Instructions to use meta-llama/Llama-3.2-11B-Vision 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 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")

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("meta-llama/Llama-3.2-11B-Vision")
model = AutoModelForMultimodalLM.from_pretrained("meta-llama/Llama-3.2-11B-Vision", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use meta-llama/Llama-3.2-11B-Vision 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"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "meta-llama/Llama-3.2-11B-Vision",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/meta-llama/Llama-3.2-11B-Vision

SGLang

How to use meta-llama/Llama-3.2-11B-Vision 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" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "meta-llama/Llama-3.2-11B-Vision",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "meta-llama/Llama-3.2-11B-Vision",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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

What broken open source model is not used by Chinese people? What kind of open source model is it if you don't use it? Let's call it a closed source model!

#41

by hanson888 - opened Oct 16, 2024

Discussion

hanson888

Oct 16, 2024

What broken open source model is not used by Chinese people? What kind of open source model is it if you don't use it? Let's call it a closed source model!

nxsimon

Nov 25, 2024

yeah, that is focusing on qwen. this is disrespectful, we all contribute to the community, from what i've seen, most contributions are actually from Chinese. what a shame!!!

hanson888

Nov 25, 2024

What do you mean?

jacksims

Mar 6, 2025

What do you mean?

I am applying to get access meta-llama at Huggingface but after I submit my application I got a reject "Your request to access this repo has been rejected by the repo's authors." , I don't know why and how to fix this. Can any body explain why I got rejected and may be reapply again? after that i know all chinese be rejected !

hanson888

Mar 6, 2025

Now it is not important to use or not, deepseek v3 and r1 large models come out directly to hit all models including gpt and claude series, this llama model does not matter.

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