tokens = (height // self.patch_size) * (
157 width // self.patch_size
158 ) + self.num_additional_image_tokens
159 if self.vision_feature_select_strategy == "default":
160 num_image_tokens -= 1

TypeError: unsupported operand type(s) for //: 'int' and 'NoneType'

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