Instructions to use BAAI/Bunny-Llama-3-8B-V with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BAAI/Bunny-Llama-3-8B-V with Transformers:

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

pipe = pipeline("text-generation", model="BAAI/Bunny-Llama-3-8B-V", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("BAAI/Bunny-Llama-3-8B-V", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use BAAI/Bunny-Llama-3-8B-V with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BAAI/Bunny-Llama-3-8B-V"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BAAI/Bunny-Llama-3-8B-V",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/BAAI/Bunny-Llama-3-8B-V

SGLang

How to use BAAI/Bunny-Llama-3-8B-V 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 "BAAI/Bunny-Llama-3-8B-V" \
    --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": "BAAI/Bunny-Llama-3-8B-V",
		"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 "BAAI/Bunny-Llama-3-8B-V" \
        --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": "BAAI/Bunny-Llama-3-8B-V",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use BAAI/Bunny-Llama-3-8B-V with Docker Model Runner:
```
docker model run hf.co/BAAI/Bunny-Llama-3-8B-V
```

Isaachhe commited on Jun 1, 2024

Commit

e1c449a

1 Parent(s): 8d9c671

update

Browse files

Files changed (2) hide show

README.md +1 -1
comparison.png +0 -0

README.md CHANGED Viewed

@@ -13,7 +13,7 @@ license: apache-2.0
 This is Bunny-Llama-3-8B-V.
 Bunny is a family of lightweight but powerful multimodal models. It offers multiple plug-and-play vision encoders, like EVA-CLIP, SigLIP and language backbones, including Llama-3-8B, Phi-1.5, StableLM-2, Qwen1.5, MiniCPM and Phi-2. To compensate for the decrease in model size, we construct more informative training data by curated selection from a broader data source.

 This is Bunny-Llama-3-8B-V.
+We also provide v1.1 version accepting high-resolution images up to 1152x1152. 🤗 [v1.1](https://huggingface.co/BAAI/Bunny-v1_1-Llama-3-8B-V)
 Bunny is a family of lightweight but powerful multimodal models. It offers multiple plug-and-play vision encoders, like EVA-CLIP, SigLIP and language backbones, including Llama-3-8B, Phi-1.5, StableLM-2, Qwen1.5, MiniCPM and Phi-2. To compensate for the decrease in model size, we construct more informative training data by curated selection from a broader data source.

comparison.png CHANGED Viewed