Instructions to use MBZUAI/GLaMM-GCG with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MBZUAI/GLaMM-GCG with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="MBZUAI/GLaMM-GCG")# Load model directly from transformers import AutoProcessor, AutoModelForCausalLM processor = AutoProcessor.from_pretrained("MBZUAI/GLaMM-GCG") model = AutoModelForCausalLM.from_pretrained("MBZUAI/GLaMM-GCG") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use MBZUAI/GLaMM-GCG with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "MBZUAI/GLaMM-GCG" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "MBZUAI/GLaMM-GCG", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/MBZUAI/GLaMM-GCG
- SGLang
How to use MBZUAI/GLaMM-GCG 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 "MBZUAI/GLaMM-GCG" \ --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": "MBZUAI/GLaMM-GCG", "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 "MBZUAI/GLaMM-GCG" \ --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": "MBZUAI/GLaMM-GCG", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use MBZUAI/GLaMM-GCG with Docker Model Runner:
docker model run hf.co/MBZUAI/GLaMM-GCG
Update README.md
Browse files
README.md
CHANGED
|
@@ -8,7 +8,7 @@ license: apache-2.0
|
|
| 8 |
GLaMM-GCG is the model specific to the Grounded Conversation Generation (GCG) task. It is finetuned of GranD-f dataset.
|
| 9 |
|
| 10 |
## 💻 Download
|
| 11 |
-
To get started with GLaMM-
|
| 12 |
```
|
| 13 |
git lfs install
|
| 14 |
git clone https://huggingface.co/MBZUAI/GLaMM-GCG
|
|
|
|
| 8 |
GLaMM-GCG is the model specific to the Grounded Conversation Generation (GCG) task. It is finetuned of GranD-f dataset.
|
| 9 |
|
| 10 |
## 💻 Download
|
| 11 |
+
To get started with GLaMM-GCG, follow these steps:
|
| 12 |
```
|
| 13 |
git lfs install
|
| 14 |
git clone https://huggingface.co/MBZUAI/GLaMM-GCG
|