Instructions to use google/codegemma-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/codegemma-7b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="google/codegemma-7b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("google/codegemma-7b") model = AutoModelForCausalLM.from_pretrained("google/codegemma-7b") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use google/codegemma-7b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "google/codegemma-7b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "google/codegemma-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/google/codegemma-7b
- SGLang
How to use google/codegemma-7b 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/codegemma-7b" \ --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/codegemma-7b", "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/codegemma-7b" \ --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/codegemma-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use google/codegemma-7b with Docker Model Runner:
docker model run hf.co/google/codegemma-7b
How can I finetune?
#12
by Mic-k3y - opened
Is there any doc that I can use to help me fine-tune this model?
Hi Currently, the Gemma Cookbook contains three tutorials on fine-tuning the Gemma model:
Finetune_with_XTuner.ipynb
Finetune_with_Axolotl.ipynb
Finetune_with_LLaMA_Factory.ipynb
Kindly find this three tutorials on fine-tuning, and let me know if you any concern. Thank you.
Yes, I can confirm that I have been able to access the tutorials and didn't encounter any issues.