Instructions to use BK-Lee/MoAI-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BK-Lee/MoAI-7B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="BK-Lee/MoAI-7B")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("BK-Lee/MoAI-7B", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use BK-Lee/MoAI-7B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "BK-Lee/MoAI-7B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "BK-Lee/MoAI-7B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/BK-Lee/MoAI-7B
- SGLang
How to use BK-Lee/MoAI-7B 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 "BK-Lee/MoAI-7B" \ --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": "BK-Lee/MoAI-7B", "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 "BK-Lee/MoAI-7B" \ --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": "BK-Lee/MoAI-7B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use BK-Lee/MoAI-7B with Docker Model Runner:
docker model run hf.co/BK-Lee/MoAI-7B
Add link to paper, pipeline tag
#7
by nielsr HF Staff - opened
README.md
CHANGED
|
@@ -1,7 +1,12 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
|
|
|
| 3 |
---
|
| 4 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
### Simple running code is based on [MoAI-Github](https://github.com/ByungKwanLee/MoAI).
|
| 6 |
|
| 7 |
You need only the following seven steps.
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
+
pipeline_tag: image-text-to-text
|
| 4 |
---
|
| 5 |
|
| 6 |
+
## MoAI model
|
| 7 |
+
|
| 8 |
+
This repository contains the weights of the model presented in [MoAI: Mixture of All Intelligence for Large Language and Vision Models](https://huggingface.co/papers/2403.07508).
|
| 9 |
+
|
| 10 |
### Simple running code is based on [MoAI-Github](https://github.com/ByungKwanLee/MoAI).
|
| 11 |
|
| 12 |
You need only the following seven steps.
|