Instructions to use google/gemma-2-2b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/gemma-2-2b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="google/gemma-2-2b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-2b") model = AutoModelForCausalLM.from_pretrained("google/gemma-2-2b") - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use google/gemma-2-2b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "google/gemma-2-2b" # 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-2-2b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/google/gemma-2-2b
- SGLang
How to use google/gemma-2-2b 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 "google/gemma-2-2b" \ --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-2-2b", "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-2-2b" \ --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-2-2b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use google/gemma-2-2b with Docker Model Runner:
docker model run hf.co/google/gemma-2-2b
Request: DOI
1
#38 opened 3 months ago
by
bachvnju
API Test Discussion for Comment Testing
2
#37 opened 5 months ago
by
121tester
pulli
#36 opened 6 months ago
by
CloudCat56
Request: DOI
1
#35 opened over 1 year ago
by
amirhosseinehsani
Approval Process Duration
👍 2
15
#34 opened over 1 year ago
by
danbigioi
Error: 'System role not supported' when using gemma-2-2b with chat templates
3
#28 opened over 1 year ago
by
sbhctashi
Gemma 2 2b not authorized
1
#27 opened over 1 year ago
by
KareenaNS
Question about Gemma2:2b system prompt template and usage in Langflow
1
#26 opened over 1 year ago
by
MarcusWey
TypeError: 'HybridCache' object is not subscriptable
1
#24 opened over 1 year ago
by
muxiao
Gemma2-2b training uses much more momory!
2
#23 opened over 1 year ago
by
bubbleseller
resources needed
2
#22 opened almost 2 years ago
by
himanshuyadav62
No quantized tflite version of the model
1
#20 opened almost 2 years ago
by
stopthinking
How to generate the modeling_gemma2.py file from diff_gemma2.py
1
#19 opened almost 2 years ago
by
Asap7772
Weird output based on example code
❤️➕ 6
5
#18 opened almost 2 years ago
by
mark100
OSError: You are trying to access a gated repo.
2
#14 opened almost 2 years ago
by
anothercoder2
Problem with Lora finetuning, Out of memory
3
#13 opened almost 2 years ago
by
zokica
inference error
1
#12 opened almost 2 years ago
by
ccbbdd
What is the context length?
2
#11 opened almost 2 years ago
by
Embered