Instructions to use YanweiLi/MGM-2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use YanweiLi/MGM-2B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="YanweiLi/MGM-2B") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("YanweiLi/MGM-2B", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use YanweiLi/MGM-2B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "YanweiLi/MGM-2B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "YanweiLi/MGM-2B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/YanweiLi/MGM-2B
- SGLang
How to use YanweiLi/MGM-2B 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 "YanweiLi/MGM-2B" \ --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": "YanweiLi/MGM-2B", "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 "YanweiLi/MGM-2B" \ --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": "YanweiLi/MGM-2B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use YanweiLi/MGM-2B with Docker Model Runner:
docker model run hf.co/YanweiLi/MGM-2B
Use MGM to represent Mini-Gemini
Browse files
README.md
CHANGED
|
@@ -45,4 +45,7 @@ The primary use is research on large multimodal models and chatbots.
|
|
| 45 |
The primary intended users of the model are researchers and hobbyists in computer vision, natural language processing, machine learning, and artificial intelligence.
|
| 46 |
|
| 47 |
## Training data
|
| 48 |
-
This model is trained based on [MGM-Instruction](https://huggingface.co/datasets/YanweiLi/MGM-Instruction) dataset, please to the [Github](https://github.com/dvlab-research/MGM) for more detail.
|
|
|
|
|
|
|
|
|
|
|
|
| 45 |
The primary intended users of the model are researchers and hobbyists in computer vision, natural language processing, machine learning, and artificial intelligence.
|
| 46 |
|
| 47 |
## Training data
|
| 48 |
+
This model is trained based on [MGM-Instruction](https://huggingface.co/datasets/YanweiLi/MGM-Instruction) dataset, please to the [Github](https://github.com/dvlab-research/MGM) for more detail.
|
| 49 |
+
|
| 50 |
+
## Acknowledgement
|
| 51 |
+
This project is not affiliated with Google LLC.
|