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
```

Repo access request rejected?

#65

by deleted - opened Feb 1, 2025

Discussion

deleted

Feb 1, 2025

I requested access to the Llama 3.2 repo and it was rejected. Access was granted through the Meta website... but I'm finding that the hugging face script to convert Meta's model checkpoint files to hf format using convert_llama_weights_to_hf.py, because "11B" is not a supported model_size, as in, it's not in the dict called NUM_SHARDS.
(1) Why would I have been immediately rejected from this repo? I literally just created a hf account to access these models in hf format, or so I thought, and if it's open access on the meta site, why not here?
(2) Is there another way to convert Meta's version of llama 3.2 11B vision to hf format?

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