Instructions to use LanguageBind/MoE-LLaVA-StableLM-1.6B-4e-384 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LanguageBind/MoE-LLaVA-StableLM-1.6B-4e-384 with Transformers:

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

pipe = pipeline("text-generation", model="LanguageBind/MoE-LLaVA-StableLM-1.6B-4e-384", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("LanguageBind/MoE-LLaVA-StableLM-1.6B-4e-384", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use LanguageBind/MoE-LLaVA-StableLM-1.6B-4e-384 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LanguageBind/MoE-LLaVA-StableLM-1.6B-4e-384"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LanguageBind/MoE-LLaVA-StableLM-1.6B-4e-384",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/LanguageBind/MoE-LLaVA-StableLM-1.6B-4e-384

SGLang

How to use LanguageBind/MoE-LLaVA-StableLM-1.6B-4e-384 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 "LanguageBind/MoE-LLaVA-StableLM-1.6B-4e-384" \
    --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": "LanguageBind/MoE-LLaVA-StableLM-1.6B-4e-384",
		"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 "LanguageBind/MoE-LLaVA-StableLM-1.6B-4e-384" \
        --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": "LanguageBind/MoE-LLaVA-StableLM-1.6B-4e-384",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use LanguageBind/MoE-LLaVA-StableLM-1.6B-4e-384 with Docker Model Runner:
```
docker model run hf.co/LanguageBind/MoE-LLaVA-StableLM-1.6B-4e-384
```

what is the .bin file that is downloaded?

by sujitvasanth - opened Feb 10, 2024

Discussion

sujitvasanth

Feb 10, 2024

Hi I tried using the predict.py example and after the safetensors are dowlded a .bin file is downloaded bu cant find this in the cache... wat is this and why is it needed?
I'm able to programmatically save it but not the associated config file not even using dill

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