Instructions to use google/gemma-2-9b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/gemma-2-9b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="google/gemma-2-9b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-9b") model = AutoModelForCausalLM.from_pretrained("google/gemma-2-9b") - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use google/gemma-2-9b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "google/gemma-2-9b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "google/gemma-2-9b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/google/gemma-2-9b
- SGLang
How to use google/gemma-2-9b 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 "google/gemma-2-9b" \ --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": "google/gemma-2-9b", "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 "google/gemma-2-9b" \ --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": "google/gemma-2-9b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use google/gemma-2-9b with Docker Model Runner:
docker model run hf.co/google/gemma-2-9b
Gemma2FlashAttention2 missing sliding_window variable
#8
by emozilla - opened
Gemma2FlashAttention2.forward checks self.sliding_window, but this variable is not set in it's __init__ or in the __init__ of the parent Gemma2Attention, causing a crash when trying to use Flash Attention 2. Simple solution is to just add
self.sliding_window = self.config.sliding_window to Gemma2FlashAttention2.__init__ (line 303)
Where is Gemma2FlashAttention2.init
?