Instructions to use kadirnar/Llama3.3-70b-Vision with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kadirnar/Llama3.3-70b-Vision with Transformers:

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

pipe = pipeline("text-generation", model="kadirnar/Llama3.3-70b-Vision", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("kadirnar/Llama3.3-70b-Vision", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use kadirnar/Llama3.3-70b-Vision with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kadirnar/Llama3.3-70b-Vision"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kadirnar/Llama3.3-70b-Vision",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kadirnar/Llama3.3-70b-Vision

SGLang

How to use kadirnar/Llama3.3-70b-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 "kadirnar/Llama3.3-70b-Vision" \
    --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": "kadirnar/Llama3.3-70b-Vision",
		"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 "kadirnar/Llama3.3-70b-Vision" \
        --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": "kadirnar/Llama3.3-70b-Vision",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use kadirnar/Llama3.3-70b-Vision with Docker Model Runner:
```
docker model run hf.co/kadirnar/Llama3.3-70b-Vision
```

Llama-3.2-1B-Vision(development process continues)

A vision-enhanced version of the Llama-3.3-70B language model, capable of understanding and describing images while maintaining the base model's language capabilities.

Model Details

Base Model: Llama-3.3-70B
Model Type: Vision-Language Model
Last Updated: December ?, 2024
Model Architecture: Llama architecture with SigLIP vision encoder

Downloads last month: 18

Safetensors

Model size

71B params

Tensor type

BF16

Model tree for kadirnar/Llama3.3-70b-Vision

Base model

meta-llama/Llama-3.1-70B

Finetuned

meta-llama/Llama-3.3-70B-Instruct

Finetuned

(608)

this model