Instructions to use RedHatAI/granite-3.1-2b-base-FP8-dynamic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use RedHatAI/granite-3.1-2b-base-FP8-dynamic with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="RedHatAI/granite-3.1-2b-base-FP8-dynamic")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("RedHatAI/granite-3.1-2b-base-FP8-dynamic") model = AutoModelForCausalLM.from_pretrained("RedHatAI/granite-3.1-2b-base-FP8-dynamic") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use RedHatAI/granite-3.1-2b-base-FP8-dynamic with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "RedHatAI/granite-3.1-2b-base-FP8-dynamic" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "RedHatAI/granite-3.1-2b-base-FP8-dynamic", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/RedHatAI/granite-3.1-2b-base-FP8-dynamic
- SGLang
How to use RedHatAI/granite-3.1-2b-base-FP8-dynamic 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 "RedHatAI/granite-3.1-2b-base-FP8-dynamic" \ --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": "RedHatAI/granite-3.1-2b-base-FP8-dynamic", "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 "RedHatAI/granite-3.1-2b-base-FP8-dynamic" \ --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": "RedHatAI/granite-3.1-2b-base-FP8-dynamic", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use RedHatAI/granite-3.1-2b-base-FP8-dynamic with Docker Model Runner:
docker model run hf.co/RedHatAI/granite-3.1-2b-base-FP8-dynamic
Commit History
Update README.md 0d4e980 verified
Update README.md 9e2e4de verified
Update README.md 891df40 verified
Update README.md bb96ea6 verified
Update README.md 0f12672 verified
Update README.md 1a350b6 verified
Update README.md a131fcb verified
Update README.md 79efea7 verified
Create README.md 4618a5f verified
Upload model files ab028eb
Shubhra Pandit commited on