Instructions to use meta-llama/Llama-3.2-11B-Vision-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use meta-llama/Llama-3.2-11B-Vision-Instruct with Transformers:

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

pipe = pipeline("image-text-to-text", model="meta-llama/Llama-3.2-11B-Vision-Instruct")
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, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("meta-llama/Llama-3.2-11B-Vision-Instruct")
model = AutoModelForMultimodalLM.from_pretrained("meta-llama/Llama-3.2-11B-Vision-Instruct", 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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use meta-llama/Llama-3.2-11B-Vision-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "meta-llama/Llama-3.2-11B-Vision-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "meta-llama/Llama-3.2-11B-Vision-Instruct",
		"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/meta-llama/Llama-3.2-11B-Vision-Instruct

SGLang

How to use meta-llama/Llama-3.2-11B-Vision-Instruct 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 "meta-llama/Llama-3.2-11B-Vision-Instruct" \
    --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": "meta-llama/Llama-3.2-11B-Vision-Instruct",
		"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 "meta-llama/Llama-3.2-11B-Vision-Instruct" \
        --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": "meta-llama/Llama-3.2-11B-Vision-Instruct",
		"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 meta-llama/Llama-3.2-11B-Vision-Instruct with Docker Model Runner:
```
docker model run hf.co/meta-llama/Llama-3.2-11B-Vision-Instruct
```

Llama-3.2-11B-Vision-Instruct and Llama-3.2-11B-Vision results are exactly same, coincidentally or it's same model?

#25

by aaditya - opened Sep 26, 2024

Discussion

aaditya

Sep 26, 2024

I benchmarked the model on several datasets, and I noticed that the results were identical, including the floating-point details.

aaditya changed discussion title from Llama-3.2-90B-Vision-Instruct and Llama-3.2-90B-Vision results are exactly same, coincidentally or it's same model? to Llama-3.2-11B-Vision-Instruct and Llama-3.2-11B-Vision results are exactly same, coincidentally or it's same model? Sep 26, 2024

Sanyam

Sep 26, 2024

Both share the same Base, the instruct Model was taught Instruction-Following after the base model was trained

wukaixingxp

Sep 26, 2024

@aaditya Can you tell me more what benchmark did you run? How did you run them and what result did you get? Thanks!

aaditya

Sep 26, 2024

•

edited Sep 26, 2024

Both share the same Base, the instruct Model was taught Instruction-Following after the base model was trained

@Sanyam Yes, you're absolutely right. However, after fine-tuning the base model, isn't it common for performance to change slightly, whether it's an improvement or a slight decline?

aaditya

Sep 26, 2024

@wukaixingxp I evaluated the medical benchmark multimedqa, which includes 9 different datasets, using lm-harness. I tried twice and got the same results both times, though I acknowledge there could be a possibility of an error on my part.

wukaixingxp

Sep 26, 2024

@aaditya Can you tell me the command you used to run the eval? what number did you get? Thanks!

aaditya

Sep 26, 2024

Hi @wukaixingxp Here are the details:

command for Llama-3.2-11B-Vision

lm_eval --model hf \ --model_args pretrained=meta-llama/Llama-3.2-11B-Vision \ --tasks multimedqa \ --device cuda:0 \ --batch_size auto \ --output_path results --log_samples

Result on single A100:

command for Llama-3.2-11B-Vision-Instruct

lm_eval --model hf \ --model_args pretrained=meta-llama/Llama-3.2-11B-Vision-Instruct \ --tasks multimedqa \ --device cuda:0 \ --batch_size auto \ --output_path results --log_samples

Result on single A100:

wukaixingxp

Sep 27, 2024

@aaditya For instruct model please use --apply_chat_template option to get the special token like <|start_header_id|>user<|end_header_id|> added. Let me know if that works.

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