Instructions to use Xkev/Llama-3.2V-11B-cot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Xkev/Llama-3.2V-11B-cot with Transformers:

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

pipe = pipeline("image-text-to-text", model="Xkev/Llama-3.2V-11B-cot")
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("Xkev/Llama-3.2V-11B-cot")
model = AutoModelForImageTextToText.from_pretrained("Xkev/Llama-3.2V-11B-cot")
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

vLLM

How to use Xkev/Llama-3.2V-11B-cot with vLLM:

Install from pip and serve model

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

SGLang

How to use Xkev/Llama-3.2V-11B-cot 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 "Xkev/Llama-3.2V-11B-cot" \
    --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": "Xkev/Llama-3.2V-11B-cot",
		"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 "Xkev/Llama-3.2V-11B-cot" \
        --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": "Xkev/Llama-3.2V-11B-cot",
		"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 Xkev/Llama-3.2V-11B-cot with Docker Model Runner:
```
docker model run hf.co/Xkev/Llama-3.2V-11B-cot
```

recourses needed to run this efficiently?

by Daemontatox - opened Nov 24, 2024

Discussion

Daemontatox

Nov 24, 2024

I can run the base Llama3.2 11b on single Nvidia L4 (24 vram) , whats the recommended amount to run this model efficiently?

Xkev

Owner Nov 26, 2024

I think you can run this model using the same resource as the base model. Feel free to contact me if you encounter any issues!

nudelbrot

Nov 26, 2024

for anyone trying this out, running on L4 is very slow (<10 tok/ sec). The speed on the HF space is much faster.

Daemontatox

Nov 26, 2024

•

edited Dec 13, 2024

@nudelbrot ofcourse the one on huggingface is faster its a rotating A100.

Daemontatox

Nov 26, 2024

@Xkev thank you , i was making , because when i was trying to host it on huggingface, it kept saying L4 is too low of a memory and i thought the COT requires more VRAM.

Daemontatox changed discussion status to closed Dec 13, 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